Camouflaged object detection (COD) aims to segment camouflaged objects which exhibit very similar patterns with the surrounding environment. Recent research works have shown that enhancing the feature representation via the frequency information can greatly alleviate the ambiguity problem between the foreground objects and the background. With the emergence of vision foundation models, like InternImage, Segment Anything Model etc, adapting the pretrained model on COD tasks with a lightweight adapter module shows a novel and promising research direction. Existing adapter modules mainly care about the feature adaptation in the spatial domain. In this paper, we propose a novel frequency-guided spatial adaptation method for COD task. Specifically, we transform the input features of the adapter into frequency domain. By grouping and interacting with frequency components located within non overlapping circles in the spectrogram, different frequency components are dynamically enhanced or weakened, making the intensity of image details and contour features adaptively adjusted. At the same time, the features that are conducive to distinguishing object and background are highlighted, indirectly implying the position and shape of camouflaged object. We conduct extensive experiments on four widely adopted benchmark datasets and the proposed method outperforms 26 state-of-the-art methods with large margins. Code will be released.
{"title":"Frequency-Guided Spatial Adaptation for Camouflaged Object Detection","authors":"Shizhou Zhang;Dexuan Kong;Yinghui Xing;Yue Lu;Lingyan Ran;Guoqiang Liang;Hexu Wang;Yanning Zhang","doi":"10.1109/TMM.2024.3521681","DOIUrl":"https://doi.org/10.1109/TMM.2024.3521681","url":null,"abstract":"Camouflaged object detection (COD) aims to segment camouflaged objects which exhibit very similar patterns with the surrounding environment. Recent research works have shown that enhancing the feature representation via the frequency information can greatly alleviate the ambiguity problem between the foreground objects and the background. With the emergence of vision foundation models, like InternImage, Segment Anything Model etc, adapting the pretrained model on COD tasks with a lightweight adapter module shows a novel and promising research direction. Existing adapter modules mainly care about the feature adaptation in the spatial domain. In this paper, we propose a novel frequency-guided spatial adaptation method for COD task. Specifically, we transform the input features of the adapter into frequency domain. By grouping and interacting with frequency components located within non overlapping circles in the spectrogram, different frequency components are dynamically enhanced or weakened, making the intensity of image details and contour features adaptively adjusted. At the same time, the features that are conducive to distinguishing object and background are highlighted, indirectly implying the position and shape of camouflaged object. We conduct extensive experiments on four widely adopted benchmark datasets and the proposed method outperforms 26 state-of-the-art methods with large margins. Code will be released.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"27 ","pages":"72-83"},"PeriodicalIF":8.4,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993824","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 : 2025-01-13DOI: 10.1109/TMM.2024.3521731
Lin Jiang;Jigang Wu;Shuping Zhao;Jiaxing Li
In cross-domain recognition tasks, the divergent distributions of data acquired from various domains degrade the effectiveness of knowledge transfer. Additionally, in practice, cross-domain data also contain a massive amount of redundant information, usually disturbing the training processes of cross-domain classifiers. Seeking to address these issues and obtain efficient domain-invariant knowledge, this paper proposes a novel cross-domain classification method, named cross-scatter sparse dictionary pair learning (CSSDL). Firstly, a pair of dictionaries is learned in a common subspace, in which the marginal distribution divergence between the cross-domain data is mitigated, and domain-invariant information can be efficiently extracted. Then, a cross-scatter discriminant term is proposed to decrease the distance between cross-domain data belonging to the same class. As such, this term guarantees that the data derived from same class can be aligned and that the conditional distribution divergence is mitigated. In addition, a flexible label regression method is introduced to match the feature representation and label information in the label space. Thereafter, a discriminative and transferable feature representation can be obtained. Moreover, two sparse constraints are introduced to maintain the sparse characteristics of the feature representation. Extensive experimental results obtained on public datasets demonstrate the effectiveness of the proposed CSSDL approach.
