With the availability of high-performance computing technology and the development of advanced numerical simulation methods, Computational Fluid Dynamics (CFD) is becoming more and more practical and efficient in engi...With the availability of high-performance computing technology and the development of advanced numerical simulation methods, Computational Fluid Dynamics (CFD) is becoming more and more practical and efficient in engineering. As one of the high-precision representative algorithms, the high-order Discontinuous Galerkin Method (DGM) has not only attracted widespread attention from scholars in the CFD research community, but also received strong development. However, when DGM is extended to high-speed aerodynamic flow field calculations, non-physical numerical Gibbs oscillations near shock waves often significantly affect the numerical accuracy and even cause calculation failure. Data driven approaches based on machine learning techniques can be used to learn the characteristics of Gibbs noise, which motivates us to use it in high-speed DG applications. To achieve this goal, labeled data need to be generated in order to train the machine learning models. This paper proposes a new method for denoising modeling of Gibbs phenomenon using a machine learning technique, the zero-shot learning strategy, to eliminate acquiring large amounts of CFD data. The model adopts a graph convolutional network combined with graph attention mechanism to learn the denoising paradigm from synthetic Gibbs noise data and generalize to DGM numerical simulation data. Numerical simulation results show that the Gibbs denoising model proposed in this paper can suppress the numerical oscillation near shock waves in the high-order DGM. Our work automates the extension of DGM to high-speed aerodynamic flow field calculations with higher generalization and lower cost.展开更多
Zero-shot learning enables the recognition of new class samples by migrating models learned from semanticfeatures and existing sample features to things that have never been seen before. The problems of consistencyof ...Zero-shot learning enables the recognition of new class samples by migrating models learned from semanticfeatures and existing sample features to things that have never been seen before. The problems of consistencyof different types of features and domain shift problems are two of the critical issues in zero-shot learning. Toaddress both of these issues, this paper proposes a new modeling structure. The traditional approach mappedsemantic features and visual features into the same feature space;based on this, a dual discriminator approachis used in the proposed model. This dual discriminator approach can further enhance the consistency betweensemantic and visual features. At the same time, this approach can also align unseen class semantic features andtraining set samples, providing a portion of information about the unseen classes. In addition, a new feature fusionmethod is proposed in the model. This method is equivalent to adding perturbation to the seen class features,which can reduce the degree to which the classification results in the model are biased towards the seen classes.At the same time, this feature fusion method can provide part of the information of the unseen classes, improvingits classification accuracy in generalized zero-shot learning and reducing domain bias. The proposed method isvalidated and compared with othermethods on four datasets, and fromthe experimental results, it can be seen thatthe method proposed in this paper achieves promising results.展开更多
Audio-visual learning,aimed at exploiting the relationship between audio and visual modalities,has drawn considerable attention since deep learning started to be used successfully.Researchers tend to leverage these tw...Audio-visual learning,aimed at exploiting the relationship between audio and visual modalities,has drawn considerable attention since deep learning started to be used successfully.Researchers tend to leverage these two modalities to improve the performance of previously considered single-modality tasks or address new challenging problems.In this paper,we provide a comprehensive survey of recent audio-visual learning development.We divide the current audio-visual learning tasks into four different subfields:audiovisual separation and localization,audio-visual correspondence learning,audio-visual generation,and audio-visual representation learning.State-of-the-art methods,as well as the remaining challenges of each subfield,are further discussed.Finally,we summarize the commonly used datasets and challenges.展开更多
Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task for two main reasons: lack of sufficient training data for every class and difficulty in learning dis...Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task for two main reasons: lack of sufficient training data for every class and difficulty in learning discriminative features for representation. In this paper, to address the two issues, we propose a two-phase framework for recognizing images from unseen fine-grained classes, i.e., zeroshot fine-grained classification. In the first feature learning phase, we finetune deep convolutional neural networks using hierarchical semantic structure among fine-grained classes to extract discriminative deep visual features. Meanwhile, a domain adaptation structure is induced into deep convolutional neural networks to avoid domain shift from training data to test data. In the second label inference phase, a semantic directed graph is constructed over attributes of fine-grained classes. Based on this graph, we develop a label propagation algorithm to infer the labels of images in the unseen classes. Experimental results on two benchmark datasets demonstrate that our model outperforms the state-of-the-art zero-shot learning models. In addition, the features obtained by our feature learning model also yield significant gains when they are used by other zero-shot learning models, which shows the flexility of our model in zero-shot finegrained classification.展开更多
