Lv Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Lv Tang has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Xinfeng Zhang
University of the Chinese Academy of Sciences, Beijing, China
8 shared publications - Bo Li
Vivo Mobile Communication Co., Ltd
5 shared publications - Gai Zhang
School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China
5 shared publications - Li Zhang
ByteDance Inc., Beijing, China
5 shared publications - Senyun Kuang
School of Information Science and Technology, Southwest Jiaotong University, Chengdu, China
4 shared publications Jun Zhu
University of Chinese Academy of Sciences
3 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (11) , 17670-17683
RNeRV: Recurrent Neural Representation for Video Compression
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (11) , 17670-17683
RNeRV: Recurrent Neural Representation for Video Compression
- 3 August 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 333
ReVerSeg: Training-free reason-and-verify video segmentation for traffic scenes
- 3 August 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 333
ReVerSeg: Training-free reason-and-verify video segmentation for traffic scenes
- 29 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 5773-5788
HANeRV: Hierarchically Adaptive Neural Representation for Video Compression
Recent advances in video compression introduce implicit neural representation (INR) based methods, which effectively capture global dependencies and characteristics of entire video sequences. Unlike traditional and deep learning based approaches, INR-based methods optimize network parameters from a global perspective, resulting in superior compression potential. However, most current INR methods utilize a fixed and uniform network architecture across all frames, limiting their adaptability to dynamic variations within and between video sequences. This often leads to suboptimal compression outcomes as these methods struggle to capture the distinct nuances and transitions in video content. To overcome these challenges, we propose Hierarchically Adaptive Neural Representation for Video Compression (HANeRV), an innovative INR-based video compression network that adaptively conducts structure optimisation based on the specific content of each video sequence. To better capture dynamic information across video sequences, we propose a dynamic architecture-level adjustment (DAA). Furthermore, to enhance the capture of dynamics between frames within a sequence, we implement a dynamic frame-level adjustment (DFA). Finally, to effectively capture spatial structural information within video frames, thereby enhancing the detail restoration capabilities of HANeRV, we devise a structure level hierarchical structural adaptation (HSA). Experimental results show that HANeRV achieves state-of-the-art performance among INR-based video compression methods and surpasses the H.266/VVC (x266, medium preset) anchor on diverse datasets.
- 29 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 5773-5788
HANeRV: Hierarchically Adaptive Neural Representation for Video Compression
Recent advances in video compression introduce implicit neural representation (INR) based methods, which effectively capture global dependencies and characteristics of entire video sequences. Unlike traditional and deep learning based approaches, INR-based methods optimize network parameters from a global perspective, resulting in superior compression potential. However, most current INR methods utilize a fixed and uniform network architecture across all frames, limiting their adaptability to dynamic variations within and between video sequences. This often leads to suboptimal compression outcomes as these methods struggle to capture the distinct nuances and transitions in video content. To overcome these challenges, we propose Hierarchically Adaptive Neural Representation for Video Compression (HANeRV), an innovative INR-based video compression network that adaptively conducts structure optimisation based on the specific content of each video sequence. To better capture dynamic information across video sequences, we propose a dynamic architecture-level adjustment (DAA). Furthermore, to enhance the capture of dynamics between frames within a sequence, we implement a dynamic frame-level adjustment (DFA). Finally, to effectively capture spatial structural information within video frames, thereby enhancing the detail restoration capabilities of HANeRV, we devise a structure level hierarchical structural adaptation (HSA). Experimental results show that HANeRV achieves state-of-the-art performance among INR-based video compression methods and surpasses the H.266/VVC (x266, medium preset) anchor on diverse datasets.