{"title":"Cross-Scatter Sparse Dictionary Pair Learning for Cross-Domain Classification","authors":"Lin Jiang;Jigang Wu;Shuping Zhao;Jiaxing Li","doi":"10.1109/TMM.2024.3521731","DOIUrl":"https://doi.org/10.1109/TMM.2024.3521731","url":null,"abstract":"In cross-domain recognition tasks, the divergent distributions of data acquired from various domains degrade the effectiveness of knowledge transfer. Additionally, in practice, cross-domain data also contain a massive amount of redundant information, usually disturbing the training processes of cross-domain classifiers. Seeking to address these issues and obtain efficient domain-invariant knowledge, this paper proposes a novel cross-domain classification method, named cross-scatter sparse dictionary pair learning (CSSDL). Firstly, a pair of dictionaries is learned in a common subspace, in which the marginal distribution divergence between the cross-domain data is mitigated, and domain-invariant information can be efficiently extracted. Then, a cross-scatter discriminant term is proposed to decrease the distance between cross-domain data belonging to the same class. As such, this term guarantees that the data derived from same class can be aligned and that the conditional distribution divergence is mitigated. In addition, a flexible label regression method is introduced to match the feature representation and label information in the label space. Thereafter, a discriminative and transferable feature representation can be obtained. Moreover, two sparse constraints are introduced to maintain the sparse characteristics of the feature representation. Extensive experimental results obtained on public datasets demonstrate the effectiveness of the proposed CSSDL approach.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"27 ","pages":"371-384"},"PeriodicalIF":8.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993814","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 : 2025-01-06DOI: 10.1109/TMM.2024.3521671
Yunlong Tang;Yuxuan Wan;Lei Qi;Xin Geng
Source-Free Domain Generalization (SFDG) aims to develop a model that works for unseen target domains without relying on any source domain. Research in SFDG primarily bulids upon the existing knowledge of large-scale vision-language models and utilizes the pre-trained model's joint vision-language space to simulate style transfer across domains, thus eliminating the dependency on source domain images. However, how to efficiently simulate rich and diverse styles using text prompts, and how to extract domain-invariant information useful for classification from features that contain both semantic and style information after the encoder, are directions that merit improvement. In this paper, we introduce Dynamic PromptStyler (DPStyler), comprising Style Generation and Style Removal modules to address these issues. The Style Generation module refreshes all styles at every training epoch, while the Style Removal module eliminates variations in the encoder's output features caused by input styles. Moreover, since the Style Generation module, responsible for generating style word vectors using random sampling or style mixing, makes the model sensitive to input text prompts, we introduce a model ensemble method to mitigate this sensitivity. Extensive experiments demonstrate that our framework outperforms state-of-the-art methods on benchmark datasets.
{"title":"DPStyler: Dynamic PromptStyler for Source-Free Domain Generalization","authors":"Yunlong Tang;Yuxuan Wan;Lei Qi;Xin Geng","doi":"10.1109/TMM.2024.3521671","DOIUrl":"https://doi.org/10.1109/TMM.2024.3521671","url":null,"abstract":"Source-Free Domain Generalization (SFDG) aims to develop a model that works for unseen target domains without relying on any source domain. Research in SFDG primarily bulids upon the existing knowledge of large-scale vision-language models and utilizes the pre-trained model's joint vision-language space to simulate style transfer across domains, thus eliminating the dependency on source domain images. However, how to efficiently simulate rich and diverse styles using text prompts, and how to extract domain-invariant information useful for classification from features that contain both semantic and style information after the encoder, are directions that merit improvement. In this paper, we introduce Dynamic PromptStyler (DPStyler), comprising Style Generation and Style Removal modules to address these issues. The Style Generation module refreshes all styles at every training epoch, while the Style Removal module eliminates variations in the encoder's output features caused by input styles. Moreover, since the Style Generation module, responsible for generating style word vectors using random sampling or style mixing, makes the model sensitive to input text prompts, we introduce a model ensemble method to mitigate this sensitivity. Extensive experiments demonstrate that our framework outperforms state-of-the-art methods on benchmark datasets.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"27 ","pages":"120-132"},"PeriodicalIF":8.4,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993520","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 : 2025-01-03DOI: 10.1109/TMM.2024.3501532
{"title":"List of Reviewers","authors":"","doi":"10.1109/TMM.2024.3501532","DOIUrl":"https://doi.org/10.1109/TMM.2024.3501532","url":null,"abstract":"","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"26 ","pages":"11428-11439"},"PeriodicalIF":8.4,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10823085","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01DOI: 10.1109/TMM.2024.3521676
Kefan Tang;Lihuo He;Nannan Wang;Xinbo Gao
Weakly supervised temporal sentence grounding aims to identify semantically relevant video moments in an untrimmed video corresponding to a given sentence query without exact timestamps. Neuropsychology research indicates that the way the human brain handles information varies based on the grammatical categories of words, highlighting the importance of separately considering nouns and verbs. However, current methodologies primarily utilize pre-extracted video features to reconstruct randomly masked queries, neglecting the distinction between grammatical classes. This oversight could hinder forming meaningful connections between linguistic elements and the corresponding components in the video. To address this limitation, this paper introduces the dual semantic reconstruction network (DSRN) model. DSRN processes video features by distinctly correlating object features with nouns and motion features with verbs, thereby mimicking the human brain's parsing mechanism. It begins with a feature disentanglement module that separately extracts object-aware and motion-aware features from video content. Then, in a dual-branch structure, these disentangled features are used to generate separate proposals for objects and motions through two dedicated proposal generation modules. A consistency constraint is proposed to ensure a high level of agreement between the boundaries of object-related and motion-related proposals. Subsequently, the DSRN independently reconstructs masked nouns and verbs from the sentence queries using the generated proposals. Finally, an integration block is applied to synthesize the two types of proposals, distinguishing between positive and negative instances through contrastive learning. Experiments on the Charades-STA and ActivityNet Captions datasets demonstrate that the proposed method achieves state-of-the-art performance.
