IEEE Transactions on Circuits and Systems for Video Technology最新文献_第6页

Clustered Adaptive Graph Priors Network for Few-Shot Image Denoising 基于聚类自适应图先验网络的小样本图像去噪

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-06-22 DOI: 10.1109/TCSVT.2026.3705049

Bo Jiang;Yao Lu;Huaibo Song;Bob Zhang;Guangming Lu

{"title":"Clustered Adaptive Graph Priors Network for Few-Shot Image Denoising","authors":"Bo Jiang;Yao Lu;Huaibo Song;Bob Zhang;Guangming Lu","doi":"10.1109/TCSVT.2026.3705049","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3705049","url":null,"abstract":"Recently, although current few-shot image denoising methods use limited samples to alleviate the problem of data scarcity, they still suffer from two main problems. Firstly, regular <bold>Convolutional <bold>Neural <bold>Networks (CNNs) cannot explicitly use the relationship between various parts of the image to construct global information in each layer, which hinders the image denoising performance promotion when using limited training samples. Secondly, due to limited training data, especially for noisy images with high diversity and complex noise, the retrieved features are insufficient to recover the denoised image. To address these issues, this work proposes a Clustered Adaptive Graph Priors Network (CAGP-Net) with few-shot learning for image denoising. Specifically, Graph Neural Networks (GNNs) are applied to capture local and global features. Then, a new method is proposed in CAGP-Net to transform image feature maps into graphs to generate local and global features and construct their interdependence. Additionally, to flexibly supplement the feature prior information required for image denoising, we propose a Clustering Adaptive Graph Prior (CAGP) mechanism to supplement the graph prior information learned from embedding features and provide adaptive graph prior information for restoring denoised images. Finally, to further improve the performance of few-shot image denoising methods, we propose a new two-stage few-shot learning strategy, which mainly aims to integrate the reconstruction feature maps from the first stage into each layer of CAGP-Net in the second stage to adaptively remove noise from noisy images. Extensive ablation and benchmark tests show that our CAGP-Net achieves state-of-the-art performance of the few-shot image denoising tasks.","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"15039-15053"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ViKSeR: Visual Knowledge-Driven Self-Reinforcing Reasoning Framework 视觉知识驱动的自我强化推理框架

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-06-25 DOI: 10.1109/TCSVT.2026.3707187

Chao Wang;Chunbai Zhang;Yongxiao Tian;Yang Zhou;Yan Peng

{"title":"ViKSeR: Visual Knowledge-Driven Self-Reinforcing Reasoning Framework","authors":"Chao Wang;Chunbai Zhang;Yongxiao Tian;Yang Zhou;Yan Peng","doi":"10.1109/TCSVT.2026.3707187","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3707187","url":null,"abstract":"Visual reasoning refers to the task of solving questions about visual information. Current visual reasoning methods typically employ pre-trained vision-language model (VLM) strategies or deep neural network approaches. However, existing efforts are constrained by limited reasoning interpretability, while hindered by the phenomenon of underspecification in the question text. Additionally, the absence of fine-grained visual knowledge limits the precise understanding of subject behavior in visual reasoning tasks. To address these issues, we propose <sc>ViKSeR (Visual Knowledge-Driven Self-Reinforcing Reasoning Framework). Specifically, <sc>ViKSeR, trained using knowledge distilled from multimodal large language models, extracts fine-grained visual knowledge with the assistance of visual relationship detection techniques. Subsequently, <sc>ViKSeR utilizes fine-grained visual knowledge to paraphrase the question with underspecification. Additionally, we introduce a tailored prompting strategy called Chain-of-Evidence (CoE), which leverages the power of “evidence for reasoning” to endow <sc>ViKSeR with interpretable reasoning capabilities. Meanwhile, the integration of self-reflection technology empowers <sc>ViKSeR with the ability to learn and improve from its mistakes. Experiments conducted on widely used datasets demonstrate that <sc>ViKSeR achieves new state-of-the-art (SOTA) results in relevant tasks. Moreover, <sc>ViKSeR achieves performance on par with leading proprietary models, such as the latest ChatGPT-5.","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"15097-15109"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Spatially-Aware Video Frame Interpolation for Viewpoint-Varying Sequences 视点变化序列的空间感知视频帧插值

