Activity cliffs(ACs)are generally defined as pairs of similar compounds that only differ by a minor structural modification but exhibit a large difference in their binding affinity for a given target.ACs offer crucial...Activity cliffs(ACs)are generally defined as pairs of similar compounds that only differ by a minor structural modification but exhibit a large difference in their binding affinity for a given target.ACs offer crucial insights that aid medicinal chemists in optimizing molecular structures.Nonetheless,they also form a major source of prediction error in structure-activity relationship(SAR)models.To date,several studies have demonstrated that deep neural networks based on molecular images or graphs might need to be improved further in predicting the potency of ACs.In this paper,we integrated the triplet loss in face recognition with pre-training strategy to develop a prediction model ACtriplet,tailored for ACs.Through extensive comparison with multiple baseline models on 30 benchmark datasets,the results showed that ACtriplet was significantly better than those deep learning(DL)models without pretraining.In addition,we explored the effect of pre-training on data representation.Finally,the case study demonstrated that our model's interpretability module could explain the prediction results reasonably.In the dilemma that the amount of data could not be increased rapidly,this innovative framework would better make use of the existing data,which would propel the potential of DL in the early stage of drug discovery and optimization.展开更多
With the continuous advancement of unmanned technology in various application domains,the development and deployment of blind-spot-free panoramic video systems have gained increasing importance.Such systems are partic...With the continuous advancement of unmanned technology in various application domains,the development and deployment of blind-spot-free panoramic video systems have gained increasing importance.Such systems are particularly critical in battlefield environments,where advanced panoramic video processing and wireless communication technologies are essential to enable remote control and autonomous operation of unmanned ground vehicles(UGVs).However,conventional video surveillance systems suffer from several limitations,including limited field of view,high processing latency,low reliability,excessive resource consumption,and significant transmission delays.These shortcomings impede the widespread adoption of UGVs in battlefield settings.To overcome these challenges,this paper proposes a novel multi-channel video capture and stitching system designed for real-time video processing.The system integrates the Speeded-Up Robust Features(SURF)algorithm and the Fast Library for Approximate Nearest Neighbors(FLANN)algorithm to execute essential operations such as feature detection,descriptor computation,image matching,homography estimation,and seamless image fusion.The fused panoramic video is then encoded and assembled to produce a seamless output devoid of stitching artifacts and shadows.Furthermore,H.264 video compression is employed to reduce the data size of the video stream without sacrificing visual quality.Using the Real-Time Streaming Protocol(RTSP),the compressed stream is transmitted efficiently,supporting real-time remote monitoring and control of UGVs in dynamic battlefield environments.Experimental results indicate that the proposed system achieves high stability,flexibility,and low latency.With a wireless link latency of 30 ms,the end-to-end video transmission latency remains around 140 ms,enabling smooth video communication.The system can tolerate packet loss rates(PLR)of up to 20%while maintaining usable video quality(with latency around 200 ms).These properties make it well-suited for mobile communication scenarios demanding high real-time video performance.展开更多
Scalable simulation leveraging real-world data plays an essential role in advancing autonomous driving,owing to its efficiency and applicability in both training and evaluating algorithms.Consequently,there has been i...Scalable simulation leveraging real-world data plays an essential role in advancing autonomous driving,owing to its efficiency and applicability in both training and evaluating algorithms.Consequently,there has been increasing attention on generating highly realistic and consistent driving videos,particularly those involving viewpoint changes guided by the control commands or trajectories of ego vehicles.However,current reconstruction approaches,such as Neural Radiance Fields and 3D Gaussian Splatting,frequently suffer from limited generalization and depend on substantial input data.Meanwhile,2D generative models,though capable of producing unknown scenes,still have room for improvement in terms of coherence and visual realism.To overcome these challenges,we introduce GenScene,a world model that synthesizes front-view driving videos conditioned on trajectories.A new temporal module is presented to improve video consistency by extracting the global context of each frame,calculating relationships of frames using these global representations,and fusing frame contexts accordingly.Moreover,we propose an innovative attention mechanism that computes relations of pixels within each frame and pixels in the corresponding window range of the initial frame.Extensive experiments show that our approach surpasses various state-of-the-art models in driving video generation,and the introduced modules contribute significantly to model performance.This work establishes a new paradigm for goal-oriented video synthesis in autonomous driving,which facilitates on-demand simulation to expedite algorithm development.展开更多
Background:This study aims to investigate the underlying mechanisms between parental marital conflict and adolescent short video dependence by constructing a chain mediation model,focusing on the mediating roles of ex...Background:This study aims to investigate the underlying mechanisms between parental marital conflict and adolescent short video dependence by constructing a chain mediation model,focusing on the mediating roles of experiential avoidance and emotional disturbance(anxiety,depression,and stress).Methods:Conducted in January 2025,the research recruited 4125 adolescents from multiple Chinese provinces through convenience sampling;after data cleaning,3957 valid participants(1959 males,1998 females)were included.Using a cross-sectional design,measures included parental marital conflict,experiential avoidance,anxiety,depression,stress,and short video dependence.Results:Pearson correlation analysis revealed significant positive correlations among all variables.Mediation analysis using the SPSS PROCESS macro showed that parental marital conflict directly predicted short video dependence(β=0.269,p<0.001),and also significantly predicted experiential avoidance(β=0.519,p<0.001),anxiety(β=0.072,p<0.001),depression(β=0.067,p<0.001),and stress(β=0.048,p<0.05).Experiential avoidance further predicted anxiety(β=0.521,p<0.001),depression(β=0.489,p<0.001),stress(β=0.408,p<0.001),and short video dependence(β=0.244,p<0.001).While both anxiety(β=0.050,p<0.05)and depression(β=0.116,p<0.001)positively predicted short video dependence,stress did not(β=0.019,p=0.257).Overall,experiential avoidance,anxiety,depression,and stress significantly mediated the relationship between parental marital conflict and short video dependence.Conclusion:These findings confirm that parental marital conflict not only directly influences adolescent short video dependence but also operates through a chain mediation pathway involving experiential avoidance and emotional disturbance,highlighting central psychological mechanisms and providing theoretical support for integrated mental health and behavioral interventions.展开更多
