In the video captioning methods based on an encoder-decoder,limited visual features are extracted by an encoder,and a natural sentence of the video content is generated using a decoder.However,this kind ofmethod is de...In the video captioning methods based on an encoder-decoder,limited visual features are extracted by an encoder,and a natural sentence of the video content is generated using a decoder.However,this kind ofmethod is dependent on a single video input source and few visual labels,and there is a problem with semantic alignment between video contents and generated natural sentences,which are not suitable for accurately comprehending and describing the video contents.To address this issue,this paper proposes a video captioning method by semantic topic-guided generation.First,a 3D convolutional neural network is utilized to extract the spatiotemporal features of videos during the encoding.Then,the semantic topics of video data are extracted using the visual labels retrieved from similar video data.In the decoding,a decoder is constructed by combining a novel Enhance-TopK sampling algorithm with a Generative Pre-trained Transformer-2 deep neural network,which decreases the influence of“deviation”in the semantic mapping process between videos and texts by jointly decoding a baseline and semantic topics of video contents.During this process,the designed Enhance-TopK sampling algorithm can alleviate a long-tail problem by dynamically adjusting the probability distribution of the predicted words.Finally,the experiments are conducted on two publicly used Microsoft Research Video Description andMicrosoft Research-Video to Text datasets.The experimental results demonstrate that the proposed method outperforms several state-of-art approaches.Specifically,the performance indicators Bilingual Evaluation Understudy,Metric for Evaluation of Translation with Explicit Ordering,Recall Oriented Understudy for Gisting Evaluation-longest common subsequence,and Consensus-based Image Description Evaluation of the proposed method are improved by 1.2%,0.1%,0.3%,and 2.4% on the Microsoft Research Video Description dataset,and 0.1%,1.0%,0.1%,and 2.8% on the Microsoft Research-Video to Text dataset,respectively,compared with the existing video captioning methods.As a result,the proposed method can generate video captioning that is more closely aligned with human natural language expression habits.展开更多
Currently,the video captioning models based on an encoder-decoder mainly rely on a single video input source.The contents of video captioning are limited since few studies employed external corpus information to guide...Currently,the video captioning models based on an encoder-decoder mainly rely on a single video input source.The contents of video captioning are limited since few studies employed external corpus information to guide the generation of video captioning,which is not conducive to the accurate descrip-tion and understanding of video content.To address this issue,a novel video captioning method guided by a sentence retrieval generation network(ED-SRG)is proposed in this paper.First,a ResNeXt network model,an efficient convolutional network for online video understanding(ECO)model,and a long short-term memory(LSTM)network model are integrated to construct an encoder-decoder,which is utilized to extract the 2D features,3D features,and object features of video data respectively.These features are decoded to generate textual sentences that conform to video content for sentence retrieval.Then,a sentence-transformer network model is employed to retrieve different sentences in an external corpus that are semantically similar to the above textual sentences.The candidate sentences are screened out through similarity measurement.Finally,a novel GPT-2 network model is constructed based on GPT-2 network structure.The model introduces a designed random selector to randomly select predicted words with a high probability in the corpus,which is used to guide and generate textual sentences that are more in line with human natural language expressions.The proposed method in this paper is compared with several existing works by experiments.The results show that the indicators BLEU-4,CIDEr,ROUGE_L,and METEOR are improved by 3.1%,1.3%,0.3%,and 1.5%on a public dataset MSVD and 1.3%,0.5%,0.2%,1.9%on a public dataset MSR-VTT respectively.It can be seen that the proposed method in this paper can generate video captioning with richer semantics than several state-of-the-art approaches.展开更多