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-06-29 DOI: 10.1109/TCSVT.2026.3708314

Rui Hong;Shanding Diao;Yuan Chen;Yang Zhao;Wei Jia;Ronggang Wang

{"title":"Spatially-Aware Video Frame Interpolation for Viewpoint-Varying Sequences","authors":"Rui Hong;Shanding Diao;Yuan Chen;Yang Zhao;Wei Jia;Ronggang Wang","doi":"10.1109/TCSVT.2026.3708314","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3708314","url":null,"abstract":"Video Frame Interpolation (VFI) is a technique for increasing the frame rate by predicting intermediate frames. Current algorithms typically estimate intermediate frame pixels using dense motion fields like optical flow. The rapid development of embodied vision and free-viewpoint video has introduced more viewpoint changes in videos, posing new challenges for traditional VFI algorithms. Viewpoint synthesis algorithms can learn spatial scene representations from multiple viewpoints to render intermediate viewpoint, providing better spatial information than VFI. However, viewpoint synthesis often introduces visual artifacts in occluded and exposed regions, which are unacceptable in VFI tasks. In contrast, the dense motion fields from traditional VFI can maintain global image quality. This paper proposes a viewpoint synthesis reference-based VFI method for viewpoint-varying videos. To the best of our knowledge, this is the first work to leverage the spatial information from viewpoint synthesis to assist VFI. The proposed method uses a viewpoint synthesis model to predict a multi-plane spatial representation of the scene from adjacent frames, thus rendering intermediate viewpoint. The rendered viewpoint then serves as spatial structure References for the VFI network, enabling the learning of high-quality interpolation results. Experimental results demonstrate that the proposed method can effectively handle the VFI for viewpoint-varying sequences. The source code is available at <uri>https://github.com/xiaorui0319/View-Synthesis-Reference-based-VFI</uri>","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"15172-15186"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

UPhy-Diff: A Text-Guided Multimodal Physical Diffusion Model for Underwater Image Enhancement UPhy-Diff：用于水下图像增强的文本引导多模态物理扩散模型

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-06-05 DOI: 10.1109/TCSVT.2026.3700657

Jingyu Song;Haiyong Xu;Gangyi Jiang;Yeyao Chen;Ting Luo;Yang Song

{"title":"UPhy-Diff: A Text-Guided Multimodal Physical Diffusion Model for Underwater Image Enhancement","authors":"Jingyu Song;Haiyong Xu;Gangyi Jiang;Yeyao Chen;Ting Luo;Yang Song","doi":"10.1109/TCSVT.2026.3700657","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3700657","url":null,"abstract":"Multifaceted environmental degradation inherently obscures critical visual information in underwater imagery. Recently, most underwater image enhancement methods (UIE) neglect physical imaging and multi-modal information compensation. Simultaneously, a domain gap exists between reference images and real-world natural images. To address these limitations, a text-guided multimodal underwater physical diffusion framework (UPhy-Diff) is presented. Specifically, pre-trained foundation models are utilized to generate textual descriptions and relative depth maps, enabling the creation of UIE triplets and expanding diffusion models to RGBD generation tasks. Subsequently, a noise estimation network decoupled from the guiding image, termed Struct-UNet, is proposed. Beneficial features are captured based on the state space model (SSM). Ultimately, during the diffusion sampling stage, physical optimization is incorporated to achieve physically-aware fine-tuning. This compensates to a certain extent for the inter-domain gap caused by reference images and pre-trained large models. Thus, the model is capable of generating high-quality underwater images that align better with human visual perception. Comprehensive experimental evaluations confirm the efficacy and robustness of the proposed method across diverse color distortions, low-light conditions, and underwater haze degradation scenarios.","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"15367-15381"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Time-Perception-Enhanced Video Grounding Framework With Density-Aware Position Encoding 具有密度感知位置编码的时间感知增强视频接地框架