Background:In the Chinese context,the impact of short video applications on the psychological well-being of older adults is contested.While often examined through a pathological lens of addiction,this perspective may ...Background:In the Chinese context,the impact of short video applications on the psychological well-being of older adults is contested.While often examined through a pathological lens of addiction,this perspective may overlook paradoxical,context-dependent positive outcomes.Therefore,the main objective of this study is to challenge the traditional Compensatory Internet Use Theory by proposing and testing a chained mediation model that explores a paradoxical pathway from social support to life satisfaction via problematic social media use.Methods:Data were collected between July and August 2025 via the Credamo online survey platform,yielding 384 valid responses from Chinese older adults aged 60 and above.Key constructs were assessed using the Social Support Rating Scale(SSRS),Bergen Social Media Addiction Scale(BSMAS),Simplified UCLA Loneliness Scale,and Satisfaction with Life Scale(SWLS).A chained mediation model was tested using stepwise regression and non-parametric bootstrapping(5000 resamples),controlling for age,gender,household income,and health status.Results:The analysis revealed a paradoxical pathway,which was clarified by a key statistical suppression effect.Social support significantly and positively predicted problematic usage(β=0.157,p=0.002).After controlling for the suppressor effect of social support,problematic usage in turn negatively predicted social connectedness(β=−0.177,p<0.001).Finally,reduced social connectedness—reflecting a state of solitude—positively predicted life satisfaction(β=−0.227,p<0.001).Conclusion:The findings suggest that for older adults with sufficient offline social support,these resources may serve a“social empowerment”function.This empowerment allows behaviors measured as“problematic usage”to be theoretically reframed as a form of“deep immersive entertainment”.This immersion appears to occur alongside a state of“high-quality solitude”,which ultimately is associated with higher life satisfaction.This study provides a novel,non-pathological theoretical perspective on the consequences of high engagement with emerging social media,offering empirical grounds for non-abstinence-based intervention strategies.展开更多
How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classif...How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However,the training and testing of CNN mainly rely on single machine.Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure.When a model is complex or the training data is relatively small,overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore,Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Na¨?ve Bayes classifier, a distributed Na¨?ve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.展开更多
Vision-Language-Navigation(VLN) task is a cross-modality task that combines natural language processing and computer vision. This task requires the agent to automatically move to the destination according to the natur...Vision-Language-Navigation(VLN) task is a cross-modality task that combines natural language processing and computer vision. This task requires the agent to automatically move to the destination according to the natural language instruction and the observed surrounding visual information. To make the best decision, in every step during the navigation, the agent should pay more attention to understanding the objects, the object attributes, and the object relationships. But most current methods process all received textual and visual information equally. Therefore, this paper integrates more detailed semantic connections between visual and textual information through three pre-training tasks(object prediction, object attributes prediction, and object relationship prediction). The model will learn better fusion representation and alignment between these two types of information to improve the success rate(SR) and generalization. The experiments show that compared with the former baseline models, the SR on the unseen validation set(Val Unseen) increased by 7%, and the SR weighted by path length(SPL) increased by 7%;the SR on the test set(Test) increased 4%, SPL increased by 3%.展开更多
Web-based training is growing quickly in popularit y for professionals in industrial organizations and large enterprises. The savings in cost and time are significant. The instructor-led trainings are bounded by time ...Web-based training is growing quickly in popularit y for professionals in industrial organizations and large enterprises. The savings in cost and time are significant. The instructor-led trainings are bounded by time and place, not to mention the cost involved in traveling, accommodation and training venue. However, in the most online training courses, all trainees are given same training materials and teaching paradigms. The problem of differentia ting the trainees’ abilities is the main concern. We need a pre-training test t o identify and classify of the weaknesses and strengths of differentiate trainee s so as to devise an appropriate training programs for the trainees. Adaptation of a Web-based Computer adaptive Test (CAT) for the pre-training test make the web-based training more efficient. The advantages of CAT are self-pacing, eff iciency, time and cost saving, immediate scoring and feedback, accuracy and secu rity, etc (Rudner, 1998; UMN, 1999; Novell, 2000; Linacre, 2000; Windowsglore, 2 000). Moreover, Web-based CAT also gives greater flexibility and convenience. T his paper describes how this CAT tool is built, how it helps instructor identify the strengths and weaknesses of trainees, and how to assure quality on the CAT system.展开更多
Handheld ultrasound devices are known for their portability and affordability,making them widely utilized in underdeveloped areas and community healthcare for rapid diagnosis and early screening.However,the image qual...Handheld ultrasound devices are known for their portability and affordability,making them widely utilized in underdeveloped areas and community healthcare for rapid diagnosis and early screening.However,the image quality of handheld ultrasound devices is not always satisfactory due to the limited equipment size,which hinders accurate diagnoses by doctors.At the same time,paired ultrasound images are difficult to obtain from the clinic because imaging process is complicated.Therefore,we propose a modified cycle generative adversarial network(cycleGAN) for ultrasound image enhancement from multiple organs via unpaired pre-training.We introduce an ultrasound image pre-training method that does not require paired images,alleviating the requirement for large-scale paired datasets.We also propose an enhanced block with different structures in the pre-training and fine-tuning phases,which can help achieve the goals of different training phases.To improve the robustness of the model,we add Gaussian noise to the training images as data augmentation.Our approach is effective in obtaining the best quantitative evaluation results using a small number of parameters and less training costs to improve the quality of handheld ultrasound devices.展开更多
As important geological data,a geological report contains rich expert and geological knowledge,but the challenge facing current research into geological knowledge extraction and mining is how to render accurate unders...As important geological data,a geological report contains rich expert and geological knowledge,but the challenge facing current research into geological knowledge extraction and mining is how to render accurate understanding of geological reports guided by domain knowledge.While generic named entity recognition models/tools can be utilized for the processing of geoscience reports/documents,their effectiveness is hampered by a dearth of domain-specific knowledge,which in turn leads to a pronounced decline in recognition accuracy.This study summarizes six types of typical geological entities,with reference to the ontological system of geological domains and builds a high quality corpus for the task of geological named entity recognition(GNER).In addition,Geo Wo BERT-adv BGP(Geological Word-base BERTadversarial training Bi-directional Long Short-Term Memory Global Pointer)is proposed to address the issues of ambiguity,diversity and nested entities for the geological entities.The model first uses the fine-tuned word granularitybased pre-training model Geo Wo BERT(Geological Word-base BERT)and combines the text features that are extracted using the Bi LSTM(Bi-directional Long Short-Term Memory),followed by an adversarial training algorithm to improve the robustness of the model and enhance its resistance to interference,the decoding finally being performed using a global association pointer algorithm.The experimental results show that the proposed model for the constructed dataset achieves high performance and is capable of mining the rich geological information.展开更多