- Open Access
- 5 May 2026
- Published by Elsevier in SSRN Electronic Journal
ReVerSeg: Training-Free Reason-and-Verify Video Segmentation for Traffic Scenes
Language-driven video segmentation enables flexible target perception beyond fixed category sets, but existing methods often rely on supervised training and remain fragile in real-world traffic videos where dense instances, occlusions, and visual degradation can trigger error propagation and identity drift. We study a training-free setting for short-clip traffic video segmentation and propose ReVerSeg, an inference framework that decomposes the task into target localization and video segmentation with explicit verification. We observe that failures in this setting are frequently caused by unstable initialization when the anchor frame is not semantically reliable, as well as semantic mistakes from large multimodal models under ambiguity and degraded visual evidence. To improve reliability without additional training, ReVerSeg performs semantic-aware keyframe selection for robust initialization and applies a two-stage verification procedure that checks both box-level localization and pixel-level masks during inference, allowing incorrect results to be rejected or refined before they propagate across frames. We further construct the Ref-Perceive benchmark with 2,000 short traffic video clips (10,000 frames), each paired with a compositional referring instruction and frame-wise pixel annotations across multiple cities and weather conditions. Experiments show that ReVerSeg consistently improves robustness and cross-frame identity consistency over naive training-free baselines and existing language-driven video segmentation methods, while preserving zero-shot capability. The project homepage and code repository are available at \url{https://github.com/Concernin9/ReVerSeg-RefPerceive}.
- 5 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessReVerSeg: Training-Free Reason-and-Verify Video Segmentation for Traffic Scenes
Language-driven video segmentation enables flexible target perception beyond fixed category sets, but existing methods often rely on supervised training and remain fragile in real-world traffic videos where dense instances, occlusions, and visual degradation can trigger error propagation and identity drift. We study a training-free setting for short-clip traffic video segmentation and propose ReVerSeg, an inference framework that decomposes the task into target localization and video segmentation with explicit verification. We observe that failures in this setting are frequently caused by unstable initialization when the anchor frame is not semantically reliable, as well as semantic mistakes from large multimodal models under ambiguity and degraded visual evidence. To improve reliability without additional training, ReVerSeg performs semantic-aware keyframe selection for robust initialization and applies a two-stage verification procedure that checks both box-level localization and pixel-level masks during inference, allowing incorrect results to be rejected or refined before they propagate across frames. We further construct the Ref-Perceive benchmark with 2,000 short traffic video clips (10,000 frames), each paired with a compositional referring instruction and frame-wise pixel annotations across multiple cities and weather conditions. Experiments show that ReVerSeg consistently improves robustness and cross-frame identity consistency over naive training-free baselines and existing language-driven video segmentation methods, while preserving zero-shot capability. The project homepage and code repository are available at \url{https://github.com/Concernin9/ReVerSeg-RefPerceive}.
- 22 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-12
SANR: Scene-Aware Neural Representation for Light Field Image Compression with Rate-Distortion Optimization
Light field images capture multi-view scene information and play a crucial role in 3D scene reconstruction. However, their high-dimensional nature results in enormous data volumes, posing a significant challenge for efficient compression in practical storage and transmission scenarios. Although neural representation-based methods have shown promise in light field image compression, most approaches rely on direct coordinate-to-pixel mapping through implicit neural representation (INR), often neglecting the explicit modeling of scene structure. Moreover, they typically lack end-to-end rate-distortion optimization, limiting their compression efficiency. To address these limitations, we propose SANR, a Scene-Aware Neural Representation framework for light field image compression with end-to-end rate-distortion optimization. For scene awareness, SANR introduces a hierarchical scene modeling block that leverages multi-scale latent codes to capture intrinsic scene structures, thereby reducing the information gap between INR input coordinates and the target light field image. From a compression perspective, SANR is the first to incorporate entropy-constrained quantization-aware training (QAT) into neural representation-based light field image compression, enabling end-to-end rate-distortion optimization. Extensive experiment results demonstrate that SANR significantly outperforms state-of-the-art techniques regarding rate-distortion performance with a 65.62% BD-rate saving against HEVC.
