Yufei Gao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yufei Gao has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Jinjia Zhou
Hosei University
4 shared publications - Keren He
Graduate School of Science and Engineering, Hosei University, Tokyo 184-8584, Japan
3 shared publications - Haixin Wang
Graduate School of Science and Engineering, Hosei University, Tokyo 184-8584, Japan
1 shared publication Keren He
Hosei University
1 shared publication- Kun Xiang
Graduate School of Science and Engineering, Hosei University, Tokyo 184-8584, Japan
1 shared publication - Qi Wang
Hosei University
1 shared publication
Latest Publications
- Open Access
- 21 August 2026
- Published by MDPI AG in Information
- Vol. 17 (8) , 808
ChoreDiffusion: Beat-Aware Diffusion for Music-to-Dance Generation
Music-to-dance generation requires precisely aligning movement dynamics with musical rhythm, yet existing methods rely on shallow conditioning or auxiliary beat-alignment objectives that fail to establish stable beat–motion correspondences. We present ChoreDiffusion, a diffusion-based framework that integrates explicit beat guidance directly into the denoising process. Central to our approach is a beat-enhanced cross-modal attention mechanism that injects beat-salience cues at every refinement step, promoting fine-grained synchronization beyond the reach of conventional conditioning pipelines. To support multiple dance styles within a unified model, we incorporate lightweight low-rank adaptation (LoRA) modules that encode style-specific motion signatures with only a small set of additional parameters per style, and a three-stage progressive curriculum stabilizes the joint learning of rhythmic alignment and stylistic expressivity. Experiments on two public multi-style dance benchmarks (AIST++ and FineDance) show that ChoreDiffusion achieves the lowest FID values among the compared generation methods on both benchmarks, while maintaining competitive rhythm alignment and multi-style controllability. These results indicate that embedding beat-aware guidance during generation, rather than applying it afterwards, is an effective route toward human-like musicality in music-driven choreography.
- 21 August 2026
- Published by MDPI AG in Information
- Vol. 17 (8) , 808
Open AccessChoreDiffusion: Beat-Aware Diffusion for Music-to-Dance Generation
Music-to-dance generation requires precisely aligning movement dynamics with musical rhythm, yet existing methods rely on shallow conditioning or auxiliary beat-alignment objectives that fail to establish stable beat–motion correspondences. We present ChoreDiffusion, a diffusion-based framework that integrates explicit beat guidance directly into the denoising process. Central to our approach is a beat-enhanced cross-modal attention mechanism that injects beat-salience cues at every refinement step, promoting fine-grained synchronization beyond the reach of conventional conditioning pipelines. To support multiple dance styles within a unified model, we incorporate lightweight low-rank adaptation (LoRA) modules that encode style-specific motion signatures with only a small set of additional parameters per style, and a three-stage progressive curriculum stabilizes the joint learning of rhythmic alignment and stylistic expressivity. Experiments on two public multi-style dance benchmarks (AIST++ and FineDance) show that ChoreDiffusion achieves the lowest FID values among the compared generation methods on both benchmarks, while maintaining competitive rhythm alignment and multi-style controllability. These results indicate that embedding beat-aware guidance during generation, rather than applying it afterwards, is an effective route toward human-like musicality in music-driven choreography.
- Open Access
A Multi-Module Fusion Framework for Restoring Human and Machine Vision Quality in Compressed Video
With the increasing demand for video processing in both human perception and machine vision applications, enhancing heavily compressed video has become a critical problem in practical multimedia systems. In many real-world scenarios, video data acquired by image sensors are often compressed for efficient transmission and storage, which introduces compression artifacts and degrades both visual quality and downstream task performance. This issue is especially significant in sensor-based systems such as surveillance cameras and mobile imaging devices. To address these challenges, we propose a novel joint human–machine video enhancement framework for compressed video enhancement that jointly targets human perceptual quality and machine vision performance. The framework integrates four complementary components: a Spatio-Temporal Fusion Module that leverages inter-frame correlations, a High-Frequency Semantic Fusion module for recovering structurally important details relevant to machine tasks, a Texture-Guided Model that enhances low-level visual features, and a Refined Attention Residual Quality Enhancement Module that adaptively emphasizes salient regions. By progressively combining these modules, the framework effectively restores compressed content while preserving task-relevant semantics. The experimental results demonstrate that our method consistently outperforms existing approaches, achieving higher PSNR and SSIM as well as improved object detection and video object segmentation performance. These results highlight the framework’s practical applicability for compressed video enhancement in sensor-based systems, including intelligent surveillance and autonomous imaging platforms.