The rapid development of short video platforms poses new challenges for traditional recommendation systems.Recommender systems typically depend on two types of user behavior feedback to construct user interest profile...The rapid development of short video platforms poses new challenges for traditional recommendation systems.Recommender systems typically depend on two types of user behavior feedback to construct user interest profiles:explicit feedback(interactive behavior),which significantly influences users’short-term interests,and implicit feedback(viewing time),which substantially affects their long-term interests.However,the previous model fails to distinguish between these two feedback methods,leading it to predict only the overall preferences of users based on extensive historical behavior sequences.Consequently,it cannot differentiate between users’long-term and shortterm interests,resulting in low accuracy in describing users’interest states and predicting the evolution of their interests.This paper introduces a video recommendationmodel calledCAT-MFRec(CrossAttention Transformer-Mixed Feedback Recommendation)designed to differentiate between explicit and implicit user feedback within the DIEN(Deep Interest Evolution Network)framework.This study emphasizes the separate learning of the two types of behavioral feedback,effectively integrating them through the cross-attention mechanism.Additionally,it leverages the long sequence dependence capabilities of Transformer technology to accurately construct user interest profiles and predict the evolution of user interests.Experimental results indicate that CAT-MF Rec significantly outperforms existing recommendation methods across various performance indicators.This advancement offers new theoretical and practical insights for the development of video recommendations,particularly in addressing complex and dynamic user behavior patterns.展开更多
Internal learning-based video inpainting methods have shown promising results by exploiting the intrinsic properties of the video to fill in the missing region without external dataset supervision.However,existing int...Internal learning-based video inpainting methods have shown promising results by exploiting the intrinsic properties of the video to fill in the missing region without external dataset supervision.However,existing internal learning-based video inpainting methods would produce inconsistent structures or blurry textures due to the insufficient utilisation of motion priors within the video sequence.In this paper,the authors propose a new internal learning-based video inpainting model called appearance consistency and motion coherence network(ACMC-Net),which can not only learn the recurrence of appearance prior but can also capture motion coherence prior to improve the quality of the inpainting results.In ACMC-Net,a transformer-based appearance network is developed to capture global context information within the video frame for representing appearance consistency accurately.Additionally,a novel motion coherence learning scheme is proposed to learn the motion prior in a video sequence effectively.Finally,the learnt internal appearance consistency and motion coherence are implicitly propagated to the missing regions to achieve inpainting well.Extensive experiments conducted on the DAVIS dataset show that the proposed model obtains the superior performance in terms of quantitative measurements and produces more visually plausible results compared with the state-of-the-art methods.展开更多
Airway management plays a crucial role in providing adequate oxygenation and ventilation to patients during various medical procedures and emergencies.When patients have a limited mouth opening due to factors such as ...Airway management plays a crucial role in providing adequate oxygenation and ventilation to patients during various medical procedures and emergencies.When patients have a limited mouth opening due to factors such as trauma,inflammation,or anatomical abnormalities airway management becomes challenging.A commonly utilized method to overcome this challenge is the use of video laryngoscopy(VL),which employs a specialized device equipped with a camera and a light source to allow a clear view of the larynx and vocal cords.VL overcomes the limitations of direct laryngoscopy in patients with limited mouth opening,enabling better visualization and successful intubation.Various types of VL blades are available.We devised a novel flangeless video laryngoscope for use in patients with a limited mouth opening and then tested it on a manikin.展开更多
Semantic segmentation is a core task in computer vision that allows AI models to interact and understand their surrounding environment. Similarly to how humans subconsciously segment scenes, this ability is crucial fo...Semantic segmentation is a core task in computer vision that allows AI models to interact and understand their surrounding environment. Similarly to how humans subconsciously segment scenes, this ability is crucial for scene understanding. However, a challenge many semantic learning models face is the lack of data. Existing video datasets are limited to short, low-resolution videos that are not representative of real-world examples. Thus, one of our key contributions is a customized semantic segmentation version of the Walking Tours Dataset that features hour-long, high-resolution, real-world data from tours of different cities. Additionally, we evaluate the performance of open-vocabulary, semantic model OpenSeeD on our own custom dataset and discuss future implications.展开更多
Objective: The purpose of this study was to evaluate health education using videos and leaflets for preconception care (PCC) awareness among adolescent females up to six months after the health education. Methods: The...Objective: The purpose of this study was to evaluate health education using videos and leaflets for preconception care (PCC) awareness among adolescent females up to six months after the health education. Methods: The subjects were female university students living in the Kinki area. A longitudinal survey was conducted on 67 members in the intervention group, who received the health education, and 52 members in the control group, who did not receive the health education. The primary outcome measures were knowledge of PCC and the subscales of the Health Promotion Lifestyle Profile. Surveys were conducted before, after, and six months after the intervention in the intervention group, and an initial survey and survey six months later were conducted in the control group. Cochran’s Q test, Bonferroni’s multiple comparison test, and McNemar’s test were used to analyze the knowledge of PCC data. The Health Awareness, Nutrition, and Stress Management subscales of the Health Promotion Lifestyle Profile were analyzed by paired t-test, and comparisons between the intervention and control groups were performed using the two-way repeated measures analysis of variance. Results: In the intervention group of 67 people, the number of subjects who answered “correct” for five of the nine items concerning knowledge of PCC increased immediately after the health education (P = 0.006) but decreased for five items from immediately after the health education to six months later (P = 0.043). In addition, the number of respondents who answered “correct” for “low birth weight infants and future lifestyle-related diseases” (P = 0.016) increased after six months compared with before the health education. For the 52 subjects in the control group, there was no change in the number of subjects who answered “correct” for eight out of the nine items after six months. There was also no increase in scores for the Health Promotion Lifestyle Profile after six months for either the intervention or control group. Conclusion: Providing health education about PCC using videos and leaflets to adolescent females was shown to enhance the knowledge of PCC immediately after the education.展开更多