Video description generates natural language sentences that describe the subject,verb,and objects of the targeted Video.The video description has been used to help visually impaired people to understand the content.It...Video description generates natural language sentences that describe the subject,verb,and objects of the targeted Video.The video description has been used to help visually impaired people to understand the content.It is also playing an essential role in devolving human-robot interaction.The dense video description is more difficult when compared with simple Video captioning because of the object’s interactions and event overlapping.Deep learning is changing the shape of computer vision(CV)technologies and natural language processing(NLP).There are hundreds of deep learning models,datasets,and evaluations that can improve the gaps in current research.This article filled this gap by evaluating some state-of-the-art approaches,especially focusing on deep learning and machine learning for video caption in a dense environment.In this article,some classic techniques concerning the existing machine learning were reviewed.And provides deep learning models,a detail of benchmark datasets with their respective domains.This paper reviews various evaluation metrics,including Bilingual EvaluationUnderstudy(BLEU),Metric for Evaluation of Translation with Explicit Ordering(METEOR),WordMover’s Distance(WMD),and Recall-Oriented Understudy for Gisting Evaluation(ROUGE)with their pros and cons.Finally,this article listed some future directions and proposed work for context enhancement using key scene extraction with object detection in a particular frame.Especially,how to improve the context of video description by analyzing key frames detection through morphological image analysis.Additionally,the paper discusses a novel approach involving sentence reconstruction and context improvement through key frame object detection,which incorporates the fusion of large languagemodels for refining results.The ultimate results arise fromenhancing the generated text of the proposedmodel by improving the predicted text and isolating objects using various keyframes.These keyframes identify dense events occurring in the video sequence.展开更多
For news video images, caption recognizing is a useful and important step for content understanding. Caption locating is usually the first step of caption recognizing and this paper proposes a simple but effective cap...For news video images, caption recognizing is a useful and important step for content understanding. Caption locating is usually the first step of caption recognizing and this paper proposes a simple but effective caption locating algorithm called maximum feature score region （MFSR） based method, which mainly consists of two stages： In the first stage, up/down boundaries are attained by turning to edge map projection. Then, maximum feature score region is defined and left/right boundaries are achieved by utilizing MFSR. Experiments show that the proposed MFSR based method has superior and robust performance on news video images of different types.展开更多
视频字幕生成(Video Captioning)旨在用自然语言描述视频中的内容,在人机交互、辅助视障人士、体育视频解说等领域具有广泛的应用前景。然而视频中复杂的时空内容变化增加了视频字幕生成的难度,之前的方法通过提取时空特征、先验信息等...视频字幕生成(Video Captioning)旨在用自然语言描述视频中的内容,在人机交互、辅助视障人士、体育视频解说等领域具有广泛的应用前景。然而视频中复杂的时空内容变化增加了视频字幕生成的难度,之前的方法通过提取时空特征、先验信息等方式提高生成字幕的质量,但在时空联合建模方面仍存在不足,可能导致视觉信息提取不充分,影响字幕生成结果。为了解决这个问题,本文提出一种新颖的时空增强的状态空间模型和Transformer(SpatioTemporal-enhanced State space model and Transformer,ST2)模型,通过引入最近流行的具有全局感受野和线性的计算复杂度的Mamba(一种状态空间模型),增强时空联合建模能力。首先,通过将Mamba与Transformer并行结合,提出空间增强的状态空间模型(State Space Model,SSM)和Transformer(Spatial enHanced State space model and Transformer module,SH-ST),克服了卷积的感受野问题并降低计算复杂度,同时增强模型提取空间信息的能力。然后为了增强时间建模,我们利用Mamba的时间扫描特性,并结合Transformer的全局建模能力,提出时间增强的SSM和Transformer(Temporal enHanced State space model and Transformer module,TH-ST)。具体地,我们对SH-ST产生的特征进行重排序,从而使Mamba以交叉扫描的方式增强重排序后特征的时间关系,最后用Transformer进一步增强时间建模能力。实验结果表明,我们ST2模型中SH-ST和TH-ST结构设计的有效性,且在广泛使用的视频字幕生成数据集MSVD和MSR-VTT上取得了具有竞争力的结果。具体的,我们的方法分别在MSVD和MSR-VTT数据集上的绝对CIDEr分数超过最先进的结果6.9%和2.6%,在MSVD上的绝对CIDEr分数超过了基线结果4.9%。展开更多
基金supported in part by the National Natural Science Foundation of China under Grant 61873277in part by the Natural Science Basic Research Plan in Shaanxi Province of China underGrant 2020JQ-758in part by the Chinese Postdoctoral Science Foundation under Grant 2020M673446.