This paper proposes a zero-shot based spatial recognition AI algorithm by fusing and developing multidimensional vision identification technology adapted to the situation in large indoor and underground spaces.With th...This paper proposes a zero-shot based spatial recognition AI algorithm by fusing and developing multidimensional vision identification technology adapted to the situation in large indoor and underground spaces.With the expansion of large shopping malls and underground urban spaces(UUS),there is an increasing need for new technologies that can quickly identify complex indoor structures and changes such as relocation,remodeling,and construction for the safety and management of citizens through the provision of the up-to-date indoor 3D site maps.The proposed algorithm utilizes data collected by an unmanned robot to create a 3D site map of the up-to-date indoor site and recognizes complex indoor spaces based on zero-shot learning.This research specifically addresses two major challenges:the difficulty of detecting walls and floors due to complex patterns and the difficulty of spatial perception due to unknown obstacles.The proposed algorithm addresses the limitations of the existing foundation model,detects floors and obstacles without expensive sensors,and improves the accuracy of spatial recognition by combining floor detection,vanishing point detection,and fusion obstacle detection algorithms.The experimental results show that the algorithm effectively detects the floor and obstacles in various indoor environments,with F1 scores of 0.96 and 0.93 in the floor detection and obstacle detection experiments,respectively.展开更多
The goal of zero-shot recognition is to classify classes it has never seen before, which needs to build a bridge between seen and unseen classes through semantic embedding space. Therefore, semantic embedding space le...The goal of zero-shot recognition is to classify classes it has never seen before, which needs to build a bridge between seen and unseen classes through semantic embedding space. Therefore, semantic embedding space learning plays an important role in zero-shot recognition. Among existing works, semantic embedding space is mainly taken by user-defined attribute vectors. However, the discriminative information included in the user-defined attribute vector is limited. In this paper, we propose to learn an extra latent attribute space automatically to produce a more generalized and discriminative semantic embedded space. To prevent the bias problem, both user-defined attribute vector and latent attribute space are optimized by adversarial learning with auto-encoders. We also propose to reconstruct semantic patterns produced by explanatory graphs, which can make semantic embedding space more sensitive to usefully semantic information and less sensitive to useless information. The proposed method is evaluated on the AwA2 and CUB dataset. These results show that our proposed method achieves superior performance.展开更多
Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fin...Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fine-grained features by training deep models such that similar images are clustered,and dissimilar images are separated in the low embedding space.Previous works primarily focused on defining local structure loss functions like triplet loss,pairwise loss,etc.However,training via these approaches takes a long training time,and they have poor accuracy.Additionally,representations learned through it tend to tighten up in the embedded space and lose generalizability to unseen classes.This paper proposes a noise-assisted representation learning method for fine-grained image retrieval to mitigate these issues.In the proposed work,class manifold learning is performed in which positive pairs are created with noise insertion operation instead of tightening class clusters.And other instances are treated as negatives within the same cluster.Then a loss function is defined to penalize when the distance between instances of the same class becomes too small relative to the noise pair in that class in embedded space.The proposed approach is validated on CARS-196 and CUB-200 datasets and achieved better retrieval results(85.38%recall@1 for CARS-196%and 70.13%recall@1 for CUB-200)compared to other existing methods.展开更多