Multimedia semantic communication has been receiving increasing attention due to its significant enhancement of communication efficiency.Semantic coding,which is oriented towards extracting and encoding the key semant...Multimedia semantic communication has been receiving increasing attention due to its significant enhancement of communication efficiency.Semantic coding,which is oriented towards extracting and encoding the key semantics of video for transmission,is a key aspect in the framework of multimedia semantic communication.In this paper,we propose a facial video semantic coding method with low bitrate based on the temporal continuity of video semantics.At the sender’s end,we selectively transmit facial keypoints and deformation information,allocating distinct bitrates to different keypoints across frames.Compressive techniques involving sampling and quantization are employed to reduce the bitrate while retaining facial key semantic information.At the receiver’s end,a GAN-based generative network is utilized for reconstruction,effectively mitigating block artifacts and buffering problems present in traditional codec algorithms under low bitrates.The performance of the proposed approach is validated on multiple datasets,such as VoxCeleb and TalkingHead-1kH,employing metrics such as LPIPS,DISTS,and AKD for assessment.Experimental results demonstrate significant advantages over traditional codec methods,achieving up to approximately 10-fold bitrate reduction in prolonged,stable head pose scenarios across diverse conversational video settings.展开更多
The application of short videos in agricultural scenarios has become a new form of productive force driving agricultural development,injecting new vitality and opportunities into traditional agriculture.These videos l...The application of short videos in agricultural scenarios has become a new form of productive force driving agricultural development,injecting new vitality and opportunities into traditional agriculture.These videos leverage the unique expressive logic of the platform by adopting a small entry point and prioritizing dissemination rate.They are strategically planned in terms of content,visuals,and interaction to cater to users needs for relaxation,knowledge acquisition,social sharing,agricultural product marketing,and talent display.Through careful design,full creativity,rich emotion,and the creation of distinct character personalities,these videos deliver positive,entertaining,informative,and opinion-driven agricultural content.The production and operation of agricultural short videos can be effectively optimized by analyzing the characteristics of both popular and less popular videos,and utilizing smart tools and trending topics.展开更多
Objectives:Medical students often rely on recreational internet media to relieve the stress caused by immense academic and life pressures,and among these media,short-form videos,which are an emerging digital medium,ha...Objectives:Medical students often rely on recreational internet media to relieve the stress caused by immense academic and life pressures,and among these media,short-form videos,which are an emerging digital medium,have gradually become the mainstream choice of students to relieve their stress.However,the addiction caused by their usage has attracted the widespread attention of both academia and society,which is why the purpose of this study is to systematically explore the underlying mechanisms that link perceived stress,entertainment gratification,emotional gratification,short-form video usage intensity,and short-form video addiction based on multiple theoretical frameworks including the Compensatory Internet Use Model(CIU),the Interaction of Person-Affect-Cognition-Execution Model(I-PACE),and the Use and Gratification Theory(UGT).Methods:A hypothetical model with 9 research hypotheses was constructed.Taking medical students from Chi-nese universities as the research subjects,1057 valid responses were collected through an online questionnaire survey,including 358 males and 658 females.Structural equation modelling(SEM)was performed using the AMOS software to test the research hypotheses.Results:(1)Perceived stress positively predicted entertainment gratification and emotional gratification(β=0.72,p<0.001;β=0.61,p<0.001);(2)Entertainment gratifi-cation and emotional gratification positively influenced short-form video usage intensity(β=0.35,p<0.001;β=0.19,p<0.001);(3)Entertainment gratification and emotional gratification positively predicted short-form video addiction(β=0.40,p<0.001;β=0.17,p<0.001);(4)Short-form video usage intensity positively influenced short-form video addiction(β=0.36,p<0.001);and(5)Perceived stress exerted an indirect but positive effect on both short-form video usage intensity and short-form video addiction,mediated by entertainment and emotional gratification(β=0.37,p<0.001;β=0.52,p<0.001).Conclusion:The mechanisms that underlie medical students’short-form video addiction in stressful situations were revealed in this study.It was found that stress enhances medical students’need for entertainment and emotional online compensation,prompting more frequent short-form video usage and ultimately leading to addiction.These results underscore the need to address the stressors faced by medical students.Effective interventions should prioritise stress management strategies and promote healthier alternative coping mechanisms to mitigate the risk of addiction.展开更多
Intelligent sorting is an important prerequisite for the full quantitative consumption and harmless disposal of kitchen waste.The existing object detection method based on an ImageNet pre-trained model is an effective...Intelligent sorting is an important prerequisite for the full quantitative consumption and harmless disposal of kitchen waste.The existing object detection method based on an ImageNet pre-trained model is an effective way of sorting.Owing to significant domain gaps between natural images and kitchen waste images,it is difficult to reflect the characteristics of diverse scales and dense distribution in kitchen waste based on an ImageNet pre-trained model,leading to poor generalisation.In this article,the authors propose the first pre-trained model for kitchen waste sorting called KitWaSor,which combines both contrastive learning(CL)and masked image modelling(MIM)through self-supervised learning(SSL).First,to address the issue of diverse scales,the authors propose a mixed masking strategy by introducing an incomplete masking branch based on the original random masking branch.It prevents the complete loss of small-scale objects while avoiding excessive leakage of large-scale object pixels.Second,to address the issue of dense distribution,the authors introduce semantic consistency constraints on the basis of the mixed masking strategy.That is,object semantic reasoning is performed through semantic consistency constraints to compensate for the lack of contextual information.To train KitWaSor,the authors construct the first million-level kitchen waste dataset across seasonal and regional distributions,named KWD-Million.Extensive experiments show that KitWaSor achieves state-of-the-art(SOTA)performance on the two most relevant downstream tasks for kitchen waste sorting(i.e.image classification and object detection),demonstrating the effectiveness of the proposed KitWaSor.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.:U23A20530,82273858,and 82173746)the National Key Research and Development Programof China(Grant No.:2023YFF1204904)Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism(Shanghai Municipal Education Commission,China).