{"title":"Dual Semantic Reconstruction Network for Weakly Supervised Temporal Sentence Grounding","authors":"Kefan Tang;Lihuo He;Nannan Wang;Xinbo Gao","doi":"10.1109/TMM.2024.3521676","DOIUrl":"https://doi.org/10.1109/TMM.2024.3521676","url":null,"abstract":"Weakly supervised temporal sentence grounding aims to identify semantically relevant video moments in an untrimmed video corresponding to a given sentence query without exact timestamps. Neuropsychology research indicates that the way the human brain handles information varies based on the grammatical categories of words, highlighting the importance of separately considering nouns and verbs. However, current methodologies primarily utilize pre-extracted video features to reconstruct randomly masked queries, neglecting the distinction between grammatical classes. This oversight could hinder forming meaningful connections between linguistic elements and the corresponding components in the video. To address this limitation, this paper introduces the dual semantic reconstruction network (DSRN) model. DSRN processes video features by distinctly correlating object features with nouns and motion features with verbs, thereby mimicking the human brain's parsing mechanism. It begins with a feature disentanglement module that separately extracts object-aware and motion-aware features from video content. Then, in a dual-branch structure, these disentangled features are used to generate separate proposals for objects and motions through two dedicated proposal generation modules. A consistency constraint is proposed to ensure a high level of agreement between the boundaries of object-related and motion-related proposals. Subsequently, the DSRN independently reconstructs masked nouns and verbs from the sentence queries using the generated proposals. Finally, an integration block is applied to synthesize the two types of proposals, distinguishing between positive and negative instances through contrastive learning. Experiments on the Charades-STA and ActivityNet Captions datasets demonstrate that the proposed method achieves state-of-the-art performance.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"27 ","pages":"95-107"},"PeriodicalIF":8.4,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993523","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}
Person search is a challenging task in computer vision and multimedia understanding, which aims at localizing and identifying target individuals in realistic scenes. State-of-the-art models achieve remarkable success but suffer from overloaded computation and inefficient inference, making them impractical in most real-world applications. A promising approach to tackle this dilemma is to compress person search models with knowledge distillation (KD). Previous KD-based person search methods typically distill the knowledge from the re-identification (re-id) branch, completely overlooking the useful knowledge from the detection branch. In addition, we elucidate that the imbalance between person and background regions in feature maps has a negative impact on the distillation process. To this end, we propose a novel KD-based approach, namely Disaggregation Distillation for Person Search (DDPS), which disaggregates the distillation process and feature maps, respectively. Firstly, the distillation process is disaggregated into two task-oriented sub-processes, i.e., detection distillation and re-id distillation, to help the student learn both accurate localization capability and discriminative person embeddings. Secondly, we disaggregate each feature map into person and background regions, and distill these two regions independently to alleviate the imbalance problem. More concretely, three types of distillation modules, i.e., logit distillation (LD), correlation distillation (CD), and disaggregation feature distillation (DFD), are particularly designed to transfer comprehensive information from the teacher to the student. Note that such a simple yet effective distillation scheme can be readily applied to both homogeneous and heterogeneous teacher-student combinations. We conduct extensive experiments on two person search benchmarks, where the results demonstrate that, surprisingly, our DDPS enables the student model to surpass the performance of the corresponding teacher model, even achieving comparable results with general person search models.