- 22 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-12
SANR: Scene-Aware Neural Representation for Light Field Image Compression with Rate-Distortion Optimization
Light field images capture multi-view scene information and play a crucial role in 3D scene reconstruction. However, their high-dimensional nature results in enormous data volumes, posing a significant challenge for efficient compression in practical storage and transmission scenarios. Although neural representation-based methods have shown promise in light field image compression, most approaches rely on direct coordinate-to-pixel mapping through implicit neural representation (INR), often neglecting the explicit modeling of scene structure. Moreover, they typically lack end-to-end rate-distortion optimization, limiting their compression efficiency. To address these limitations, we propose SANR, a Scene-Aware Neural Representation framework for light field image compression with end-to-end rate-distortion optimization. For scene awareness, SANR introduces a hierarchical scene modeling block that leverages multi-scale latent codes to capture intrinsic scene structures, thereby reducing the information gap between INR input coordinates and the target light field image. From a compression perspective, SANR is the first to incorporate entropy-constrained quantization-aware training (QAT) into neural representation-based light field image compression, enabling end-to-end rate-distortion optimization. Extensive experiment results demonstrate that SANR significantly outperforms state-of-the-art techniques regarding rate-distortion performance with a 65.62% BD-rate saving against HEVC.
- 27 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (2) , 1681-1695
UAR-NVC: A Unified Autoregressive Framework for Memory-Efficient Neural Video Compression
Implicit Neural Representations (INRs) have demonstrated significant potential in video compression by representing videos as neural networks. However, as the number of frames increases, the memory consumption for training and inference increases substantially, posing challenges in resource-constrained scenarios. Inspired by the success of traditional video compression frameworks, which process video frame by frame and can efficiently compress long videos, we adopt this modeling strategy for INRs to decrease memory consumption, while aiming to unify the frameworks from the perspective of timeline-based autoregressive modeling. In this work, we present a novel understanding of INR models from an autoregressive (AR) perspective and introduce a Unified AutoRegressive Framework for memory-efficient Neural Video Compression (UAR-NVC). UAR-NVC integrates timeline-based and INR-based neural video compression under a unified autoregressive paradigm. It partitions videos into several clips and processes each clip using a different INR model instance, leveraging the advantages of both compression frameworks while allowing seamless adaptation to either in form. To further reduce temporal redundancy between clips, we treat the corresponding model parameters as proxies for these clips, and design two modules to optimize the initialization, training, and compression of these model parameters. In special, the Residual Quantization and Entropy Constraint (RQEC) module dynamically balances the reconstruction quality of the current clip and the newly introduced bitrate cost using the previously optimized parameters as conditioning. In addition, the Interpolation-based Initialization (II) module flexibly adjusts the degree of reference used during the initialization of neighboring video clips, based on their correlation. UAR-NVC supports adjustable latencies by varying the clip length. Extensive experimental results demonstrate that UAR-NVC, with its flexible video clip setting, can adapt to resource-constrained environments and significantly improve performance compared to different baseline models. The project page: https://wj-inf.github.io/UAR-NVC-page/.