文摘Activity cliffs(ACs)are generally defined as pairs of similar compounds that only differ by a minor structural modification but exhibit a large difference in their binding affinity for a given target.ACs offer crucial insights that aid medicinal chemists in optimizing molecular structures.Nonetheless,they also form a major source of prediction error in structure-activity relationship(SAR)models.To date,several studies have demonstrated that deep neural networks based on molecular images or graphs might need to be improved further in predicting the potency of ACs.In this paper,we integrated the triplet loss in face recognition with pre-training strategy to develop a prediction model ACtriplet,tailored for ACs.Through extensive comparison with multiple baseline models on 30 benchmark datasets,the results showed that ACtriplet was significantly better than those deep learning(DL)models without pretraining.In addition,we explored the effect of pre-training on data representation.Finally,the case study demonstrated that our model's interpretability module could explain the prediction results reasonably.In the dilemma that the amount of data could not be increased rapidly,this innovative framework would better make use of the existing data,which would propel the potential of DL in the early stage of drug discovery and optimization.
基金supported by the National Natural Science Foundation of China(Grant No.72334003)the National Key Research and Development Program of China(Grant No.2022YFB2702804)+1 种基金the Shandong Key Research and Development Program(Grant No.2020ZLYS09)the Jinan Program(Grant No.2021GXRC084-2).
文摘With the continuous advancement of unmanned technology in various application domains,the development and deployment of blind-spot-free panoramic video systems have gained increasing importance.Such systems are particularly critical in battlefield environments,where advanced panoramic video processing and wireless communication technologies are essential to enable remote control and autonomous operation of unmanned ground vehicles(UGVs).However,conventional video surveillance systems suffer from several limitations,including limited field of view,high processing latency,low reliability,excessive resource consumption,and significant transmission delays.These shortcomings impede the widespread adoption of UGVs in battlefield settings.To overcome these challenges,this paper proposes a novel multi-channel video capture and stitching system designed for real-time video processing.The system integrates the Speeded-Up Robust Features(SURF)algorithm and the Fast Library for Approximate Nearest Neighbors(FLANN)algorithm to execute essential operations such as feature detection,descriptor computation,image matching,homography estimation,and seamless image fusion.The fused panoramic video is then encoded and assembled to produce a seamless output devoid of stitching artifacts and shadows.Furthermore,H.264 video compression is employed to reduce the data size of the video stream without sacrificing visual quality.Using the Real-Time Streaming Protocol(RTSP),the compressed stream is transmitted efficiently,supporting real-time remote monitoring and control of UGVs in dynamic battlefield environments.Experimental results indicate that the proposed system achieves high stability,flexibility,and low latency.With a wireless link latency of 30 ms,the end-to-end video transmission latency remains around 140 ms,enabling smooth video communication.The system can tolerate packet loss rates(PLR)of up to 20%while maintaining usable video quality(with latency around 200 ms).These properties make it well-suited for mobile communication scenarios demanding high real-time video performance.
基金supported by the Cultivation Program for Major Scientific Research Projects of Harbin Institute of Technology(ZDXMPY20180109).
文摘Scalable simulation leveraging real-world data plays an essential role in advancing autonomous driving,owing to its efficiency and applicability in both training and evaluating algorithms.Consequently,there has been increasing attention on generating highly realistic and consistent driving videos,particularly those involving viewpoint changes guided by the control commands or trajectories of ego vehicles.However,current reconstruction approaches,such as Neural Radiance Fields and 3D Gaussian Splatting,frequently suffer from limited generalization and depend on substantial input data.Meanwhile,2D generative models,though capable of producing unknown scenes,still have room for improvement in terms of coherence and visual realism.To overcome these challenges,we introduce GenScene,a world model that synthesizes front-view driving videos conditioned on trajectories.A new temporal module is presented to improve video consistency by extracting the global context of each frame,calculating relationships of frames using these global representations,and fusing frame contexts accordingly.Moreover,we propose an innovative attention mechanism that computes relations of pixels within each frame and pixels in the corresponding window range of the initial frame.Extensive experiments show that our approach surpasses various state-of-the-art models in driving video generation,and the introduced modules contribute significantly to model performance.This work establishes a new paradigm for goal-oriented video synthesis in autonomous driving,which facilitates on-demand simulation to expedite algorithm development.
文摘Background:This study aims to investigate the underlying mechanisms between parental marital conflict and adolescent short video dependence by constructing a chain mediation model,focusing on the mediating roles of experiential avoidance and emotional disturbance(anxiety,depression,and stress).Methods:Conducted in January 2025,the research recruited 4125 adolescents from multiple Chinese provinces through convenience sampling;after data cleaning,3957 valid participants(1959 males,1998 females)were included.Using a cross-sectional design,measures included parental marital conflict,experiential avoidance,anxiety,depression,stress,and short video dependence.Results:Pearson correlation analysis revealed significant positive correlations among all variables.Mediation analysis using the SPSS PROCESS macro showed that parental marital conflict directly predicted short video dependence(β=0.269,p<0.001),and also significantly predicted experiential avoidance(β=0.519,p<0.001),anxiety(β=0.072,p<0.001),depression(β=0.067,p<0.001),and stress(β=0.048,p<0.05).Experiential avoidance further predicted anxiety(β=0.521,p<0.001),depression(β=0.489,p<0.001),stress(β=0.408,p<0.001),and short video dependence(β=0.244,p<0.001).While both anxiety(β=0.050,p<0.05)and depression(β=0.116,p<0.001)positively predicted short video dependence,stress did not(β=0.019,p=0.257).Overall,experiential avoidance,anxiety,depression,and stress significantly mediated the relationship between parental marital conflict and short video dependence.Conclusion:These findings confirm that parental marital conflict not only directly influences adolescent short video dependence but also operates through a chain mediation pathway involving experiential avoidance and emotional disturbance,highlighting central psychological mechanisms and providing theoretical support for integrated mental health and behavioral interventions.