文摘In the video captioning methods based on an encoder-decoder,limited visual features are extracted by an encoder,and a natural sentence of the video content is generated using a decoder.However,this kind ofmethod is dependent on a single video input source and few visual labels,and there is a problem with semantic alignment between video contents and generated natural sentences,which are not suitable for accurately comprehending and describing the video contents.To address this issue,this paper proposes a video captioning method by semantic topic-guided generation.First,a 3D convolutional neural network is utilized to extract the spatiotemporal features of videos during the encoding.Then,the semantic topics of video data are extracted using the visual labels retrieved from similar video data.In the decoding,a decoder is constructed by combining a novel Enhance-TopK sampling algorithm with a Generative Pre-trained Transformer-2 deep neural network,which decreases the influence of“deviation”in the semantic mapping process between videos and texts by jointly decoding a baseline and semantic topics of video contents.During this process,the designed Enhance-TopK sampling algorithm can alleviate a long-tail problem by dynamically adjusting the probability distribution of the predicted words.Finally,the experiments are conducted on two publicly used Microsoft Research Video Description andMicrosoft Research-Video to Text datasets.The experimental results demonstrate that the proposed method outperforms several state-of-art approaches.Specifically,the performance indicators Bilingual Evaluation Understudy,Metric for Evaluation of Translation with Explicit Ordering,Recall Oriented Understudy for Gisting Evaluation-longest common subsequence,and Consensus-based Image Description Evaluation of the proposed method are improved by 1.2%,0.1%,0.3%,and 2.4% on the Microsoft Research Video Description dataset,and 0.1%,1.0%,0.1%,and 2.8% on the Microsoft Research-Video to Text dataset,respectively,compared with the existing video captioning methods.As a result,the proposed method can generate video captioning that is more closely aligned with human natural language expression habits.
基金supported in part by the National Natural Science Foundation of China under Grants 62273272 and 61873277in part by the Chinese Postdoctoral Science Foundation under Grant 2020M673446+1 种基金in part by the Key Research and Development Program of Shaanxi Province under Grant 2023-YBGY-243in part by the Youth Innovation Team of Shaanxi Universities.
文摘Currently,the video captioning models based on an encoder-decoder mainly rely on a single video input source.The contents of video captioning are limited since few studies employed external corpus information to guide the generation of video captioning,which is not conducive to the accurate descrip-tion and understanding of video content.To address this issue,a novel video captioning method guided by a sentence retrieval generation network(ED-SRG)is proposed in this paper.First,a ResNeXt network model,an efficient convolutional network for online video understanding(ECO)model,and a long short-term memory(LSTM)network model are integrated to construct an encoder-decoder,which is utilized to extract the 2D features,3D features,and object features of video data respectively.These features are decoded to generate textual sentences that conform to video content for sentence retrieval.Then,a sentence-transformer network model is employed to retrieve different sentences in an external corpus that are semantically similar to the above textual sentences.The candidate sentences are screened out through similarity measurement.Finally,a novel GPT-2 network model is constructed based on GPT-2 network structure.The model introduces a designed random selector to randomly select predicted words with a high probability in the corpus,which is used to guide and generate textual sentences that are more in line with human natural language expressions.The proposed method in this paper is compared with several existing works by experiments.The results show that the indicators BLEU-4,CIDEr,ROUGE_L,and METEOR are improved by 3.1%,1.3%,0.3%,and 1.5%on a public dataset MSVD and 1.3%,0.5%,0.2%,1.9%on a public dataset MSR-VTT respectively.It can be seen that the proposed method in this paper can generate video captioning with richer semantics than several state-of-the-art approaches.
