Jufeng Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jufeng Yang has a total of 229 co-authors. Here are the top co-authors by number of shared publications:
- Jie Liang
OPPO Research Institute, Shenzhen, China
8 shared publications - Sicheng Zhao
Tsinghua University, Beijing, China
8 shared publications - Eunil Park
Department of Applied Artificial Intelligence, Sungkyunkwan University, Seoul, Republic of Korea and Jaume I University, Castellon, Spain
7 shared publications - Ming-Ming Cheng
Nankai University, China
7 shared publications - Paul L. Rosin
Cardiff University, Cardiff, United Kingdom
7 shared publications - Shihao Zhou
VCIP & TMCC & DISSec College of Computer Science Nankai University
7 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2525-2536
SAVER: Selective and Adaptive Multi-View Routing for Visual Emotion Reasoning in Vision-Language Models
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2525-2536
Open AccessSAVER: Selective and Adaptive Multi-View Routing for Visual Emotion Reasoning in Vision-Language Models
- 25 September 2026
- Published by Springer Nature
- p. 381-398
Finding Highlight Images In Your Albums: From Benchmark to Agentic MLLMs
- 25 September 2026
- Published by Springer Nature
- p. 381-398
Finding Highlight Images In Your Albums: From Benchmark to Agentic MLLMs
- 16 September 2026
- Published by Springer Nature
- p. 414-432
ExpoMotion: A Large-Scale Benchmark and A Householder Projection Network for Multi-Exposure Fusion
- 16 September 2026
- Published by Springer Nature
- p. 414-432
ExpoMotion: A Large-Scale Benchmark and A Householder Projection Network for Multi-Exposure Fusion
- 15 September 2026
- Published by Springer Nature
- p. 631-650
There and Back Again: A Flexible-Frame Transformer for Multi-exposure Fusion
- 15 September 2026
- Published by Springer Nature
- p. 631-650
There and Back Again: A Flexible-Frame Transformer for Multi-exposure Fusion
- 10 September 2026
- Published by Springer Nature
- p. 111-129
Pixel Ignores, Superpixel Sees: Adverse Weather Image Restoration via Semantic-Center SSM
- 10 September 2026
- Published by Springer Nature
- p. 111-129
Pixel Ignores, Superpixel Sees: Adverse Weather Image Restoration via Semantic-Center SSM
- Open Access
- 11 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (14) , 1-37
Deep Learning in Concealed Dense Prediction
Deep learning is developing rapidly and handling common computer vision tasks well. It is time to pay attention to more complex vision tasks, as model size, knowledge, and reasoning capabilities continue to improve. In this article, we introduce and review a family of complex tasks, termed Concealed Dense Prediction (CDP), which has great value in agriculture, industry, etc. CDP’s intrinsic trait is that the targets are concealed in their surroundings, thus fully perceiving them requires fine-grained representations, prior knowledge, auxiliary reasoning, etc. The contributions of this review are three-fold: (i) We introduce the scope, characteristics, and challenges specific to CDP tasks and emphasize their essential differences from generic vision tasks. (ii) We develop a taxonomy based on concealment counteracting to summarize deep learning efforts in CDP through experiments on three tasks. We compare 25 state-of-the-art methods across 12 widely used concealed datasets. (iii) We discuss the potential applications of CDP in the large model era and summarize 6 potential research directions. We offer perspectives for the future development of CDP by constructing a large-scale multimodal instruction fine-tuning dataset, CvpINST , and a concealed visual perception agent, CvpAgent . Our traceable resource links are https://github.com/PanchengZhao/Concealed-Dense-Prediction .
- 11 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (14) , 1-37
Open AccessDeep Learning in Concealed Dense Prediction
Deep learning is developing rapidly and handling common computer vision tasks well. It is time to pay attention to more complex vision tasks, as model size, knowledge, and reasoning capabilities continue to improve. In this article, we introduce and review a family of complex tasks, termed Concealed Dense Prediction (CDP), which has great value in agriculture, industry, etc. CDP’s intrinsic trait is that the targets are concealed in their surroundings, thus fully perceiving them requires fine-grained representations, prior knowledge, auxiliary reasoning, etc. The contributions of this review are three-fold: (i) We introduce the scope, characteristics, and challenges specific to CDP tasks and emphasize their essential differences from generic vision tasks. (ii) We develop a taxonomy based on concealment counteracting to summarize deep learning efforts in CDP through experiments on three tasks. We compare 25 state-of-the-art methods across 12 widely used concealed datasets. (iii) We discuss the potential applications of CDP in the large model era and summarize 6 potential research directions. We offer perspectives for the future development of CDP by constructing a large-scale multimodal instruction fine-tuning dataset, CvpINST , and a concealed visual perception agent, CvpAgent . Our traceable resource links are https://github.com/PanchengZhao/Concealed-Dense-Prediction .
