Pub Date : 2024-07-15DOI: 10.1109/tmm.2024.3428317
Yunxin Li, Baotian Hu, Xinyu Chen, Lin Ma, Yong Xu, Min Zhang
{"title":"LMEye: An Interactive Perception Network for Large Language Models","authors":"Yunxin Li, Baotian Hu, Xinyu Chen, Lin Ma, Yong Xu, Min Zhang","doi":"10.1109/tmm.2024.3428317","DOIUrl":"https://doi.org/10.1109/tmm.2024.3428317","url":null,"abstract":"","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"74 1","pages":""},"PeriodicalIF":7.3,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141720781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Video compression leads to compression artifacts, among which Perceivable Encoding Artifacts (PEAs) degrade user perception. Most of existing state-of-the-art Video Compression Artifact Removal (VCAR) methods indiscriminately process all artifacts, thus leading to over-enhancement in non-PEA regions. Therefore, accurate detection and location of PEAs is crucial. In this paper, we propose the largest-ever Fine-grained PEA database (FPEA). First, we employ the popular video codecs, VVC and AVS3, as well as their common test settings, to generate four types of spatial PEAs (blurring, blocking, ringing and color bleeding) and two types of temporal PEAs (flickering and floating). Second, we design a labeling platform and recruit sufficient subjects to manually locate all the above types of PEAs. Third, we propose a voting mechanism and feature matching to synthesize all subjective labels to obtain the final PEA labels with fine-grained locations. Besides, we also provide Mean Opinion Score (MOS) values of all compressed video sequences. Experimental results show the effectiveness of FPEA database on both VCAR and compressed Video Quality Assessment (VQA). We envision that FPEA database will benefit the future development of VCAR, VQA and perception-aware video encoders. The FPEA database has been made publicly available.
视频压缩会产生压缩伪影，其中的可感知编码伪影（PEAs）会降低用户的感知能力。现有的大多数最先进的视频压缩伪影去除（VCAR）方法会不加区分地处理所有伪影，从而导致非 PEA 区域的过度增强。因此，准确检测和定位 PEA 至关重要。在本文中，我们提出了有史以来最大的细粒度 PEA 数据库 (FPEA)。首先，我们采用流行的视频编解码器 VVC 和 AVS3 及其常用测试设置，生成四种空间 PEA（模糊、阻塞、振铃和渗色）和两种时间 PEA（闪烁和浮动）。其次，我们设计了一个标记平台，并招募了足够多的受试者来手动定位上述所有类型的 PEA。第三，我们提出了一种投票机制和特征匹配来综合所有的主观标签，从而得到具有精细定位的最终 PEA 标签。此外，我们还提供了所有压缩视频序列的平均意见分值（MOS）。实验结果表明，FPEA 数据库在 VCAR 和压缩视频质量评估（VQA）方面都很有效。我们认为 FPEA 数据库将有利于 VCAR、VQA 和感知型视频编码器的未来发展。FPEA 数据库已公开发布。
{"title":"Toward Efficient Video Compression Artifact Detection and Removal: A Benchmark Dataset","authors":"Liqun Lin;Mingxing Wang;Jing Yang;Keke Zhang;Tiesong Zhao","doi":"10.1109/TMM.2024.3414549","DOIUrl":"10.1109/TMM.2024.3414549","url":null,"abstract":"Video compression leads to compression artifacts, among which Perceivable Encoding Artifacts (PEAs) degrade user perception. Most of existing state-of-the-art Video Compression Artifact Removal (VCAR) methods indiscriminately process all artifacts, thus leading to over-enhancement in non-PEA regions. Therefore, accurate detection and location of PEAs is crucial. In this paper, we propose the largest-ever Fine-grained PEA database (FPEA). First, we employ the popular video codecs, VVC and AVS3, as well as their common test settings, to generate four types of spatial PEAs (blurring, blocking, ringing and color bleeding) and two types of temporal PEAs (flickering and floating). Second, we design a labeling platform and recruit sufficient subjects to manually locate all the above types of PEAs. Third, we propose a voting mechanism and feature matching to synthesize all subjective labels to obtain the final PEA labels with fine-grained locations. Besides, we also provide Mean Opinion Score (MOS) values of all compressed video sequences. Experimental results show the effectiveness of FPEA database on both VCAR and compressed Video Quality Assessment (VQA). We envision that FPEA database will benefit the future development of VCAR, VQA and perception-aware video encoders. The FPEA database has been made publicly available.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"26 ","pages":"10816-10827"},"PeriodicalIF":8.4,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141549758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the domain of video surveillance, describing the behavior of each individual within the video is becoming increasingly essential, especially in complex scenarios with multiple individuals present. This is because describing each individual's behavior provides more detailed situational analysis, enabling accurate assessment and response to potential risks, ensuring the safety and harmony of public places. Currently, video-level captioning datasets cannot provide fine-grained descriptions for each individual's specific behavior. However, mere descriptions at the video-level fail to provide an in-depth interpretation of individual behaviors, making it challenging to accurately determine the specific identity of each individual. To address this challenge, we construct a human-centric video surveillance captioning dataset, which provides detailed descriptions of the dynamic behaviors of 7,820 individuals. Specifically, we have labeled several aspects of each person, such as location, clothing, and interactions with other elements in the scene, and these people are distributed across 1,012 videos. Based on this dataset, we can link individuals to their respective behaviors, allowing for further analysis of each person's behavior in surveillance videos. Besides the dataset, we propose a novel video captioning approach that can describe individual behavior in detail on a person-level basis, achieving state-of-the-art results.