人物搜索是计算机视觉和多媒体理解领域的一项具有挑战性的任务，其目的是在现实场景中定位和识别目标个体。最先进的模型取得了显著的成功，但受到计算过载和推理效率低下的影响，使其在大多数实际应用中不切实际。解决这一困境的一个很有前途的方法是用知识蒸馏（KD）压缩人员搜索模型。以前基于kd的人员搜索方法通常是从重新识别分支中提取知识，而完全忽略了从检测分支中提取的有用知识。此外，我们阐明了特征映射中人物和背景区域之间的不平衡对蒸馏过程有负面影响。为此，我们提出了一种新的基于kd的方法，即Disaggregation Distillation for Person Search (DDPS)，它分别分解了蒸馏过程和特征映射。首先，将蒸馏过程分解为两个面向任务的子过程，即检测蒸馏和重新识别蒸馏，以帮助学生学习准确的定位能力和判别性的人嵌入。其次，我们将每个特征映射分解为人物和背景区域，并将这两个区域独立提取，以缓解不平衡问题；更具体地说，专门设计了三种类型的蒸馏模块，即logit蒸馏（LD），相关蒸馏（CD）和分解特征蒸馏（DFD），以将全面的信息从教师传递给学生。注意，这种简单而有效的蒸馏方案可以很容易地应用于同质和异质师生组合。我们在两个人物搜索基准上进行了广泛的实验，结果表明，令人惊讶的是，我们的DDPS使学生模型的性能超过了相应的教师模型，甚至达到了与一般人物搜索模型相当的结果。
{"title":"Disaggregation Distillation for Person Search","authors":"Yizhen Jia;Rong Quan;Haiyan Chen;Jiamei Liu;Yichao Yan;Song Bai;Jie Qin","doi":"10.1109/TMM.2024.3521732","DOIUrl":"https://doi.org/10.1109/TMM.2024.3521732","url":null,"abstract":"Person search is a challenging task in computer vision and multimedia understanding, which aims at localizing and identifying target individuals in realistic scenes. State-of-the-art models achieve remarkable success but suffer from overloaded computation and inefficient inference, making them impractical in most real-world applications. A promising approach to tackle this dilemma is to compress person search models with knowledge distillation (KD). Previous KD-based person search methods typically distill the knowledge from the re-identification (re-id) branch, completely overlooking the useful knowledge from the detection branch. In addition, we elucidate that the imbalance between person and background regions in feature maps has a negative impact on the distillation process. To this end, we propose a novel KD-based approach, namely Disaggregation Distillation for Person Search (DDPS), which disaggregates the distillation process and feature maps, respectively. Firstly, the distillation process is disaggregated into two task-oriented sub-processes, <italic>i.e.</i>, detection distillation and re-id distillation, to help the student learn both accurate localization capability and discriminative person embeddings. Secondly, we disaggregate each feature map into person and background regions, and distill these two regions independently to alleviate the imbalance problem. More concretely, three types of distillation modules, <italic>i.e.</i>, logit distillation (LD), correlation distillation (CD), and disaggregation feature distillation (DFD), are particularly designed to transfer comprehensive information from the teacher to the student. Note that such a simple yet effective distillation scheme can be readily applied to both homogeneous and heterogeneous teacher-student combinations. We conduct extensive experiments on two person search benchmarks, where the results demonstrate that, surprisingly, our DDPS enables the student model to surpass the performance of the corresponding teacher model, even achieving comparable results with general person search models.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"27 ","pages":"158-170"},"PeriodicalIF":8.4,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993576","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}
Vision-Language Models (VLMs), pre-trained on large-scale datasets, have shown impressive performance in various visual recognition tasks. This advancement paves the way for notable performance in some egocentric tasks, Zero-Shot Egocentric Action Recognition (ZS-EAR), entailing VLMs zero-shot to recognize actions from first-person videos enriched in more realistic human-environment interactions. Typically, VLMs handle ZS-EAR as a global video-text matching task, which often leads to suboptimal alignment of vision and linguistic knowledge. We propose a refined approach for ZS-EAR using VLMs, emphasizing fine-grained concept-description alignment that capitalizes on the rich semantic and contextual details in egocentric videos. In this work, we introduce a straightforward yet remarkably potent VLM framework, aka GPT4Ego, designed to enhance the fine-grained alignment of concept and description between vision and language. Specifically, we first propose a new Ego-oriented Text Prompting (EgoTP$spadesuit$) scheme, which effectively prompts action-related text-contextual semantics by evolving word-level class names to sentence-level contextual descriptions by ChatGPT with well-designed chain-of-thought textual prompts. Moreover, we design a new Ego-oriented Visual Parsing (EgoVP$clubsuit$) strategy that learns action-related vision-contextual semantics by refining global-level images to part-level contextual concepts with the help of SAM. Extensive experiments demonstrate GPT4Ego significantly outperforms existing VLMs on three large-scale egocentric video benchmarks, i.e., EPIC-KITCHENS-100 (33.2%$uparrow$$_{bm {+9.4}}$), EGTEA (39.6%$uparrow$$_{bm {+5.5}}$), and CharadesEgo (31.5%$uparrow$$_{bm {+2.6}}$). In addition, benefiting from the novel mechanism of fine-grained concept and description alignment, GPT4Ego can sustainably evolve with the advancement of ever-growing pre-trained foundational models. We hope this work can encourage the egocentric community to build more investigation into pre-trained vision-language models.