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-06-30 DOI: 10.1109/TCSVT.2026.3708456

Bo Wang;Heyan Huang;Xuefen Li;Ge Shi;Jiahao Teng;Chong Feng

{"title":"Time-Perception-Enhanced Video Grounding Framework With Density-Aware Position Encoding","authors":"Bo Wang;Heyan Huang;Xuefen Li;Ge Shi;Jiahao Teng;Chong Feng","doi":"10.1109/TCSVT.2026.3708456","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3708456","url":null,"abstract":"Existing video-language large models (video-LLMs) have made notable progress in understanding global video content but still struggle to capture fine-grained temporal dynamics and accurately align visual events with textual descriptions. In this work, we introduce DAPE-VLLM (Density-Aware Position Encoding enhanced Video-Language Large Model), a time-perception enhanced video grounding framework that integrates density-aware position encoding with boundary perception, to address these limitations and bridge the temporal discrepancy between video and language modalities. We propose a suite of boundary-aware tasks that explicitly model event durations, locations, and transitions, enabling large language models to better understand temporal structure within videos. In addition, we develop a novel density-aware temporal encoding mechanism that dynamically adapts position representations to varying temporal information density, enhancing the model’s ability to localize events precisely across diverse video content. Extensive experiments across ActivityNet, Charades, and DiDeMo datasets demonstrate the effectiveness of our approach, yielding consistent performance improvements and achieving up to 11.2% relative gain in R@0.3. These results validate the importance of integrating density-aware modeling and boundary perception to advance fine-grained video grounding capabilities in large language models.","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"15220-15229"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Beyond Static Prompts: Dynamic Token Fusion for Temporal-Align Visual--Language Tracking 超越静态提示：时间对齐视觉语言跟踪的动态令牌融合

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-06-05 DOI: 10.1109/TCSVT.2026.3700716

Tianpeng Liu;Xinrong Hu;Jing Li;Lefei Zhang

{"title":"Beyond Static Prompts: Dynamic Token Fusion for Temporal-Align Visual--Language Tracking","authors":"Tianpeng Liu;Xinrong Hu;Jing Li;Lefei Zhang","doi":"10.1109/TCSVT.2026.3700716","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3700716","url":null,"abstract":"Visual-language (VL) tracking leverages natural language descriptions to enhance visual object tracking. However, a critical yet overlooked issue is the inherent temporal heterogeneity between static language descriptions and dynamic visual sequences, which limits the efficacy of cross-modal fusion. To bridge this gap, we propose a novel Temporal-Align Visual-Language Tracker (TAVLT). Unlike prior works that simply concatenate multimodal tokens, TAVLT processes template, search, and language features separately to explicitly model their interrelations. Our framework introduces two core components: 1) a Temporal Semantic Enrichment Module (TSEM) that constructs a Spatio-Temporal Semantic Affinity Matrix to dynamically recalibrate language token weights, ensuring temporal alignment with the visual sequence; and 2) a lightweight Cross-Modal Feature Fusion Module (CMFFM) that leverages the affinity matrices for efficient feature integration. Furthermore, we introduce a Consistency Learning Balance (CLB) strategy to mitigate performance disparities across different perceptual constancy tasks (e.g., shape vs. color). Extensive experiments on LaSOT, LaSOT-ext, TNL2K, and OTB99-Lang demonstrate that TAVLT achieves state-of-the-art performance while maintaining high inference efficiency (49 FPS). Our approach effectively addresses the temporal misalignment in VL tracking, setting a new standard for robust and efficient cross-modal learning.","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"16010-16024"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SWFNet: A Spiking-Wavelet Fusion Network for Frame-Level Quality Enhancement of VVC-Compressed 360° Video SWFNet：一种用于vvc压缩360°视频帧级质量增强的峰值-小波融合网络