{"title":"Human-Centric Behavior Description in Videos: New Benchmark and Model","authors":"Lingru Zhou;Yiqi Gao;Manqing Zhang;Peng Wu;Peng Wang;Yanning Zhang","doi":"10.1109/TMM.2024.3414263","DOIUrl":"10.1109/TMM.2024.3414263","url":null,"abstract":"In the domain of video surveillance, describing the behavior of each individual within the video is becoming increasingly essential, especially in complex scenarios with multiple individuals present. This is because describing each individual's behavior provides more detailed situational analysis, enabling accurate assessment and response to potential risks, ensuring the safety and harmony of public places. Currently, video-level captioning datasets cannot provide fine-grained descriptions for each individual's specific behavior. However, mere descriptions at the video-level fail to provide an in-depth interpretation of individual behaviors, making it challenging to accurately determine the specific identity of each individual. To address this challenge, we construct a human-centric video surveillance captioning dataset, which provides detailed descriptions of the dynamic behaviors of 7,820 individuals. Specifically, we have labeled several aspects of each person, such as location, clothing, and interactions with other elements in the scene, and these people are distributed across 1,012 videos. Based on this dataset, we can link individuals to their respective behaviors, allowing for further analysis of each person's behavior in surveillance videos. Besides the dataset, we propose a novel video captioning approach that can describe individual behavior in detail on a person-level basis, achieving state-of-the-art results.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"26 ","pages":"10867-10878"},"PeriodicalIF":8.4,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141531141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-26DOI: 10.1109/TMM.2024.3405724
Peiguang Jing;Xuan Zhao;Fugui Fan;Fan Yang;Yun Li;Yuting Su
Micro-videos, as an increasingly popular form of user-generated content (UGC), naturally include diverse multimodal cues. However, in pursuit of consistent representations, existing methods neglect the simultaneous consideration of exploring modality discrepancy and preserving modality diversity. In this paper, we propose a multimodal progressive modulation network (MPMNet) for micro-video multi-label classification, which enhances the indicative ability of each modality through gradually regulating various modality biases. In MPMNet, we first leverage a unimodal-centered parallel aggregation strategy to obtain preliminary comprehensive representations. We then integrate feature-domain disentangled modulation process and category-domain adaptive modulation process into a unified framework to jointly refine modality-oriented representations. In the former modulation process, we constrain inter-modal dependencies in a latent space to obtain modality-oriented sample representations, and introduce a disentangled paradigm to further maintain modality diversity. In the latter modulation process, we construct global-context-aware graph convolutional networks to acquire modality-oriented category representations, and develop two instance-level parameter generators to further regulate unimodal semantic biases. Extensive experiments on two micro-video multi-label datasets show that our proposed approach outperforms the state-of-the-art methods.