- 27 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (2) , 1681-1695
UAR-NVC: A Unified Autoregressive Framework for Memory-Efficient Neural Video Compression
Implicit Neural Representations (INRs) have demonstrated significant potential in video compression by representing videos as neural networks. However, as the number of frames increases, the memory consumption for training and inference increases substantially, posing challenges in resource-constrained scenarios. Inspired by the success of traditional video compression frameworks, which process video frame by frame and can efficiently compress long videos, we adopt this modeling strategy for INRs to decrease memory consumption, while aiming to unify the frameworks from the perspective of timeline-based autoregressive modeling. In this work, we present a novel understanding of INR models from an autoregressive (AR) perspective and introduce a Unified AutoRegressive Framework for memory-efficient Neural Video Compression (UAR-NVC). UAR-NVC integrates timeline-based and INR-based neural video compression under a unified autoregressive paradigm. It partitions videos into several clips and processes each clip using a different INR model instance, leveraging the advantages of both compression frameworks while allowing seamless adaptation to either in form. To further reduce temporal redundancy between clips, we treat the corresponding model parameters as proxies for these clips, and design two modules to optimize the initialization, training, and compression of these model parameters. In special, the Residual Quantization and Entropy Constraint (RQEC) module dynamically balances the reconstruction quality of the current clip and the newly introduced bitrate cost using the previously optimized parameters as conditioning. In addition, the Interpolation-based Initialization (II) module flexibly adjusts the degree of reference used during the initialization of neighboring video clips, based on their correlation. UAR-NVC supports adjustable latencies by varying the clip length. Extensive experimental results demonstrate that UAR-NVC, with its flexible video clip setting, can adapt to resource-constrained environments and significantly improve performance compared to different baseline models. The project page: https://wj-inf.github.io/UAR-NVC-page/.
- Open Access
- 10 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (3) , 1-23
UVC: A Unified Deep Video Compression Framework
Recently, many works have applied deep learning techniques to video compression tasks, achieving promising results and advancing the field of Deep Learning-Based Video Compression (DLVC). However, the architecture design of the existing DLVC is rigid and limited in terms of flexibility. Specifically, different networks must be designed for different scenarios, such as delay-constrained scenario or non-delay-constrained scenario. Frequent switching between networks would reduce the speed of modern deep learning platforms and increase the maintenance costs. To address this problem, we propose a Unified Video Compression (UVC) framework that can be freely switched to different application scenarios without changing the network architecture. Our proposed UVC framework is based on the explicit-compression and implicit-generation perspective, which contains two sub-networks—the Explicit Reference Frame Compression Network (ERFCN) and the Implicit Reference Frame Generation Network (IRFGN). The aim of ERFCN is to compress the current frame with the help of the reference frame. To improve the performance of ERFCN, we first introduce the Transformer in this network, which can fully remove the spatial redundancy of the input image and is beneficial for the following inter-prediction process. We also develop a novel long-range motion estimation module for inter-prediction to generate motion vectors based on global motion information between two frames, which can handle long-range complex motion relations. The aim of IRFGN is to capture the temporal relationship between forward and backward reconstructed frames and synthesize a high-quality implicit reference frame for the current frame. To achieve this, we design the split spatial-temporal attention and multi-scale prediction module. We conduct extensive experiments on three widely used video compression databases (HEVC, UVG, and MCL-JVC), and the results demonstrate the superiority of our approach over other related DLVC methods.
- 10 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (3) , 1-23
Open AccessUVC: A Unified Deep Video Compression Framework
Recently, many works have applied deep learning techniques to video compression tasks, achieving promising results and advancing the field of Deep Learning-Based Video Compression (DLVC). However, the architecture design of the existing DLVC is rigid and limited in terms of flexibility. Specifically, different networks must be designed for different scenarios, such as delay-constrained scenario or non-delay-constrained scenario. Frequent switching between networks would reduce the speed of modern deep learning platforms and increase the maintenance costs. To address this problem, we propose a Unified Video Compression (UVC) framework that can be freely switched to different application scenarios without changing the network architecture. Our proposed UVC framework is based on the explicit-compression and implicit-generation perspective, which contains two sub-networks—the Explicit Reference Frame Compression Network (ERFCN) and the Implicit Reference Frame Generation Network (IRFGN). The aim of ERFCN is to compress the current frame with the help of the reference frame. To improve the performance of ERFCN, we first introduce the Transformer in this network, which can fully remove the spatial redundancy of the input image and is beneficial for the following inter-prediction process. We also develop a novel long-range motion estimation module for inter-prediction to generate motion vectors based on global motion information between two frames, which can handle long-range complex motion relations. The aim of IRFGN is to capture the temporal relationship between forward and backward reconstructed frames and synthesize a high-quality implicit reference frame for the current frame. To achieve this, we design the split spatial-temporal attention and multi-scale prediction module. We conduct extensive experiments on three widely used video compression databases (HEVC, UVG, and MCL-JVC), and the results demonstrate the superiority of our approach over other related DLVC methods.
