Ji Gan
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
Ji Gan has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Xinbo Gao
Xidian University, Xi'an, China
13 shared publications - Jiaxu Leng
Chongqing University of Posts and Telecommunications
11 shared publications Weiqiang Wang
5 shared publications- Feng Gao
School of Computer Science and Technology, Chongqing University of Posts and Telecommunications (CQUPT), Chongqing, China
4 shared publications Ke Lu
3 shared publications- Weiqiang Wang
University of the Chinese Academy of Sciences
3 shared publications
Latest Publications
- 18 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13  (11) , 24990-25003
Transformer-Based 3-D Hand Pose Estimation via Bidirectional Multiscale Fusion and Learnable Anchor Guidance
Accurate 3-D hand pose estimation faces inherent challenges, including self-occlusions, joint similarities, and high degrees of freedom. Although most existing CNN-based or Transformer-based methods leverage global contexts, they often fail to capture fine-grained local details and robustly handle occluded joints. To address these limitations, we propose a novel Transformer framework for depth-based 3-D hand pose estimation, which incorporates two key designs: the bidirectional multiscale fusion (BMF) and learnable anchor guidance (LAG). First, we propose BMF that sequentially propagates features from different encoder levels in both top-down and bottom-up directions, followed by a final aggregation of all scale features. Such an intricate feature interaction eventually enables effective joint modeling of fine-grained local details (e.g., fingertip positions) and high-level semantic context information (e.g., palm orientation). Second, we introduce the learnable anchor query as prior guidance to dynamically guide the decoder to localize ambiguous joints better. The learnable anchors are derived from joint-specific attention maps under 3-D ground-truth supervision and then are concatenated with static grid anchors to form hybrid anchors, which effectively enable more precise 3-D hand pose estimation, especially for occlusions. To further demonstrate the practicality of our framework for IoT-oriented deployment, we conduct edge-device experiments to validate its deployment feasibility. Experiments on benchmark datasets (including NYU, ICVL, MSRA, and DexYCB) demonstrate the superiority of our method over previous state-of-the-art approaches.
- 18 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13  (11) , 24990-25003
Transformer-Based 3-D Hand Pose Estimation via Bidirectional Multiscale Fusion and Learnable Anchor Guidance
Accurate 3-D hand pose estimation faces inherent challenges, including self-occlusions, joint similarities, and high degrees of freedom. Although most existing CNN-based or Transformer-based methods leverage global contexts, they often fail to capture fine-grained local details and robustly handle occluded joints. To address these limitations, we propose a novel Transformer framework for depth-based 3-D hand pose estimation, which incorporates two key designs: the bidirectional multiscale fusion (BMF) and learnable anchor guidance (LAG). First, we propose BMF that sequentially propagates features from different encoder levels in both top-down and bottom-up directions, followed by a final aggregation of all scale features. Such an intricate feature interaction eventually enables effective joint modeling of fine-grained local details (e.g., fingertip positions) and high-level semantic context information (e.g., palm orientation). Second, we introduce the learnable anchor query as prior guidance to dynamically guide the decoder to localize ambiguous joints better. The learnable anchors are derived from joint-specific attention maps under 3-D ground-truth supervision and then are concatenated with static grid anchors to form hybrid anchors, which effectively enable more precise 3-D hand pose estimation, especially for occlusions. To further demonstrate the practicality of our framework for IoT-oriented deployment, we conduct edge-device experiments to validate its deployment feasibility. Experiments on benchmark datasets (including NYU, ICVL, MSRA, and DexYCB) demonstrate the superiority of our method over previous state-of-the-art approaches.