{"title":"Multimodal Progressive Modulation Network for Micro-Video Multi-Label Classification","authors":"Peiguang Jing;Xuan Zhao;Fugui Fan;Fan Yang;Yun Li;Yuting Su","doi":"10.1109/TMM.2024.3405724","DOIUrl":"10.1109/TMM.2024.3405724","url":null,"abstract":"Micro-videos, as an increasingly popular form of user-generated content (UGC), naturally include diverse multimodal cues. However, in pursuit of consistent representations, existing methods neglect the simultaneous consideration of exploring modality discrepancy and preserving modality diversity. In this paper, we propose a multimodal progressive modulation network (MPMNet) for micro-video multi-label classification, which enhances the indicative ability of each modality through gradually regulating various modality biases. In MPMNet, we first leverage a unimodal-centered parallel aggregation strategy to obtain preliminary comprehensive representations. We then integrate feature-domain disentangled modulation process and category-domain adaptive modulation process into a unified framework to jointly refine modality-oriented representations. In the former modulation process, we constrain inter-modal dependencies in a latent space to obtain modality-oriented sample representations, and introduce a disentangled paradigm to further maintain modality diversity. In the latter modulation process, we construct global-context-aware graph convolutional networks to acquire modality-oriented category representations, and develop two instance-level parameter generators to further regulate unimodal semantic biases. Extensive experiments on two micro-video multi-label datasets show that our proposed approach outperforms the state-of-the-art methods.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"26 ","pages":"10134-10144"},"PeriodicalIF":8.4,"publicationDate":"2024-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141528982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Owing to the capacity of performing full-time target searches, cross-modality vehicle re-identification based on unmanned aerial vehicles (UAV) is gaining more attention in both video surveillance and public security. However, this promising and innovative research has not been studied sufficiently due to the issue of data inadequacy. Meanwhile, the cross-modality discrepancy and orientation discrepancy challenges further aggravate the difficulty of this task. To this end, we pioneer a cross-modality vehicle Re-ID benchmark named UAV Cross-Modality Vehicle Re-ID (UCM-VeID), containing 753 identities with 16015 RGB and 13913 infrared images. Moreover, to meet cross-modality discrepancy and orientation discrepancy challenges, we present a hybrid weights decoupling network (HWDNet) to learn the shared discriminative orientation-invariant features. For the first challenge, we proposed a hybrid weights siamese network with a well-designed weight restrainer and its corresponding objective function to learn both modality-specific and modality shared information. In terms of the second challenge, three effective decoupling structures with two pretext tasks are investigated to flexibly conduct orientation-invariant feature separation task. Comprehensive experiments are carried out to validate the effectiveness of the proposed method.
{"title":"Relation-Aware Weight Sharing in Decoupling Feature Learning Network for UAV RGB-Infrared Vehicle Re-Identification","authors":"Xingyue Liu;Jiahao Qi;Chen Chen;Kangcheng Bin;Ping Zhong","doi":"10.1109/TMM.2024.3400675","DOIUrl":"10.1109/TMM.2024.3400675","url":null,"abstract":"Owing to the capacity of performing full-time target searches, cross-modality vehicle re-identification based on unmanned aerial vehicles (UAV) is gaining more attention in both video surveillance and public security. However, this promising and innovative research has not been studied sufficiently due to the issue of data inadequacy. Meanwhile, the cross-modality discrepancy and orientation discrepancy challenges further aggravate the difficulty of this task. To this end, we pioneer a cross-modality vehicle Re-ID benchmark named UAV Cross-Modality Vehicle Re-ID (UCM-VeID), containing 753 identities with \u0000<bold>16015</b>\u0000 RGB and \u0000<bold>13913</b>\u0000 infrared images. Moreover, to meet cross-modality discrepancy and orientation discrepancy challenges, we present a hybrid weights decoupling network (HWDNet) to learn the shared discriminative orientation-invariant features. For the first challenge, we proposed a hybrid weights siamese network with a well-designed weight restrainer and its corresponding objective function to learn both modality-specific and modality shared information. In terms of the second challenge, three effective decoupling structures with two pretext tasks are investigated to flexibly conduct orientation-invariant feature separation task. Comprehensive experiments are carried out to validate the effectiveness of the proposed method.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"26 ","pages":"9839-9853"},"PeriodicalIF":8.4,"publicationDate":"2024-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141517081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-21DOI: 10.1109/TMM.2024.3417694
Yahui Xu;Yi Bin;Jiwei Wei;Yang Yang;Guoqing Wang;Heng Tao Shen
We study the task of image retrieval with text feedback, where a reference image and modification text are composed to retrieve the desired target image. To accomplish this goal, existing methods always get the multimodal representations through different feature encoders and then adopt different strategies to model the correlation between the composed inputs and the target image. However, the multimodal query brings more challenges as it requires not only the synergistic understanding of the semantics from the heterogeneous multimodal inputs but also the ability to accurately build the underlying semantic correlation existing in each inputs-target triplet, i.e., reference image, modification text, and target image. In this paper, we tackle these issues with a novel Align and Retrieve (AlRet) framework. First, our proposed methods employ the contrastive loss in the feature encoders to learn meaningful multimodal representation while making the subsequent correlation modeling process in a more harmonious space. Then we propose to learn the accurate correlation between the composed inputs and target image in a novel composition-and-decomposition paradigm. Specifically, the composition network couples the reference image and modification text into a joint representation to learn the correlation between the joint representation and target image. The decomposition network conversely decouples the target image into visual and text subspaces to exploit the underlying correlation between the target image with each query element. The composition-and-decomposition paradigm forms a closed loop, which can be optimized simultaneously to promote each other in the performance. Massive comparison experiments on three real-world datasets confirm the effectiveness of the proposed method.