- Open Access
- 30 October 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (10) , 1-22
Unified and Scalable Deep Image Compression Framework for Human and Machine
Image compression aims to minimize the amount of data in image representation while maintaining a certain visual quality for humans, which is an essential technique for storage and transmission. Recently, along with the development of computer vision, machines have become another primary receiver for images and require compressed images at a certain quality level, which may be different from that of human vision. In many scenarios, compressed images should serve both human and machine vision tasks, but few compression methods are designed for both goals simultaneously. In this article, we propose a unified and scalable deep image compression (USDIC) framework that jointly optimizes the image quality according to human and machine vision in an end-to-end style. For the encoder, we propose an information splitting mechanism (ISM) to separate images into semantic and visual features, which mainly aims at machine analysis and human viewing tasks. For the decoder, we design a scalable decoding architecture. The encoded semantic feature is first decoded for machine analysis tasks, and the image is decoded and reconstructed further by leveraging the decoded semantic features. Herein, to further remove the redundancy between the semantic and visual features of images, we propose a scalable entropy model (SEM) with a joint optimization strategy to reconstruct the image using the two kinds of decoded features. Extensive experimental results show that the proposed USDIC achieves much better performance on the image analysis task while maintaining competitive performance on the traditional image reconstruction task compared with popular image compression methods.
- 30 October 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (10) , 1-22
Open AccessUnified and Scalable Deep Image Compression Framework for Human and Machine
Image compression aims to minimize the amount of data in image representation while maintaining a certain visual quality for humans, which is an essential technique for storage and transmission. Recently, along with the development of computer vision, machines have become another primary receiver for images and require compressed images at a certain quality level, which may be different from that of human vision. In many scenarios, compressed images should serve both human and machine vision tasks, but few compression methods are designed for both goals simultaneously. In this article, we propose a unified and scalable deep image compression (USDIC) framework that jointly optimizes the image quality according to human and machine vision in an end-to-end style. For the encoder, we propose an information splitting mechanism (ISM) to separate images into semantic and visual features, which mainly aims at machine analysis and human viewing tasks. For the decoder, we design a scalable decoding architecture. The encoded semantic feature is first decoded for machine analysis tasks, and the image is decoded and reconstructed further by leveraging the decoded semantic features. Herein, to further remove the redundancy between the semantic and visual features of images, we propose a scalable entropy model (SEM) with a joint optimization strategy to reconstruct the image using the two kinds of decoded features. Extensive experimental results show that the proposed USDIC achieves much better performance on the image analysis task while maintaining competitive performance on the traditional image reconstruction task compared with popular image compression methods.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 8805-8814
Chain of Visual Perception: Harnessing Multimodal Large Language Models for Zero-shot Camouflaged Object Detection
In this paper, we introduce a novel multimodal camo-perceptive framework (MMCPF) aimed at handling zero-shot Camouflaged Object Detection (COD) by leveraging the powerful capabilities of Multimodal Large Language Models (MLLMs). Recognizing the inherent limitations of current COD methodologies, which predominantly rely on supervised learning models demanding extensive and accurately annotated datasets, resulting in weak generalization, our research proposes a zero-shot MMCPF that circumvents these challenges. Although MLLMs hold significant potential for broad applications, their effectiveness in COD is hindered and they would make misinterpretations of camouflaged objects. To address this challenge, we further propose a strategic enhancement called the Chain of Visual Perception (CoVP), which significantly improves the perceptual capabilities of MLLMs in camouflaged scenes by leveraging both linguistic and visual cues more effectively. We validate the effectiveness of MMCPF on five widely used COD datasets, containing CAMO, COD10K, NC4K, MoCA-Mask and OVCamo. Experiments show that MMCPF can outperform all existing state-of-the-art zero-shot COD methods, and achieve competitive performance compared to weakly-supervised and fully-supervised methods, which demonstrates the potential of MMCPF. The Github link of this paper is https://github.com/luckybird1994/MMCPF.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 8805-8814