基金funded by the Guangxi Philosophy and Social Science Research Project,grant number 24XWC002.
文摘Background:In the Chinese context,the impact of short video applications on the psychological well-being of older adults is contested.While often examined through a pathological lens of addiction,this perspective may overlook paradoxical,context-dependent positive outcomes.Therefore,the main objective of this study is to challenge the traditional Compensatory Internet Use Theory by proposing and testing a chained mediation model that explores a paradoxical pathway from social support to life satisfaction via problematic social media use.Methods:Data were collected between July and August 2025 via the Credamo online survey platform,yielding 384 valid responses from Chinese older adults aged 60 and above.Key constructs were assessed using the Social Support Rating Scale(SSRS),Bergen Social Media Addiction Scale(BSMAS),Simplified UCLA Loneliness Scale,and Satisfaction with Life Scale(SWLS).A chained mediation model was tested using stepwise regression and non-parametric bootstrapping(5000 resamples),controlling for age,gender,household income,and health status.Results:The analysis revealed a paradoxical pathway,which was clarified by a key statistical suppression effect.Social support significantly and positively predicted problematic usage(β=0.157,p=0.002).After controlling for the suppressor effect of social support,problematic usage in turn negatively predicted social connectedness(β=−0.177,p<0.001).Finally,reduced social connectedness—reflecting a state of solitude—positively predicted life satisfaction(β=−0.227,p<0.001).Conclusion:The findings suggest that for older adults with sufficient offline social support,these resources may serve a“social empowerment”function.This empowerment allows behaviors measured as“problematic usage”to be theoretically reframed as a form of“deep immersive entertainment”.This immersion appears to occur alongside a state of“high-quality solitude”,which ultimately is associated with higher life satisfaction.This study provides a novel,non-pathological theoretical perspective on the consequences of high engagement with emerging social media,offering empirical grounds for non-abstinence-based intervention strategies.
基金supported by the National Natural Science Foundation of China(U1435220)
文摘How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However,the training and testing of CNN mainly rely on single machine.Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure.When a model is complex or the training data is relatively small,overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore,Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Na¨?ve Bayes classifier, a distributed Na¨?ve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.
基金Supported by the National Natural Science Foundation of China (62006150)Songjiang District Science and Technology Research Project (19SJKJGG83)Shanghai Young Science and Technology Talents Sailing Program (19YF1418400)。
文摘Vision-Language-Navigation(VLN) task is a cross-modality task that combines natural language processing and computer vision. This task requires the agent to automatically move to the destination according to the natural language instruction and the observed surrounding visual information. To make the best decision, in every step during the navigation, the agent should pay more attention to understanding the objects, the object attributes, and the object relationships. But most current methods process all received textual and visual information equally. Therefore, this paper integrates more detailed semantic connections between visual and textual information through three pre-training tasks(object prediction, object attributes prediction, and object relationship prediction). The model will learn better fusion representation and alignment between these two types of information to improve the success rate(SR) and generalization. The experiments show that compared with the former baseline models, the SR on the unseen validation set(Val Unseen) increased by 7%, and the SR weighted by path length(SPL) increased by 7%;the SR on the test set(Test) increased 4%, SPL increased by 3%.
文摘Web-based training is growing quickly in popularit y for professionals in industrial organizations and large enterprises. The savings in cost and time are significant. The instructor-led trainings are bounded by time and place, not to mention the cost involved in traveling, accommodation and training venue. However, in the most online training courses, all trainees are given same training materials and teaching paradigms. The problem of differentia ting the trainees’ abilities is the main concern. We need a pre-training test t o identify and classify of the weaknesses and strengths of differentiate trainee s so as to devise an appropriate training programs for the trainees. Adaptation of a Web-based Computer adaptive Test (CAT) for the pre-training test make the web-based training more efficient. The advantages of CAT are self-pacing, eff iciency, time and cost saving, immediate scoring and feedback, accuracy and secu rity, etc (Rudner, 1998; UMN, 1999; Novell, 2000; Linacre, 2000; Windowsglore, 2 000). Moreover, Web-based CAT also gives greater flexibility and convenience. T his paper describes how this CAT tool is built, how it helps instructor identify the strengths and weaknesses of trainees, and how to assure quality on the CAT system.
文摘Handheld ultrasound devices are known for their portability and affordability,making them widely utilized in underdeveloped areas and community healthcare for rapid diagnosis and early screening.However,the image quality of handheld ultrasound devices is not always satisfactory due to the limited equipment size,which hinders accurate diagnoses by doctors.At the same time,paired ultrasound images are difficult to obtain from the clinic because imaging process is complicated.Therefore,we propose a modified cycle generative adversarial network(cycleGAN) for ultrasound image enhancement from multiple organs via unpaired pre-training.We introduce an ultrasound image pre-training method that does not require paired images,alleviating the requirement for large-scale paired datasets.We also propose an enhanced block with different structures in the pre-training and fine-tuning phases,which can help achieve the goals of different training phases.To improve the robustness of the model,we add Gaussian noise to the training images as data augmentation.Our approach is effective in obtaining the best quantitative evaluation results using a small number of parameters and less training costs to improve the quality of handheld ultrasound devices.