Deep metric learning is one of the recommended methods for the challenge of supporting few/zero-shot learning by deep networks.It depends on building a Siamese architecture of two homogeneous Convolutional Neural Netw...Deep metric learning is one of the recommended methods for the challenge of supporting few/zero-shot learning by deep networks.It depends on building a Siamese architecture of two homogeneous Convolutional Neural Networks(CNNs)for learning a distance function that can map input data from the input space to the feature space.Instead of determining the class of each sample,the Siamese architecture deals with the existence of a few training samples by deciding if the samples share the same class identity or not.The traditional structure for the Siamese architecture was built by forming two CNNs from scratch with randomly initialized weights and trained by binary cross-entropy loss.Building two CNNs from scratch is a trial and error and time-consuming phase.In addition,training with binary crossentropy loss sometimes leads to poor margins.In this paper,a novel Siamese network is proposed and applied to few/zero-shot Handwritten Character Recognition(HCR)tasks.The novelties of the proposed network are in.1)Utilizing transfer learning and using the pre-trained AlexNet as a feature extractor in the Siamese architecture.Fine-tuning a pre-trained network is typically faster and easier than building from scratch.2)Training the Siamese architecture with contrastive loss instead of the binary cross-entropy.Contrastive loss helps the network to learn a nonlinear mapping function that enables it to map the extracted features in the vector space with an optimal way.The proposed network is evaluated on the challenging Chars74K datasets by conducting two experiments.One is for testing the proposed network in few-shot learning while the other is for testing it in zero-shot learning.The recognition accuracy of the proposed network reaches to 85.6%and 82%in few-and zero-shot learning respectively.In addition,a comparison between the performance of the proposed Siamese network and the traditional Siamese CNNs is conducted.The comparison results show that the proposed network achieves higher recognition results in less time.The proposed network reduces the training time from days to hours in both experiments.展开更多
Large language models(LLMs)have demonstrated remarkable generalization abilities across multiple tasks in natural language processing(NLP).For multi-step reasoning tasks,chain-of-thought(CoT)prompting facilitates step...Large language models(LLMs)have demonstrated remarkable generalization abilities across multiple tasks in natural language processing(NLP).For multi-step reasoning tasks,chain-of-thought(CoT)prompting facilitates step-by-step thinking,leading to improved performance.However,despite significant advancements in LLMs,current CoT prompting performs suboptimally on smaller-scale models that have fewer parameters.Additionally,the common paradigm of few-shot CoT prompting relies on a set of manual demonstrations,with performance contingent on the quality of these annotations and varying with task-specific requirements.To address these limitations,we propose a select-and-answer prompting method(SAP)to enhance language model performance on reasoning tasks without the need for manual demonstrations.This method comprises two primary steps:guiding the model to conduct preliminary analysis and generate several candidate answers based on the prompting;allowing the model to provide final answers derived from these candidate answers.The proposed prompting strategy is evaluated across two language models of varying sizes and six datasets.On ChatGLM-6B,SAP consistently outperforms few-shot CoT across all datasets.For GPT-3.5,SAP achieves comparable performance to few-shot CoT and outperforms zero-shot CoT in most cases.These experimental results indicate that SAP can significantly improve the accuracy of language models in reasoning tasks.展开更多
The Internet has become one of the significant sources for sharing information and expressing users’opinions about products and their interests with the associated aspects.It is essential to learn about product revie...The Internet has become one of the significant sources for sharing information and expressing users’opinions about products and their interests with the associated aspects.It is essential to learn about product reviews;however,to react to such reviews,extracting aspects of the entity to which these reviews belong is equally important.Aspect-based Sentiment Analysis(ABSA)refers to aspects extracted from an opinionated text.The literature proposes different approaches for ABSA;however,most research is focused on supervised approaches,which require labeled datasets with manual sentiment polarity labeling and aspect tagging.This study proposes a semisupervised approach with minimal human supervision to extract aspect terms by detecting the aspect categories.Hence,the study deals with two main sub-tasks in ABSA,named Aspect Category Detection(ACD)and Aspect Term Extraction(ATE).In the first sub-task,aspects categories are extracted using topic modeling and filtered by an oracle further,and it is fed to zero-shot learning as the prompts and the augmented text.The predicted categories are the input to find similar phrases curated with extracting meaningful phrases(e.g.,Nouns,Proper Nouns,NER(Named Entity Recognition)entities)to detect the aspect terms.The study sets a baseline accuracy for two main sub-tasks in ABSA on the Multi-Aspect Multi-Sentiment(MAMS)dataset along with SemEval-2014 Task 4 subtask 1 to show that the proposed approach helps detect aspect terms via aspect categories.展开更多