Open AccessA Multi-Module Fusion Framework for Restoring Human and Machine Vision Quality in Compressed Video
With the increasing demand for video processing in both human perception and machine vision applications, enhancing heavily compressed video has become a critical problem in practical multimedia systems. In many real-world scenarios, video data acquired by image sensors are often compressed for efficient transmission and storage, which introduces compression artifacts and degrades both visual quality and downstream task performance. This issue is especially significant in sensor-based systems such as surveillance cameras and mobile imaging devices. To address these challenges, we propose a novel joint human–machine video enhancement framework for compressed video enhancement that jointly targets human perceptual quality and machine vision performance. The framework integrates four complementary components: a Spatio-Temporal Fusion Module that leverages inter-frame correlations, a High-Frequency Semantic Fusion module for recovering structurally important details relevant to machine tasks, a Texture-Guided Model that enhances low-level visual features, and a Refined Attention Residual Quality Enhancement Module that adaptively emphasizes salient regions. By progressively combining these modules, the framework effectively restores compressed content while preserving task-relevant semantics. The experimental results demonstrate that our method consistently outperforms existing approaches, achieving higher PSNR and SSIM as well as improved object detection and video object segmentation performance. These results highlight the framework’s practical applicability for compressed video enhancement in sensor-based systems, including intelligent surveillance and autonomous imaging platforms.
- Open Access
Leveraging Temporal Down-Sampling Structure and Spatio-Temporal Fusion for Efficient Video Coding
Down-sampling-based video compression frameworks have shown great potential in improving compression efficiency in modern sensing and imaging systems. However, existing methods ignore critical spatial and temporal redundancy, and treat all frames uniformly during down-sampling. This leads to the loss of important information and impacts compression efficiency. To address these limitations, this paper proposes a temporal down-sampling system, in which only intermediate frames are down-sampled while preserving key frames with high quality for reference. On the decoding side, we employ a frame-recurrent enhancement mechanism to maximize the use of temporal redundancy information. In the fusion of enhancement stage, we design a Multi-scale Temporal-Spatial Attention (MTSA) module. MTSA consists of two components: Multi-Temporal Attention (MTA) and Pyramid Spatial Attention (PSA). MTA performs multi-scale temporal correlation modeling, expanding the receptive field and providing stable cues in compressed regions. PSA integrates local spatial saliency and contextual structure in a progressive and multi-stage manner. Extensive experiments show that our approach achieves consistent BD-rate reductions. Under All-Intra, Low-Delay-P, and Random Access configurations, we observe BD-rate reductions of I, P, and B frames ranging from 14% to 39% compared to VVC, and outperform prior approaches anchored by the standard HEVC.
Open AccessLeveraging Temporal Down-Sampling Structure and Spatio-Temporal Fusion for Efficient Video Coding
Down-sampling-based video compression frameworks have shown great potential in improving compression efficiency in modern sensing and imaging systems. However, existing methods ignore critical spatial and temporal redundancy, and treat all frames uniformly during down-sampling. This leads to the loss of important information and impacts compression efficiency. To address these limitations, this paper proposes a temporal down-sampling system, in which only intermediate frames are down-sampled while preserving key frames with high quality for reference. On the decoding side, we employ a frame-recurrent enhancement mechanism to maximize the use of temporal redundancy information. In the fusion of enhancement stage, we design a Multi-scale Temporal-Spatial Attention (MTSA) module. MTSA consists of two components: Multi-Temporal Attention (MTA) and Pyramid Spatial Attention (PSA). MTA performs multi-scale temporal correlation modeling, expanding the receptive field and providing stable cues in compressed regions. PSA integrates local spatial saliency and contextual structure in a progressive and multi-stage manner. Extensive experiments show that our approach achieves consistent BD-rate reductions. Under All-Intra, Low-Delay-P, and Random Access configurations, we observe BD-rate reductions of I, P, and B frames ranging from 14% to 39% compared to VVC, and outperform prior approaches anchored by the standard HEVC.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 122419-122432
PoseCodec: Specialized Human Action Compression via Pose Guidance and Adaptive Learning
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 122419-122432
Open AccessPoseCodec: Specialized Human Action Compression via Pose Guidance and Adaptive Learning