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-07-06 DOI: 10.1109/TCSVT.2026.3710288

Ziyi Cao;Haibing Yin;Hongkui Wang;Tiansong Li;Xiaofeng Huang;Jiyong Zhang

{"title":"SWFNet: A Spiking-Wavelet Fusion Network for Frame-Level Quality Enhancement of VVC-Compressed 360° Video","authors":"Ziyi Cao;Haibing Yin;Hongkui Wang;Tiansong Li;Xiaofeng Huang;Jiyong Zhang","doi":"10.1109/TCSVT.2026.3710288","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3710288","url":null,"abstract":"Aggressive compression in the Versatile Video Coding standard significantly degrades 360-degree video frame quality and induces severe artifacts in the Equirectangular Projection (ERP) format. Existing methods struggle to balance geometric correction and detail restoration under strict computational constraints. To bridge this gap, we propose the Spiking Wavelet Fusion Network (SWFNet). To the best of our knowledge, SWFNet is the first hybrid Spiking-Artificial Neural Network (SNN-ANN) architecture introduced for panoramic video quality enhancement. Guided by the Magnocellular and Parvocellular (M-P) dual-stream theory, SWFNet explicitly decouples restoration into coupled global and local processing streams. Specifically, the global pathway adopts a U-shaped spiking architecture where the encoder utilizes Transformer-SNN (TransSNN) blocks to extract global structural priors, while the decoder incorporates Spiking Channel Attention (SCAtten) to actively suppress background noise. Beyond reducing computations, the event-driven spiking pathway provides a sparse global representation that adaptively emphasizes salient structural responses and reduces redundant activations in over-sampled ERP regions. In parallel, the local pathway utilizes the Residual Wavelet Fusion Block (RWFB) to resolve high-frequency spatial details, adaptively compensating for quantization loss across multiple scales. The proposed SWFNet achieves state-of-the-art restoration performance with 1.48 million parameters, 10.3 GFLOPs, an estimated energy consumption of 44.8 mJ, and a peak memory footprint of 185.2 MB, offering a favorable fidelity-efficiency trade-off for immersive high-definition media. The source code is available at <uri>https://github.com/647-bei/SWFNet</uri>","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"15291-15304"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Continual Semantic Segmentation With Tiny Memory 小内存连续语义分割

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-06-24 DOI: 10.1109/TCSVT.2026.3706775

Qingsen Yan;Weiyu Zhou;Shengqiang Liu;Duwei Dai;Peng Wu;Yanning Zhang

{"title":"Continual Semantic Segmentation With Tiny Memory","authors":"Qingsen Yan;Weiyu Zhou;Shengqiang Liu;Duwei Dai;Peng Wu;Yanning Zhang","doi":"10.1109/TCSVT.2026.3706775","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3706775","url":null,"abstract":"Deep neural networks suffer from catastrophic forgetting when sequentially training on image semantic segmentation tasks. Storing historical images and utilizing them to train the model alongside data of new tasks can alleviate catastrophic forgetting but result in a large memory cost and an increase in training time, which limits practical applications. In this paper, we propose a continual semantic segmentation framework with tiny memory to address the catastrophic forgetting of continual semantic segmentation. To reduce memory utilization, we store small patches of specific semantic regions instead of storing entire images. This strategy eliminates the large amount of image backgrounds, allowing for the storage of a larger number of trimmed samples. Furthermore, we introduce a diffusion-based module to generate augmented images with various backgrounds to enhance the diversity of the trimmed sample images. Equipped with our dynamic similarity loss, our method achieves favourable performance on two widely used benchmarks, Pascal-VOC 2012 and ADE 20K, compared to several state-of-the-art methods while significantly reducing storage space usage.","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"15888-15899"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Domain-Invariant Representation Learning for Generalizable Deepfake Speech Detection 泛化深度假语音检测的域不变表示学习

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-07-07 DOI: 10.1109/TCSVT.2026.3710772