Face anti-spoofing aims at detecting whether the input is a real photo of a user(living)or a fake(spoofing)image.As new types of attacks keep emerging,the detection of unknown attacks,known as Zero-Shot Face Anti-Spoo...Face anti-spoofing aims at detecting whether the input is a real photo of a user(living)or a fake(spoofing)image.As new types of attacks keep emerging,the detection of unknown attacks,known as Zero-Shot Face Anti-Spoofing(ZSFA),has become increasingly important in both academia and industry.Existing ZSFA methods mainly focus on extracting discriminative features between spoofing and living faces.However,the nature of the spoofing faces is to trick anti-spoofing systems by mimicking the livings,therefore the deceptive features between the known attacks and the livings,which have been ignored by existing ZSFA methods,are essential to comprehensively represent the livings.Therefore,existing ZSFA models are incapable of learning the complete representations of living faces and thus fall short of effectively detecting newly emerged attacks.To tackle this problem,we propose an innovative method that effectively captures both the deceptive and discriminative features distinguishing between genuine and spoofing faces.Our method consists of two main components:a two-against-all training strategy and a semantic autoencoder.The two-against-all training strategy is employed to separate deceptive and discriminative features.To address the subsequent invalidation issue of categorical functions and the dominance disequilibrium issue among different dimensions of features after importing deceptive features,we introduce a modified semantic autoencoder.This autoencoder is designed to map all extracted features to a semantic space,thereby achieving a balance in the dominance of each feature dimension.We combine our method with the feature extraction model ResNet50,and experimental results show that the trained ResNet50 model simultaneously achieves a feasible detection of unknown attacks and comparably accurate detection of known spoofing.Experimental results confirm the superiority and effectiveness of our proposed method in identifying the living with the interference of both known and unknown spoofing types.展开更多
In this paper, we present Emotion-Aware Music Driven Movie Montage, a novel paradigm for the challenging task of generating movie montages. Specifically, given a movie and a piece of music as the guidance, our method ...In this paper, we present Emotion-Aware Music Driven Movie Montage, a novel paradigm for the challenging task of generating movie montages. Specifically, given a movie and a piece of music as the guidance, our method aims to generate a montage out of the movie that is emotionally consistent with the music. Unlike previous work such as video summarization, this task requires not only video content understanding, but also emotion analysis of both the input movie and music. To this end, we propose a two-stage framework, including a learning-based module for the prediction of emotion similarity and an optimization-based module for the selection and composition of candidate movie shots. The core of our method is to align and estimate emotional similarity between music clips and movie shots in a multi-modal latent space via contrastive learning. Subsequently, the montage generation is modeled as a joint optimization of emotion similarity and additional constraints such as scene-level story completeness and shot-level rhythm synchronization. We conduct both qualitative and quantitative evaluations to demonstrate that our method can generate emotionally consistent montages and outperforms alternative baselines.展开更多
基金co-supported by the Aeronautical Science Foundation of China(Nos.2018ZA52002,2019ZA052011).
文摘With the availability of high-performance computing technology and the development of advanced numerical simulation methods, Computational Fluid Dynamics (CFD) is becoming more and more practical and efficient in engineering. As one of the high-precision representative algorithms, the high-order Discontinuous Galerkin Method (DGM) has not only attracted widespread attention from scholars in the CFD research community, but also received strong development. However, when DGM is extended to high-speed aerodynamic flow field calculations, non-physical numerical Gibbs oscillations near shock waves often significantly affect the numerical accuracy and even cause calculation failure. Data driven approaches based on machine learning techniques can be used to learn the characteristics of Gibbs noise, which motivates us to use it in high-speed DG applications. To achieve this goal, labeled data need to be generated in order to train the machine learning models. This paper proposes a new method for denoising modeling of Gibbs phenomenon using a machine learning technique, the zero-shot learning strategy, to eliminate acquiring large amounts of CFD data. The model adopts a graph convolutional network combined with graph attention mechanism to learn the denoising paradigm from synthetic Gibbs noise data and generalize to DGM numerical simulation data. Numerical simulation results show that the Gibbs denoising model proposed in this paper can suppress the numerical oscillation near shock waves in the high-order DGM. Our work automates the extension of DGM to high-speed aerodynamic flow field calculations with higher generalization and lower cost.