基金financially supported by the Natural Science Foundation of China(Grant No.42301492)the National Key R&D Program of China(Grant Nos.2022YFF0711600,2022YFF0801201,2022YFF0801200)+3 种基金the Major Special Project of Xinjiang(Grant No.2022A03009-3)the Open Fund of Key Laboratory of Urban Land Resources Monitoring and Simulation,Ministry of Natural Resources(Grant No.KF-2022-07014)the Opening Fund of the Key Laboratory of the Geological Survey and Evaluation of the Ministry of Education(Grant No.GLAB 2023ZR01)the Fundamental Research Funds for the Central Universities。
文摘As important geological data,a geological report contains rich expert and geological knowledge,but the challenge facing current research into geological knowledge extraction and mining is how to render accurate understanding of geological reports guided by domain knowledge.While generic named entity recognition models/tools can be utilized for the processing of geoscience reports/documents,their effectiveness is hampered by a dearth of domain-specific knowledge,which in turn leads to a pronounced decline in recognition accuracy.This study summarizes six types of typical geological entities,with reference to the ontological system of geological domains and builds a high quality corpus for the task of geological named entity recognition(GNER).In addition,Geo Wo BERT-adv BGP(Geological Word-base BERTadversarial training Bi-directional Long Short-Term Memory Global Pointer)is proposed to address the issues of ambiguity,diversity and nested entities for the geological entities.The model first uses the fine-tuned word granularitybased pre-training model Geo Wo BERT(Geological Word-base BERT)and combines the text features that are extracted using the Bi LSTM(Bi-directional Long Short-Term Memory),followed by an adversarial training algorithm to improve the robustness of the model and enhance its resistance to interference,the decoding finally being performed using a global association pointer algorithm.The experimental results show that the proposed model for the constructed dataset achieves high performance and is capable of mining the rich geological information.
基金supported by National Natural Science Foundation of China(62072416)Key Research and Development Special Project of Henan Province(221111210500)Key TechnologiesR&DProgram of Henan rovince(232102211053,242102211071).
文摘The rapid development of short video platforms poses new challenges for traditional recommendation systems.Recommender systems typically depend on two types of user behavior feedback to construct user interest profiles:explicit feedback(interactive behavior),which significantly influences users’short-term interests,and implicit feedback(viewing time),which substantially affects their long-term interests.However,the previous model fails to distinguish between these two feedback methods,leading it to predict only the overall preferences of users based on extensive historical behavior sequences.Consequently,it cannot differentiate between users’long-term and shortterm interests,resulting in low accuracy in describing users’interest states and predicting the evolution of their interests.This paper introduces a video recommendationmodel calledCAT-MFRec(CrossAttention Transformer-Mixed Feedback Recommendation)designed to differentiate between explicit and implicit user feedback within the DIEN(Deep Interest Evolution Network)framework.This study emphasizes the separate learning of the two types of behavioral feedback,effectively integrating them through the cross-attention mechanism.Additionally,it leverages the long sequence dependence capabilities of Transformer technology to accurately construct user interest profiles and predict the evolution of user interests.Experimental results indicate that CAT-MF Rec significantly outperforms existing recommendation methods across various performance indicators.This advancement offers new theoretical and practical insights for the development of video recommendations,particularly in addressing complex and dynamic user behavior patterns.
基金Shenzhen Science and Technology Programme,Grant/Award Number:JCYJ202308071208000012023 Shenzhen sustainable supporting funds for colleges and universities,Grant/Award Number:20231121165240001Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology,Grant/Award Number:2024B1212010006。
文摘Internal learning-based video inpainting methods have shown promising results by exploiting the intrinsic properties of the video to fill in the missing region without external dataset supervision.However,existing internal learning-based video inpainting methods would produce inconsistent structures or blurry textures due to the insufficient utilisation of motion priors within the video sequence.In this paper,the authors propose a new internal learning-based video inpainting model called appearance consistency and motion coherence network(ACMC-Net),which can not only learn the recurrence of appearance prior but can also capture motion coherence prior to improve the quality of the inpainting results.In ACMC-Net,a transformer-based appearance network is developed to capture global context information within the video frame for representing appearance consistency accurately.Additionally,a novel motion coherence learning scheme is proposed to learn the motion prior in a video sequence effectively.Finally,the learnt internal appearance consistency and motion coherence are implicitly propagated to the missing regions to achieve inpainting well.Extensive experiments conducted on the DAVIS dataset show that the proposed model obtains the superior performance in terms of quantitative measurements and produces more visually plausible results compared with the state-of-the-art methods.
文摘Airway management plays a crucial role in providing adequate oxygenation and ventilation to patients during various medical procedures and emergencies.When patients have a limited mouth opening due to factors such as trauma,inflammation,or anatomical abnormalities airway management becomes challenging.A commonly utilized method to overcome this challenge is the use of video laryngoscopy(VL),which employs a specialized device equipped with a camera and a light source to allow a clear view of the larynx and vocal cords.VL overcomes the limitations of direct laryngoscopy in patients with limited mouth opening,enabling better visualization and successful intubation.Various types of VL blades are available.We devised a novel flangeless video laryngoscope for use in patients with a limited mouth opening and then tested it on a manikin.
文摘Semantic segmentation is a core task in computer vision that allows AI models to interact and understand their surrounding environment. Similarly to how humans subconsciously segment scenes, this ability is crucial for scene understanding. However, a challenge many semantic learning models face is the lack of data. Existing video datasets are limited to short, low-resolution videos that are not representative of real-world examples. Thus, one of our key contributions is a customized semantic segmentation version of the Walking Tours Dataset that features hour-long, high-resolution, real-world data from tours of different cities. Additionally, we evaluate the performance of open-vocabulary, semantic model OpenSeeD on our own custom dataset and discuss future implications.
文摘Objective: The purpose of this study was to evaluate health education using videos and leaflets for preconception care (PCC) awareness among adolescent females up to six months after the health education. Methods: The subjects were female university students living in the Kinki area. A longitudinal survey was conducted on 67 members in the intervention group, who received the health education, and 52 members in the control group, who did not receive the health education. The primary outcome measures were knowledge of PCC and the subscales of the Health Promotion Lifestyle Profile. Surveys were conducted before, after, and six months after the intervention in the intervention group, and an initial survey and survey six months later were conducted in the control group. Cochran’s Q test, Bonferroni’s multiple comparison test, and McNemar’s test were used to analyze the knowledge of PCC data. The Health Awareness, Nutrition, and Stress Management subscales of the Health Promotion Lifestyle Profile were analyzed by paired t-test, and comparisons between the intervention and control groups were performed using the two-way repeated measures analysis of variance. Results: In the intervention group of 67 people, the number of subjects who answered “correct” for five of the nine items concerning knowledge of PCC increased immediately after the health education (P = 0.006) but decreased for five items from immediately after the health education to six months later (P = 0.043). In addition, the number of respondents who answered “correct” for “low birth weight infants and future lifestyle-related diseases” (P = 0.016) increased after six months compared with before the health education. For the 52 subjects in the control group, there was no change in the number of subjects who answered “correct” for eight out of the nine items after six months. There was also no increase in scores for the Health Promotion Lifestyle Profile after six months for either the intervention or control group. Conclusion: Providing health education about PCC using videos and leaflets to adolescent females was shown to enhance the knowledge of PCC immediately after the education.