在大规模数据集上进行预训练的视觉语言模型（VLMs）在各种视觉识别任务中表现出令人印象深刻的性能。这一进步为在一些自我中心任务中的显著表现铺平了道路，零镜头自我中心动作识别（ZS-EAR），要求VLMs零镜头识别来自第一人称视频的动作，这些视频丰富了更现实的人类环境交互。通常，vlm将ZS-EAR处理为全局视频文本匹配任务，这通常会导致视觉和语言知识的次优对齐。我们提出了一种使用vlm的改进ZS-EAR方法，强调细粒度的概念-描述对齐，利用以自我为中心的视频中丰富的语义和上下文细节。在这项工作中，我们引入了一个简单但非常有效的VLM框架，即GPT4Ego，旨在增强视觉和语言之间概念和描述的细粒度一致性。具体而言，我们首先提出了一种新的自我导向文本提示（EgoTP $spadesuit$）方案，该方案通过ChatGPT将词级类名演变为句子级上下文描述，通过精心设计的思维链文本提示，有效地提示与动作相关的文本上下文语义。此外，我们设计了一种新的面向自我的视觉解析（Ego-oriented Visual Parsing, EgoVP $clubsuit$）策略，该策略通过在SAM的帮助下将全局级图像精炼为部分级上下文概念来学习与动作相关的视觉上下文语义。大量实验表明，GPT4Ego在三个大规模以自我为中心的视频基准上显著优于现有的vlm，即EPIC-KITCHENS-100 (33.2%$uparrow$$_{bm {+9.4}}$), EGTEA (39.6%$uparrow$$_{bm {+5.5}}$), and CharadesEgo (31.5%$uparrow$$_{bm {+2.6}}$). In addition, benefiting from the novel mechanism of fine-grained concept and description alignment, GPT4Ego can sustainably evolve with the advancement of ever-growing pre-trained foundational models. We hope this work can encourage the egocentric community to build more investigation into pre-trained vision-language models.