文摘Zero-shot learning enables the recognition of new class samples by migrating models learned from semanticfeatures and existing sample features to things that have never been seen before. The problems of consistencyof different types of features and domain shift problems are two of the critical issues in zero-shot learning. Toaddress both of these issues, this paper proposes a new modeling structure. The traditional approach mappedsemantic features and visual features into the same feature space;based on this, a dual discriminator approachis used in the proposed model. This dual discriminator approach can further enhance the consistency betweensemantic and visual features. At the same time, this approach can also align unseen class semantic features andtraining set samples, providing a portion of information about the unseen classes. In addition, a new feature fusionmethod is proposed in the model. This method is equivalent to adding perturbation to the seen class features,which can reduce the degree to which the classification results in the model are biased towards the seen classes.At the same time, this feature fusion method can provide part of the information of the unseen classes, improvingits classification accuracy in generalized zero-shot learning and reducing domain bias. The proposed method isvalidated and compared with othermethods on four datasets, and fromthe experimental results, it can be seen thatthe method proposed in this paper achieves promising results.
基金supported by National Key Research and Development Program of China(No.2016YFB1001001)Beijing Natural Science Foundation(No.JQ18017)National Natural Science Foundation of China(No.61976002)。
文摘Audio-visual learning,aimed at exploiting the relationship between audio and visual modalities,has drawn considerable attention since deep learning started to be used successfully.Researchers tend to leverage these two modalities to improve the performance of previously considered single-modality tasks or address new challenging problems.In this paper,we provide a comprehensive survey of recent audio-visual learning development.We divide the current audio-visual learning tasks into four different subfields:audiovisual separation and localization,audio-visual correspondence learning,audio-visual generation,and audio-visual representation learning.State-of-the-art methods,as well as the remaining challenges of each subfield,are further discussed.Finally,we summarize the commonly used datasets and challenges.
基金supported by National Basic Research Program of China (973 Program) (No. 2015CB352502)National Nature Science Foundation of China (No. 61573026)Beijing Nature Science Foundation (No. L172037)
文摘Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task for two main reasons: lack of sufficient training data for every class and difficulty in learning discriminative features for representation. In this paper, to address the two issues, we propose a two-phase framework for recognizing images from unseen fine-grained classes, i.e., zeroshot fine-grained classification. In the first feature learning phase, we finetune deep convolutional neural networks using hierarchical semantic structure among fine-grained classes to extract discriminative deep visual features. Meanwhile, a domain adaptation structure is induced into deep convolutional neural networks to avoid domain shift from training data to test data. In the second label inference phase, a semantic directed graph is constructed over attributes of fine-grained classes. Based on this graph, we develop a label propagation algorithm to infer the labels of images in the unseen classes. Experimental results on two benchmark datasets demonstrate that our model outperforms the state-of-the-art zero-shot learning models. In addition, the features obtained by our feature learning model also yield significant gains when they are used by other zero-shot learning models, which shows the flexility of our model in zero-shot finegrained classification.
基金supported by Kyonggi University Research Grant 2024.
文摘This paper proposes a zero-shot based spatial recognition AI algorithm by fusing and developing multidimensional vision identification technology adapted to the situation in large indoor and underground spaces.With the expansion of large shopping malls and underground urban spaces(UUS),there is an increasing need for new technologies that can quickly identify complex indoor structures and changes such as relocation,remodeling,and construction for the safety and management of citizens through the provision of the up-to-date indoor 3D site maps.The proposed algorithm utilizes data collected by an unmanned robot to create a 3D site map of the up-to-date indoor site and recognizes complex indoor spaces based on zero-shot learning.This research specifically addresses two major challenges:the difficulty of detecting walls and floors due to complex patterns and the difficulty of spatial perception due to unknown obstacles.The proposed algorithm addresses the limitations of the existing foundation model,detects floors and obstacles without expensive sensors,and improves the accuracy of spatial recognition by combining floor detection,vanishing point detection,and fusion obstacle detection algorithms.The experimental results show that the algorithm effectively detects the floor and obstacles in various indoor environments,with F1 scores of 0.96 and 0.93 in the floor detection and obstacle detection experiments,respectively.