文摘Video description generates natural language sentences that describe the subject,verb,and objects of the targeted Video.The video description has been used to help visually impaired people to understand the content.It is also playing an essential role in devolving human-robot interaction.The dense video description is more difficult when compared with simple Video captioning because of the object’s interactions and event overlapping.Deep learning is changing the shape of computer vision(CV)technologies and natural language processing(NLP).There are hundreds of deep learning models,datasets,and evaluations that can improve the gaps in current research.This article filled this gap by evaluating some state-of-the-art approaches,especially focusing on deep learning and machine learning for video caption in a dense environment.In this article,some classic techniques concerning the existing machine learning were reviewed.And provides deep learning models,a detail of benchmark datasets with their respective domains.This paper reviews various evaluation metrics,including Bilingual EvaluationUnderstudy(BLEU),Metric for Evaluation of Translation with Explicit Ordering(METEOR),WordMover’s Distance(WMD),and Recall-Oriented Understudy for Gisting Evaluation(ROUGE)with their pros and cons.Finally,this article listed some future directions and proposed work for context enhancement using key scene extraction with object detection in a particular frame.Especially,how to improve the context of video description by analyzing key frames detection through morphological image analysis.Additionally,the paper discusses a novel approach involving sentence reconstruction and context improvement through key frame object detection,which incorporates the fusion of large languagemodels for refining results.The ultimate results arise fromenhancing the generated text of the proposedmodel by improving the predicted text and isolating objects using various keyframes.These keyframes identify dense events occurring in the video sequence.
基金supported by National Natural Science Foundation of China(Nos.61272394,61201395 and61472119)the program for Science&Technology Innovation Talents in Universities of Henan Province(No.13HASTIT039)+1 种基金Henan Polytechnic University Innovative Research Team(No.T2014-3)Henan Polytechnic University Fund for Distinguished Young Scholars(No.J2013-2)
文摘For news video images, caption recognizing is a useful and important step for content understanding. Caption locating is usually the first step of caption recognizing and this paper proposes a simple but effective caption locating algorithm called maximum feature score region （MFSR） based method, which mainly consists of two stages： In the first stage, up/down boundaries are attained by turning to edge map projection. Then, maximum feature score region is defined and left/right boundaries are achieved by utilizing MFSR. Experiments show that the proposed MFSR based method has superior and robust performance on news video images of different types.
文摘视频字幕生成(Video Captioning)旨在用自然语言描述视频中的内容,在人机交互、辅助视障人士、体育视频解说等领域具有广泛的应用前景。然而视频中复杂的时空内容变化增加了视频字幕生成的难度,之前的方法通过提取时空特征、先验信息等方式提高生成字幕的质量,但在时空联合建模方面仍存在不足,可能导致视觉信息提取不充分,影响字幕生成结果。为了解决这个问题,本文提出一种新颖的时空增强的状态空间模型和Transformer(SpatioTemporal-enhanced State space model and Transformer,ST2)模型,通过引入最近流行的具有全局感受野和线性的计算复杂度的Mamba(一种状态空间模型),增强时空联合建模能力。首先,通过将Mamba与Transformer并行结合,提出空间增强的状态空间模型(State Space Model,SSM)和Transformer(Spatial enHanced State space model and Transformer module,SH-ST),克服了卷积的感受野问题并降低计算复杂度,同时增强模型提取空间信息的能力。然后为了增强时间建模,我们利用Mamba的时间扫描特性,并结合Transformer的全局建模能力,提出时间增强的SSM和Transformer(Temporal enHanced State space model and Transformer module,TH-ST)。具体地,我们对SH-ST产生的特征进行重排序,从而使Mamba以交叉扫描的方式增强重排序后特征的时间关系,最后用Transformer进一步增强时间建模能力。实验结果表明,我们ST2模型中SH-ST和TH-ST结构设计的有效性,且在广泛使用的视频字幕生成数据集MSVD和MSR-VTT上取得了具有竞争力的结果。具体的,我们的方法分别在MSVD和MSR-VTT数据集上的绝对CIDEr分数超过最先进的结果6.9%和2.6%,在MSVD上的绝对CIDEr分数超过了基线结果4.9%。