{"title":"GPT4Ego: Unleashing the Potential of Pre-Trained Models for Zero-Shot Egocentric Action Recognition","authors":"Guangzhao Dai;Xiangbo Shu;Wenhao Wu;Rui Yan;Jiachao Zhang","doi":"10.1109/TMM.2024.3521658","DOIUrl":"https://doi.org/10.1109/TMM.2024.3521658","url":null,"abstract":"Vision-Language Models (VLMs), pre-trained on large-scale datasets, have shown impressive performance in various visual recognition tasks. This advancement paves the way for notable performance in some egocentric tasks, Zero-Shot Egocentric Action Recognition (ZS-EAR), entailing VLMs zero-shot to recognize actions from first-person videos enriched in more realistic human-environment interactions. Typically, VLMs handle ZS-EAR as a global video-text matching task, which often leads to suboptimal alignment of vision and linguistic knowledge. We propose a refined approach for ZS-EAR using VLMs, emphasizing fine-grained concept-description alignment that capitalizes on the rich semantic and contextual details in egocentric videos. In this work, we introduce a straightforward yet remarkably potent VLM framework, <italic>aka</i> GPT4Ego, designed to enhance the fine-grained alignment of concept and description between vision and language. Specifically, we first propose a new Ego-oriented Text Prompting (EgoTP<inline-formula><tex-math>$spadesuit$</tex-math></inline-formula>) scheme, which effectively prompts action-related text-contextual semantics by evolving word-level class names to sentence-level contextual descriptions by ChatGPT with well-designed chain-of-thought textual prompts. Moreover, we design a new Ego-oriented Visual Parsing (EgoVP<inline-formula><tex-math>$clubsuit$</tex-math></inline-formula>) strategy that learns action-related vision-contextual semantics by refining global-level images to part-level contextual concepts with the help of SAM. Extensive experiments demonstrate GPT4Ego significantly outperforms existing VLMs on three large-scale egocentric video benchmarks, i.e., EPIC-KITCHENS-100 (33.2%<inline-formula><tex-math>$uparrow$</tex-math></inline-formula><inline-formula><tex-math>$_{bm {+9.4}}$</tex-math></inline-formula>), EGTEA (39.6%<inline-formula><tex-math>$uparrow$</tex-math></inline-formula><inline-formula><tex-math>$_{bm {+5.5}}$</tex-math></inline-formula>), and CharadesEgo (31.5%<inline-formula><tex-math>$uparrow$</tex-math></inline-formula><inline-formula><tex-math>$_{bm {+2.6}}$</tex-math></inline-formula>). In addition, benefiting from the novel mechanism of fine-grained concept and description alignment, GPT4Ego can sustainably evolve with the advancement of ever-growing pre-trained foundational models. We hope this work can encourage the egocentric community to build more investigation into pre-trained vision-language models.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"27 ","pages":"401-413"},"PeriodicalIF":8.4,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993807","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 : 2024-12-25DOI: 10.1109/TMM.2024.3521773
Mengzan Qi;Sixian Chan;Chen Hang;Guixu Zhang;Tieyong Zeng;Zhi Li
Visible-Infrared Person Re-identification aims to retrieve images of specific identities across modalities. To relieve the large cross-modality discrepancy, researchers introduce the auxiliary modality within the image space to assist modality-invariant representation learning. However, the challenge persists in constraining the inherent quality of generated auxiliary images, further leading to a bottleneck in retrieval performance. In this paper, we propose a novel Auxiliary Representation Guided Network (ARGN) to explore the potential of auxiliary representations, which are directly generated within the modality-shared embedding space. In contrast to the original visible and infrared representations, which contain information solely from their respective modalities, these auxiliary representations integrate cross-modality information by fusing both modalities. In our framework, we utilize these auxiliary representations as modality guidance to reduce the cross-modality discrepancy. First, we propose a High-quality Auxiliary Representation Learning (HARL) framework to generate identity-consistent auxiliary representations. The primary objective of our HARL is to ensure that auxiliary representations capture diverse modality information from both modalities while concurrently preserving identity-related discrimination. Second, guided by these auxiliary representations, we design an Auxiliary Representation Guided Constraint (ARGC) to optimize the modality-shared embedding space. By incorporating this constraint, the modality-shared embedding space is optimized to achieve enhanced intra-identity compactness and inter-identity separability, further improving the retrieval performance. In addition, to improve the robustness of our framework against the modality variation, we introduce a Part-based Adaptive Gaussian Module (PAGM) to adaptively extract discriminative information across modalities. Finally, extensive experiments are conducted to demonstrate the superiority of our method over state-of-the-art approaches on three VI-ReID datasets.