基金supported by the National Natural Science Foundation of China (Nos. NSFC 61925105, 62322109, 62171257 and U22B2001)the Xplorer Prize in Information and Electronics technologiesthe Tsinghua University (Department of Electronic Engineering)-Nantong Research Institute for Advanced Communication Technologies Joint Research Center for Space, Air, Ground and Sea Cooperative Communication Network Technology
文摘Multimedia semantic communication has been receiving increasing attention due to its significant enhancement of communication efficiency.Semantic coding,which is oriented towards extracting and encoding the key semantics of video for transmission,is a key aspect in the framework of multimedia semantic communication.In this paper,we propose a facial video semantic coding method with low bitrate based on the temporal continuity of video semantics.At the sender’s end,we selectively transmit facial keypoints and deformation information,allocating distinct bitrates to different keypoints across frames.Compressive techniques involving sampling and quantization are employed to reduce the bitrate while retaining facial key semantic information.At the receiver’s end,a GAN-based generative network is utilized for reconstruction,effectively mitigating block artifacts and buffering problems present in traditional codec algorithms under low bitrates.The performance of the proposed approach is validated on multiple datasets,such as VoxCeleb and TalkingHead-1kH,employing metrics such as LPIPS,DISTS,and AKD for assessment.Experimental results demonstrate significant advantages over traditional codec methods,achieving up to approximately 10-fold bitrate reduction in prolonged,stable head pose scenarios across diverse conversational video settings.
文摘The application of short videos in agricultural scenarios has become a new form of productive force driving agricultural development,injecting new vitality and opportunities into traditional agriculture.These videos leverage the unique expressive logic of the platform by adopting a small entry point and prioritizing dissemination rate.They are strategically planned in terms of content,visuals,and interaction to cater to users needs for relaxation,knowledge acquisition,social sharing,agricultural product marketing,and talent display.Through careful design,full creativity,rich emotion,and the creation of distinct character personalities,these videos deliver positive,entertaining,informative,and opinion-driven agricultural content.The production and operation of agricultural short videos can be effectively optimized by analyzing the characteristics of both popular and less popular videos,and utilizing smart tools and trending topics.
文摘Objectives:Medical students often rely on recreational internet media to relieve the stress caused by immense academic and life pressures,and among these media,short-form videos,which are an emerging digital medium,have gradually become the mainstream choice of students to relieve their stress.However,the addiction caused by their usage has attracted the widespread attention of both academia and society,which is why the purpose of this study is to systematically explore the underlying mechanisms that link perceived stress,entertainment gratification,emotional gratification,short-form video usage intensity,and short-form video addiction based on multiple theoretical frameworks including the Compensatory Internet Use Model(CIU),the Interaction of Person-Affect-Cognition-Execution Model(I-PACE),and the Use and Gratification Theory(UGT).Methods:A hypothetical model with 9 research hypotheses was constructed.Taking medical students from Chi-nese universities as the research subjects,1057 valid responses were collected through an online questionnaire survey,including 358 males and 658 females.Structural equation modelling(SEM)was performed using the AMOS software to test the research hypotheses.Results:(1)Perceived stress positively predicted entertainment gratification and emotional gratification(β=0.72,p<0.001;β=0.61,p<0.001);(2)Entertainment gratifi-cation and emotional gratification positively influenced short-form video usage intensity(β=0.35,p<0.001;β=0.19,p<0.001);(3)Entertainment gratification and emotional gratification positively predicted short-form video addiction(β=0.40,p<0.001;β=0.17,p<0.001);(4)Short-form video usage intensity positively influenced short-form video addiction(β=0.36,p<0.001);and(5)Perceived stress exerted an indirect but positive effect on both short-form video usage intensity and short-form video addiction,mediated by entertainment and emotional gratification(β=0.37,p<0.001;β=0.52,p<0.001).Conclusion:The mechanisms that underlie medical students’short-form video addiction in stressful situations were revealed in this study.It was found that stress enhances medical students’need for entertainment and emotional online compensation,prompting more frequent short-form video usage and ultimately leading to addiction.These results underscore the need to address the stressors faced by medical students.Effective interventions should prioritise stress management strategies and promote healthier alternative coping mechanisms to mitigate the risk of addiction.
基金National Key Research and Development Program of China,Grant/Award Number:2021YFC1910402。
文摘Intelligent sorting is an important prerequisite for the full quantitative consumption and harmless disposal of kitchen waste.The existing object detection method based on an ImageNet pre-trained model is an effective way of sorting.Owing to significant domain gaps between natural images and kitchen waste images,it is difficult to reflect the characteristics of diverse scales and dense distribution in kitchen waste based on an ImageNet pre-trained model,leading to poor generalisation.In this article,the authors propose the first pre-trained model for kitchen waste sorting called KitWaSor,which combines both contrastive learning(CL)and masked image modelling(MIM)through self-supervised learning(SSL).First,to address the issue of diverse scales,the authors propose a mixed masking strategy by introducing an incomplete masking branch based on the original random masking branch.It prevents the complete loss of small-scale objects while avoiding excessive leakage of large-scale object pixels.Second,to address the issue of dense distribution,the authors introduce semantic consistency constraints on the basis of the mixed masking strategy.That is,object semantic reasoning is performed through semantic consistency constraints to compensate for the lack of contextual information.To train KitWaSor,the authors construct the first million-level kitchen waste dataset across seasonal and regional distributions,named KWD-Million.Extensive experiments show that KitWaSor achieves state-of-the-art(SOTA)performance on the two most relevant downstream tasks for kitchen waste sorting(i.e.image classification and object detection),demonstrating the effectiveness of the proposed KitWaSor.