Senhao Zhang;Guopu Zhu;Xiwen Fu;Wei Jiang;Tao Xiang;Qiong Li;Ligang Wu

{"title":"Domain-Invariant Representation Learning for Generalizable Deepfake Speech Detection","authors":"Senhao Zhang;Guopu Zhu;Xiwen Fu;Wei Jiang;Tao Xiang;Qiong Li;Ligang Wu","doi":"10.1109/TCSVT.2026.3710772","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3710772","url":null,"abstract":"Recent advances in generative AI have significantly improved synthetic speech quality in text-to-speech and voice conversion tasks. This progress has made synthetic speech increasingly indistinguishable from human speech, posing substantial challenges for deepfake speech detection. Current state-of-the-art deepfake speech detection methods leverage pre-trained self-supervised learning (SSL) models and achieve strong performance on in-domain datasets. However, these methods still suffer from limited generalization capabilities when facing unseen and cross-domain attacks. To address this, we propose Collaborative Multi-view Spoofing Detection (CMSD) framework that effectively combines complementary spectral and waveform representations within SSL models, together with a unified cross-domain evaluation protocol for assessing generalization. Our framework incorporates two key components: <bold>Hierarchical <bold>Layer <bold>Aggregation (HLA) module and <bold>Collaborative <bold>Progressive <bold>Multi-view <bold>Fusion (CPMF) module. Specifically, the HLA module aggregates outputs from multiple hidden layers of the SSL model to construct comprehensive representations with multi-level feature information, while the CPMF module employs a two-stage progressive fusion strategy to integrate spectral and waveform features via bidirectional Mamba architecture, thereby enhancing the learning of robust multi-view representations for spoofing detection. Experiments demonstrate that the proposed method achieves state-of-the-art EER on ASVspoof 2021 LA, while also exhibiting superior cross-domain generalization across diverse unseen domains. The code is publicly available at <uri>https://github.com/zhangsenhao112-lang/Domain-Invariant-Deepfake-Speech-Detection</uri>","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"15789-15803"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Embodied Image Quality Assessment for Robotic Intelligence 机器人智能的嵌入图像质量评估

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-06-18 DOI: 10.1109/TCSVT.2026.3705308

Jianbo Zhang;Chunyi Li;Jie Hao;Jun Jia;Huiyu Duan;Guoquan Zheng;Liang Yuan;Guangtao Zhai

{"title":"Embodied Image Quality Assessment for Robotic Intelligence","authors":"Jianbo Zhang;Chunyi Li;Jie Hao;Jun Jia;Huiyu Duan;Guoquan Zheng;Liang Yuan;Guangtao Zhai","doi":"10.1109/TCSVT.2026.3705308","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3705308","url":null,"abstract":"Image Quality Assessment (IQA) of User-Generated Content (UGC) is a critical technique for human Quality of Experience (QoE). However, does the the image quality of Robot-Generated Content (RGC) demonstrate traits consistent with the Moravec paradox, potentially conflicting with human perceptual norms? Human subjective scoring is more based on the attractiveness of the image. Embodied agent are required to interact and perceive in the environment, and finally perform specific tasks. Visual images as inputs directly influence downstream tasks. In this paper, we explore the perception mechanism of embodied robots for image quality. We propose the first Embodied Preference Database (EPD), which contains 12,500 distorted image annotations. We establish assessment metrics based on the downstream tasks of robot. In addition, there is a gap between UGC and RGC. To address this, we propose a novel Multi-scale Attention Embodied Image Quality Assessment called MA-EIQA. For the proposed EPD dataset, this is the first no-reference IQA model designed for embodied robot. Finally, the performance of mainstream IQA algorithms on EPD dataset is verified. The experiments demonstrate that quality assessment of embodied images is different from that of humans. We sincerely hope that the EPD can contribute to the development of embodied AI by focusing on image quality assessment. The benchmark is available at <uri>https://github.com/Jianbo-maker/EPD_benchmark</uri>","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"15396-15408"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0