Open AccessChain of Visual Perception: Harnessing Multimodal Large Language Models for Zero-shot Camouflaged Object Detection
In this paper, we introduce a novel multimodal camo-perceptive framework (MMCPF) aimed at handling zero-shot Camouflaged Object Detection (COD) by leveraging the powerful capabilities of Multimodal Large Language Models (MLLMs). Recognizing the inherent limitations of current COD methodologies, which predominantly rely on supervised learning models demanding extensive and accurately annotated datasets, resulting in weak generalization, our research proposes a zero-shot MMCPF that circumvents these challenges. Although MLLMs hold significant potential for broad applications, their effectiveness in COD is hindered and they would make misinterpretations of camouflaged objects. To address this challenge, we further propose a strategic enhancement called the Chain of Visual Perception (CoVP), which significantly improves the perceptual capabilities of MLLMs in camouflaged scenes by leveraging both linguistic and visual cues more effectively. We validate the effectiveness of MMCPF on five widely used COD datasets, containing CAMO, COD10K, NC4K, MoCA-Mask and OVCamo. Experiments show that MMCPF can outperform all existing state-of-the-art zero-shot COD methods, and achieve competitive performance compared to weakly-supervised and fully-supervised methods, which demonstrates the potential of MMCPF. The Github link of this paper is https://github.com/luckybird1994/MMCPF.
- Open Access
- 12 June 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (8) , 1-23
High Efficiency Deep-learning Based Video Compression
Although deep learning technique has achieved significant improvement on image compression, but its advantages are not fully explored in video compression, which leads to the performance of deep-learning-based video compression (DLVC) is obviously inferior to that of hybrid video coding framework. In this article, we proposed a novel network to improve the performance of DLVC from its most important modules, including Motion Process (MP), Residual Compression (RC), and Frame Reconstruction (FR). In MP, we design a split second-order attention and multi-scale feature extraction module to fully remove the warping artifacts from multi-scale feature space and pixel space, which can help reduce the distortion in the following process. In RC, we propose a channel selection mechanism to gradually drop redundant information while preserving informative channels for a better rate-distortion performance. Finally, in FR, we introduce a residual multi-scale recurrent network to improve the quality of the current reconstructed frame by progressively exploiting temporal context information between it and its several previous reconstructed frames. Extensive experiments are conducted on the three widely used video compression datasets (HEVC, UVG, and MCL-JVC), and the performance demonstrates the superiority of our proposed approach over the state-of-the-art methods.
- 12 June 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (8) , 1-23
Open AccessHigh Efficiency Deep-learning Based Video Compression
Although deep learning technique has achieved significant improvement on image compression, but its advantages are not fully explored in video compression, which leads to the performance of deep-learning-based video compression (DLVC) is obviously inferior to that of hybrid video coding framework. In this article, we proposed a novel network to improve the performance of DLVC from its most important modules, including Motion Process (MP), Residual Compression (RC), and Frame Reconstruction (FR). In MP, we design a split second-order attention and multi-scale feature extraction module to fully remove the warping artifacts from multi-scale feature space and pixel space, which can help reduce the distortion in the following process. In RC, we propose a channel selection mechanism to gradually drop redundant information while preserving informative channels for a better rate-distortion performance. Finally, in FR, we introduce a residual multi-scale recurrent network to improve the quality of the current reconstructed frame by progressively exploiting temporal context information between it and its several previous reconstructed frames. Extensive experiments are conducted on the three widely used video compression datasets (HEVC, UVG, and MCL-JVC), and the performance demonstrates the superiority of our proposed approach over the state-of-the-art methods.