{"title":"Auxiliary Representation Guided Network for Visible-Infrared Person Re-Identification","authors":"Mengzan Qi;Sixian Chan;Chen Hang;Guixu Zhang;Tieyong Zeng;Zhi Li","doi":"10.1109/TMM.2024.3521773","DOIUrl":"https://doi.org/10.1109/TMM.2024.3521773","url":null,"abstract":"Visible-Infrared Person Re-identification aims to retrieve images of specific identities across modalities. To relieve the large cross-modality discrepancy, researchers introduce the auxiliary modality within the image space to assist modality-invariant representation learning. However, the challenge persists in constraining the inherent quality of generated auxiliary images, further leading to a bottleneck in retrieval performance. In this paper, we propose a novel Auxiliary Representation Guided Network (ARGN) to explore the potential of auxiliary representations, which are directly generated within the modality-shared embedding space. In contrast to the original visible and infrared representations, which contain information solely from their respective modalities, these auxiliary representations integrate cross-modality information by fusing both modalities. In our framework, we utilize these auxiliary representations as modality guidance to reduce the cross-modality discrepancy. First, we propose a High-quality Auxiliary Representation Learning (HARL) framework to generate identity-consistent auxiliary representations. The primary objective of our HARL is to ensure that auxiliary representations capture diverse modality information from both modalities while concurrently preserving identity-related discrimination. Second, guided by these auxiliary representations, we design an Auxiliary Representation Guided Constraint (ARGC) to optimize the modality-shared embedding space. By incorporating this constraint, the modality-shared embedding space is optimized to achieve enhanced intra-identity compactness and inter-identity separability, further improving the retrieval performance. In addition, to improve the robustness of our framework against the modality variation, we introduce a Part-based Adaptive Gaussian Module (PAGM) to adaptively extract discriminative information across modalities. Finally, extensive experiments are conducted to demonstrate the superiority of our method over state-of-the-art approaches on three VI-ReID datasets.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"27 ","pages":"340-355"},"PeriodicalIF":8.4,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993832","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 : 2024-12-25DOI: 10.1109/TMM.2024.3521797
Xu Han;Junyu Gao;Chuang Yang;Yuan Yuan;Qi Wang
Due to the diversity of scene text in aspects such as font, color, shape, and size, accurately and efficiently detecting text is still a formidable challenge. Among the various detection approaches, segmentation-based approaches have emerged as prominent contenders owing to their flexible pixel-level predictions. However, these methods typically model text instances in a bottom-up manner, which is highly susceptible to noise. In addition, the prediction of pixels is isolated without introducing pixel-feature interaction, which also influences the detection performance. To alleviate these problems, we propose a multi-information level arbitrary-shaped text detector consisting of a focus entirety module (FEM) and a perceive environment module (PEM). The former extracts instance-level features and adopts a top-down scheme to model texts to reduce the influence of noises. Specifically, it assigns consistent entirety information to pixels within the same instance to improve their cohesion. In addition, it emphasizes the scale information, enabling the model to distinguish varying scale texts effectively. The latter extracts region-level information and encourages the model to focus on the distribution of positive samples in the vicinity of a pixel, which perceives environment information. It treats the kernel pixels as positive samples and helps the model differentiate text and kernel features. Extensive experiments demonstrate the FEM's ability to efficiently support the model in handling different scale texts and confirm the PEM can assist in perceiving pixels more accurately by focusing on pixel vicinities. Comparisons show the proposed model outperforms existing state-of-the-art approaches on four public datasets.
{"title":"Focus Entirety and Perceive Environment for Arbitrary-Shaped Text Detection","authors":"Xu Han;Junyu Gao;Chuang Yang;Yuan Yuan;Qi Wang","doi":"10.1109/TMM.2024.3521797","DOIUrl":"https://doi.org/10.1109/TMM.2024.3521797","url":null,"abstract":"Due to the diversity of scene text in aspects such as font, color, shape, and size, accurately and efficiently detecting text is still a formidable challenge. Among the various detection approaches, segmentation-based approaches have emerged as prominent contenders owing to their flexible pixel-level predictions. However, these methods typically model text instances in a bottom-up manner, which is highly susceptible to noise. In addition, the prediction of pixels is isolated without introducing pixel-feature interaction, which also influences the detection performance. To alleviate these problems, we propose a multi-information level arbitrary-shaped text detector consisting of a focus entirety module (FEM) and a perceive environment module (PEM). The former extracts instance-level features and adopts a top-down scheme to model texts to reduce the influence of noises. Specifically, it assigns consistent entirety information to pixels within the same instance to improve their cohesion. In addition, it emphasizes the scale information, enabling the model to distinguish varying scale texts effectively. The latter extracts region-level information and encourages the model to focus on the distribution of positive samples in the vicinity of a pixel, which perceives environment information. It treats the kernel pixels as positive samples and helps the model differentiate text and kernel features. Extensive experiments demonstrate the FEM's ability to efficiently support the model in handling different scale texts and confirm the PEM can assist in perceiving pixels more accurately by focusing on pixel vicinities. Comparisons show the proposed model outperforms existing state-of-the-art approaches on four public datasets.","PeriodicalId":13273,"journal":{"name":"IEEE Transactions on Multimedia","volume":"27 ","pages":"287-299"},"PeriodicalIF":8.4,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993743","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：