{"title":"Align and Retrieve: Composition and Decomposition Learning in Image Retrieval With Text Feedback","authors":"Yahui Xu;Yi Bin;Jiwei Wei;Yang Yang;Guoqing Wang;Heng Tao Shen","doi":"10.1109/TMM.2024.3417694","DOIUrl":"10.1109/TMM.2024.3417694","url":null,"abstract":"We study the task of image retrieval with text feedback, where a reference image and modification text are composed to retrieve the desired target image. To accomplish this goal, existing methods always get the multimodal representations through different feature encoders and then adopt different strategies to model the correlation between the composed inputs and the target image. However, the multimodal query brings more challenges as it requires not only the synergistic understanding of the semantics from the heterogeneous multimodal inputs but also the ability to accurately build the underlying semantic correlation existing in each inputs-target triplet, i.e., reference image, modification text, and target image. In this paper, we tackle these issues with a novel Align and Retrieve (AlRet) framework. First, our proposed methods employ the contrastive loss in the feature encoders to learn meaningful multimodal representation while making the subsequent correlation modeling process in a more harmonious space. Then we propose to learn the accurate correlation between the composed inputs and target image in a novel composition-and-decomposition paradigm. Specifically, the composition network couples the reference image and modification text into a joint representation to learn the correlation between the joint representation and target image. The decomposition network conversely decouples the target image into visual and text subspaces to exploit the underlying correlation between the target image with each query element. The composition-and-decomposition paradigm forms a closed loop, which can be optimized simultaneously to promote each other in the performance. Massive comparison experiments on three real-world datasets confirm the effectiveness of the proposed method.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"26 ","pages":"9936-9948"},"PeriodicalIF":8.4,"publicationDate":"2024-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141504211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-20DOI: 10.1109/TMM.2024.3414660
Demin Gao;Liyuan Ou;Ye Liu;Qing Yang;Honggang Wang
Cross-technology communication is essential for the Internet of Multimedia Things (IoMT) applications, enabling seamless integration of diverse media formats, optimized data transmission, and improved user experiences across devices and platforms. This integration drives innovative and efficient IoMT solutions in areas like smart homes, smart cities, and healthcare monitoring. However, this integration of diverse wireless standards within cross-technology multimedia communication increases the susceptibility of wireless networks to attacks. Current methods lack robust authentication mechanisms, leaving them vulnerable to spoofing attacks. To mitigate this concern, we introduce DeepSpoof, a spoofing system that utilizes deep learning to analyze historical wireless traffic and anticipate future patterns in the IoMT context. This innovative approach significantly boosts an attacker's impersonation capabilities and offers a higher degree of covertness compared to traditional spoofing methods. Rigorous evaluations, leveraging both simulated and real-world data, confirm that DeepSpoof significantly elevates the average success rate of attacks.
{"title":"DeepSpoof: Deep Reinforcement Learning-Based Spoofing Attack in Cross-Technology Multimedia Communication","authors":"Demin Gao;Liyuan Ou;Ye Liu;Qing Yang;Honggang Wang","doi":"10.1109/TMM.2024.3414660","DOIUrl":"10.1109/TMM.2024.3414660","url":null,"abstract":"Cross-technology communication is essential for the Internet of Multimedia Things (IoMT) applications, enabling seamless integration of diverse media formats, optimized data transmission, and improved user experiences across devices and platforms. This integration drives innovative and efficient IoMT solutions in areas like smart homes, smart cities, and healthcare monitoring. However, this integration of diverse wireless standards within cross-technology multimedia communication increases the susceptibility of wireless networks to attacks. Current methods lack robust authentication mechanisms, leaving them vulnerable to spoofing attacks. To mitigate this concern, we introduce DeepSpoof, a spoofing system that utilizes deep learning to analyze historical wireless traffic and anticipate future patterns in the IoMT context. This innovative approach significantly boosts an attacker's impersonation capabilities and offers a higher degree of covertness compared to traditional spoofing methods. Rigorous evaluations, leveraging both simulated and real-world data, confirm that DeepSpoof significantly elevates the average success rate of attacks.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"26 ","pages":"10879-10891"},"PeriodicalIF":8.4,"publicationDate":"2024-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141517082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：