文摘The goal of zero-shot recognition is to classify classes it has never seen before, which needs to build a bridge between seen and unseen classes through semantic embedding space. Therefore, semantic embedding space learning plays an important role in zero-shot recognition. Among existing works, semantic embedding space is mainly taken by user-defined attribute vectors. However, the discriminative information included in the user-defined attribute vector is limited. In this paper, we propose to learn an extra latent attribute space automatically to produce a more generalized and discriminative semantic embedded space. To prevent the bias problem, both user-defined attribute vector and latent attribute space are optimized by adversarial learning with auto-encoders. We also propose to reconstruct semantic patterns produced by explanatory graphs, which can make semantic embedding space more sensitive to usefully semantic information and less sensitive to useless information. The proposed method is evaluated on the AwA2 and CUB dataset. These results show that our proposed method achieves superior performance.
文摘Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fine-grained features by training deep models such that similar images are clustered,and dissimilar images are separated in the low embedding space.Previous works primarily focused on defining local structure loss functions like triplet loss,pairwise loss,etc.However,training via these approaches takes a long training time,and they have poor accuracy.Additionally,representations learned through it tend to tighten up in the embedded space and lose generalizability to unseen classes.This paper proposes a noise-assisted representation learning method for fine-grained image retrieval to mitigate these issues.In the proposed work,class manifold learning is performed in which positive pairs are created with noise insertion operation instead of tightening class clusters.And other instances are treated as negatives within the same cluster.Then a loss function is defined to penalize when the distance between instances of the same class becomes too small relative to the noise pair in that class in embedded space.The proposed approach is validated on CARS-196 and CUB-200 datasets and achieved better retrieval results(85.38%recall@1 for CARS-196%and 70.13%recall@1 for CUB-200)compared to other existing methods.
文摘Deep metric learning is one of the recommended methods for the challenge of supporting few/zero-shot learning by deep networks.It depends on building a Siamese architecture of two homogeneous Convolutional Neural Networks(CNNs)for learning a distance function that can map input data from the input space to the feature space.Instead of determining the class of each sample,the Siamese architecture deals with the existence of a few training samples by deciding if the samples share the same class identity or not.The traditional structure for the Siamese architecture was built by forming two CNNs from scratch with randomly initialized weights and trained by binary cross-entropy loss.Building two CNNs from scratch is a trial and error and time-consuming phase.In addition,training with binary crossentropy loss sometimes leads to poor margins.In this paper,a novel Siamese network is proposed and applied to few/zero-shot Handwritten Character Recognition(HCR)tasks.The novelties of the proposed network are in.1)Utilizing transfer learning and using the pre-trained AlexNet as a feature extractor in the Siamese architecture.Fine-tuning a pre-trained network is typically faster and easier than building from scratch.2)Training the Siamese architecture with contrastive loss instead of the binary cross-entropy.Contrastive loss helps the network to learn a nonlinear mapping function that enables it to map the extracted features in the vector space with an optimal way.The proposed network is evaluated on the challenging Chars74K datasets by conducting two experiments.One is for testing the proposed network in few-shot learning while the other is for testing it in zero-shot learning.The recognition accuracy of the proposed network reaches to 85.6%and 82%in few-and zero-shot learning respectively.In addition,a comparison between the performance of the proposed Siamese network and the traditional Siamese CNNs is conducted.The comparison results show that the proposed network achieves higher recognition results in less time.The proposed network reduces the training time from days to hours in both experiments.
基金National Natural Science Foundation of China(No.62176052)。
文摘Large language models(LLMs)have demonstrated remarkable generalization abilities across multiple tasks in natural language processing(NLP).For multi-step reasoning tasks,chain-of-thought(CoT)prompting facilitates step-by-step thinking,leading to improved performance.However,despite significant advancements in LLMs,current CoT prompting performs suboptimally on smaller-scale models that have fewer parameters.Additionally,the common paradigm of few-shot CoT prompting relies on a set of manual demonstrations,with performance contingent on the quality of these annotations and varying with task-specific requirements.To address these limitations,we propose a select-and-answer prompting method(SAP)to enhance language model performance on reasoning tasks without the need for manual demonstrations.This method comprises two primary steps:guiding the model to conduct preliminary analysis and generate several candidate answers based on the prompting;allowing the model to provide final answers derived from these candidate answers.The proposed prompting strategy is evaluated across two language models of varying sizes and six datasets.On ChatGLM-6B,SAP consistently outperforms few-shot CoT across all datasets.For GPT-3.5,SAP achieves comparable performance to few-shot CoT and outperforms zero-shot CoT in most cases.These experimental results indicate that SAP can significantly improve the accuracy of language models in reasoning tasks.