- 27 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 4744-4758
Rethinking the Importance of High-Frequency Components in Transformers for Image Restoration
Transformer-based approaches have achieved superior performance in image restoration, since they can model long-term dependencies well. However, the limitation in capturing local information restricts their capacity to remove degradations. While existing approaches attempt to mitigate this issue by incorporating convolutional operations, the core component in Transformer, i.e., self-attention, which serves as a low-pass filter, could unintentionally dilute or even eliminate the acquired local patterns. In this paper, we propose HIT, a simple yet effective High-frequency Injected Transformer for image restoration. Specifically, we design a window-wise injection module (WIM), which incorporates abundant high-frequency details into the feature map, to provide reliable references for restoring high-quality images. We also develop a bidirectional interaction module (BIM) to aggregate features at different scales using a mutually reinforced paradigm, resulting in spatially and contextually improved representations. In addition, we introduce a spatial enhancement unit (SEU) to preserve essential spatial relationships that may be lost due to the computations carried out across channel dimensions in the BIM. Extensive experiments on 6 tasks (real noise, rain streak, blur, flare, underwater conditions, and low-light conditions) demonstrate that HIT with linear computational complexity performs favorably against the state-of-the-art methods. The code will be available upon acceptance.
- 27 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 4744-4758
Rethinking the Importance of High-Frequency Components in Transformers for Image Restoration
Transformer-based approaches have achieved superior performance in image restoration, since they can model long-term dependencies well. However, the limitation in capturing local information restricts their capacity to remove degradations. While existing approaches attempt to mitigate this issue by incorporating convolutional operations, the core component in Transformer, i.e., self-attention, which serves as a low-pass filter, could unintentionally dilute or even eliminate the acquired local patterns. In this paper, we propose HIT, a simple yet effective High-frequency Injected Transformer for image restoration. Specifically, we design a window-wise injection module (WIM), which incorporates abundant high-frequency details into the feature map, to provide reliable references for restoring high-quality images. We also develop a bidirectional interaction module (BIM) to aggregate features at different scales using a mutually reinforced paradigm, resulting in spatially and contextually improved representations. In addition, we introduce a spatial enhancement unit (SEU) to preserve essential spatial relationships that may be lost due to the computations carried out across channel dimensions in the BIM. Extensive experiments on 6 tasks (real noise, rain streak, blur, flare, underwater conditions, and low-light conditions) demonstrate that HIT with linear computational complexity performs favorably against the state-of-the-art methods. The code will be available upon acceptance.
- 13 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (6) , 7062-7069
PHMRNet: Persistent Homology Based Mamba–RWKV Network for LiDAR Place Recognition
LiDAR-based place recognition (LPR) is a key component of visual localization and autonomous driving. Although LiDAR data are usually preprocessed by motion undistortion, which can greatly reduce scene distortion caused by sensor motion, 3-dimensional (3D) point clouds in complex scenes still show inherent unstructured sparsity. Projecting 3D point clouds into 2D range view (RV) images can provide structured feature representations that are more suitable for neural networks and deep learning methods. However, this strategy has two main limitations: 1) the important geometric details are removed by the projection, impairing the effective extraction and representation of scene features. 2) unpredictable occlusions and viewpoint changes alter the observed scene structure and often lead to incorrect place matches. To address these limitations, we propose a LPR network that combines topological information extracted by persistent homology (PH) with RV features to compensate for missing structural information and produce more stable descriptors. Specifically, PH-stable features are added as a topology-aware sampling channel for the RV feature to integrate more stable and discriminative robust geometric cues. Next, we introduce a spatiotemporal fusion module that links topological and RV features across consecutive frames, thereby improving spatiotemporal consistency of the representation and thus reducing the impact of occlusions and rotations. Compared with OverlapMamba, PHMRNet can better handle spatial, temporal, and geometric features, improving the robustness of the descriptor. Experiments on public datasets show that PHMRNet outperforms existing methods in terms of accuracy and robustness under the same driving conditions and LiDAR scanning rate.
- 13 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (6) , 7062-7069
PHMRNet: Persistent Homology Based Mamba–RWKV Network for LiDAR Place Recognition
LiDAR-based place recognition (LPR) is a key component of visual localization and autonomous driving. Although LiDAR data are usually preprocessed by motion undistortion, which can greatly reduce scene distortion caused by sensor motion, 3-dimensional (3D) point clouds in complex scenes still show inherent unstructured sparsity. Projecting 3D point clouds into 2D range view (RV) images can provide structured feature representations that are more suitable for neural networks and deep learning methods. However, this strategy has two main limitations: 1) the important geometric details are removed by the projection, impairing the effective extraction and representation of scene features. 2) unpredictable occlusions and viewpoint changes alter the observed scene structure and often lead to incorrect place matches. To address these limitations, we propose a LPR network that combines topological information extracted by persistent homology (PH) with RV features to compensate for missing structural information and produce more stable descriptors. Specifically, PH-stable features are added as a topology-aware sampling channel for the RV feature to integrate more stable and discriminative robust geometric cues. Next, we introduce a spatiotemporal fusion module that links topological and RV features across consecutive frames, thereby improving spatiotemporal consistency of the representation and thus reducing the impact of occlusions and rotations. Compared with OverlapMamba, PHMRNet can better handle spatial, temporal, and geometric features, improving the robustness of the descriptor. Experiments on public datasets show that PHMRNet outperforms existing methods in terms of accuracy and robustness under the same driving conditions and LiDAR scanning rate.
- Open Access
- 23 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1234-1236
Revealing Deception through Cognitive Load: A Multimodal Audio-Visual Approach
- 23 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1234-1236
Open AccessRevealing Deception through Cognitive Load: A Multimodal Audio-Visual Approach
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 10942-10957
Second-Order Visual Attention Prediction in Multiagent Videos via Emotion-Aware Belief Inference
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 10942-10957
Second-Order Visual Attention Prediction in Multiagent Videos via Emotion-Aware Belief Inference