文摘The Internet has become one of the significant sources for sharing information and expressing users’opinions about products and their interests with the associated aspects.It is essential to learn about product reviews;however,to react to such reviews,extracting aspects of the entity to which these reviews belong is equally important.Aspect-based Sentiment Analysis(ABSA)refers to aspects extracted from an opinionated text.The literature proposes different approaches for ABSA;however,most research is focused on supervised approaches,which require labeled datasets with manual sentiment polarity labeling and aspect tagging.This study proposes a semisupervised approach with minimal human supervision to extract aspect terms by detecting the aspect categories.Hence,the study deals with two main sub-tasks in ABSA,named Aspect Category Detection(ACD)and Aspect Term Extraction(ATE).In the first sub-task,aspects categories are extracted using topic modeling and filtered by an oracle further,and it is fed to zero-shot learning as the prompts and the augmented text.The predicted categories are the input to find similar phrases curated with extracting meaningful phrases(e.g.,Nouns,Proper Nouns,NER(Named Entity Recognition)entities)to detect the aspect terms.The study sets a baseline accuracy for two main sub-tasks in ABSA on the Multi-Aspect Multi-Sentiment(MAMS)dataset along with SemEval-2014 Task 4 subtask 1 to show that the proposed approach helps detect aspect terms via aspect categories.
基金supported by the National Natural Science Foundation of China under Grant Nos.62072427 and 12227901the Project of Stable Support for Youth Team in Basic Research Field of Chinese Academy of Sciences under Grant No.YSBR-005the Academic Leaders Cultivation Program of University of Science and Technology of China.
文摘Face anti-spoofing aims at detecting whether the input is a real photo of a user(living)or a fake(spoofing)image.As new types of attacks keep emerging,the detection of unknown attacks,known as Zero-Shot Face Anti-Spoofing(ZSFA),has become increasingly important in both academia and industry.Existing ZSFA methods mainly focus on extracting discriminative features between spoofing and living faces.However,the nature of the spoofing faces is to trick anti-spoofing systems by mimicking the livings,therefore the deceptive features between the known attacks and the livings,which have been ignored by existing ZSFA methods,are essential to comprehensively represent the livings.Therefore,existing ZSFA models are incapable of learning the complete representations of living faces and thus fall short of effectively detecting newly emerged attacks.To tackle this problem,we propose an innovative method that effectively captures both the deceptive and discriminative features distinguishing between genuine and spoofing faces.Our method consists of two main components:a two-against-all training strategy and a semantic autoencoder.The two-against-all training strategy is employed to separate deceptive and discriminative features.To address the subsequent invalidation issue of categorical functions and the dominance disequilibrium issue among different dimensions of features after importing deceptive features,we introduce a modified semantic autoencoder.This autoencoder is designed to map all extracted features to a semantic space,thereby achieving a balance in the dominance of each feature dimension.We combine our method with the feature extraction model ResNet50,and experimental results show that the trained ResNet50 model simultaneously achieves a feasible detection of unknown attacks and comparably accurate detection of known spoofing.Experimental results confirm the superiority and effectiveness of our proposed method in identifying the living with the interference of both known and unknown spoofing types.
基金supported by the National Key Research and Development Program of China under Grant No.2020AAA0106200 and the National Natural Science Foundation of China under Grant No.61832016.
文摘In this paper, we present Emotion-Aware Music Driven Movie Montage, a novel paradigm for the challenging task of generating movie montages. Specifically, given a movie and a piece of music as the guidance, our method aims to generate a montage out of the movie that is emotionally consistent with the music. Unlike previous work such as video summarization, this task requires not only video content understanding, but also emotion analysis of both the input movie and music. To this end, we propose a two-stage framework, including a learning-based module for the prediction of emotion similarity and an optimization-based module for the selection and composition of candidate movie shots. The core of our method is to align and estimate emotional similarity between music clips and movie shots in a multi-modal latent space via contrastive learning. Subsequently, the montage generation is modeled as a joint optimization of emotion similarity and additional constraints such as scene-level story completeness and shot-level rhythm synchronization. We conduct both qualitative and quantitative evaluations to demonstrate that our method can generate emotionally consistent montages and outperforms alternative baselines.