- 6 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28  (15209210) , 3147-3159
Transferring and Refining Visual-Semantic Priors via Graph-Enhanced CLIP for 3D Hand Pose Estimation
3D hand pose estimation is crucial for many human-computer interaction applications. However, existing deep neural networks (DNNs) for 3D hand pose estimation suffer from poor generalizability due to data scarcity and a lack of domain-specific knowledge. In contrast, humans remain far better than DNNs at learning; Humans require fewer samples for learning new concepts under the guidance of their prior knowledge. Inspired by this, we propose a graph-enhanced CLIP to deliver visual-semantic priors to DNNs, and provide refined domain-specific knowledge for better 3D hand pose estimation. Specifically, we first introduce a pre-trained CLIP to guide the hand estimation model in learning the semantic-aware visual features, and text-free contrastive learning is proposed to effectively transfer high-level visual-semantic priors from the pre-trained large multimodal models. Notably, our strategy is data-agnostic and avoids designing hand-crafted text prompts for various visual inputs. Second, we introduce novel graph Transformers to refine the domain-specific knowledge by fully exploiting the local adjacent relations of hand joints and capturing the global structure representations of hand poses. The introduced graph Transformers are supposed to further refine the generalized CLIP feature for the downstream task (i.e., hand pose estimation) with better performance. Experiments show that our proposed graph-enhanced CLIP achieves state-of-the-art performances on benchmark datasets, demonstrating its effectiveness for 3D hand pose estimation. The source code is available at https://github.com/TLiu2832/TRVSP-GE-CLIP.
- 6 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28  (15209210) , 3147-3159
Transferring and Refining Visual-Semantic Priors via Graph-Enhanced CLIP for 3D Hand Pose Estimation
3D hand pose estimation is crucial for many human-computer interaction applications. However, existing deep neural networks (DNNs) for 3D hand pose estimation suffer from poor generalizability due to data scarcity and a lack of domain-specific knowledge. In contrast, humans remain far better than DNNs at learning; Humans require fewer samples for learning new concepts under the guidance of their prior knowledge. Inspired by this, we propose a graph-enhanced CLIP to deliver visual-semantic priors to DNNs, and provide refined domain-specific knowledge for better 3D hand pose estimation. Specifically, we first introduce a pre-trained CLIP to guide the hand estimation model in learning the semantic-aware visual features, and text-free contrastive learning is proposed to effectively transfer high-level visual-semantic priors from the pre-trained large multimodal models. Notably, our strategy is data-agnostic and avoids designing hand-crafted text prompts for various visual inputs. Second, we introduce novel graph Transformers to refine the domain-specific knowledge by fully exploiting the local adjacent relations of hand joints and capturing the global structure representations of hand poses. The introduced graph Transformers are supposed to further refine the generalized CLIP feature for the downstream task (i.e., hand pose estimation) with better performance. Experiments show that our proposed graph-enhanced CLIP achieves state-of-the-art performances on benchmark datasets, demonstrating its effectiveness for 3D hand pose estimation. The source code is available at https://github.com/TLiu2832/TRVSP-GE-CLIP.
- 1 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34  (10577149) , 6432-6445
Dual-Space Normalizing Flow for Unsupervised Video Anomaly Detection
Conventional reconstruction-based video anomaly detection (VAD) methods implicitly model normality in latent spaces, which is limited by the generalization ability of latent features. Normalizing Flow (NF)-based methods have been introduced to address this issue, as they explicitly model the distribution of input data and achieve significant performance in VAD. However, existing NF-based methods are confined to Euclidean space, limiting their ability to model action hierarchies. While effective at capturing local joint dynamics and short-term temporal variations, they fail to encode kinematic dependencies and long-term pose evolution, ultimately struggling to discern ambiguous anomalies that deviate minimally from normal motion. In contrast, hyperbolic representation learning, with its ability to model hierarchical and complex relationships among actions, offers a promising solution to enhance the discriminative power between similar skeletal actions. Motivated by this, we propose a novel Dual-Space Normalizing Flow (DSNF) method. Specifically, we design a Dual-Space Parallel Graph Convolutional Network (DSPGCN) that synergistically integrates the strengths of both Euclidean and hyperbolic geometries to simultaneously capture local detail features of poses and intrinsic hierarchical relationships of actions. To enhance the model’s focus on discriminative features, we design an Adaptive Weighted Approximation Mass (AWAM) loss that dynamically adjusts weights to impose stronger constraints on regions with low discriminability in the dual space, encouraging the model to focus more on key discriminative features in hyperbolic space that reflect complex relationships between actions. Extensive experiments on public datasets demonstrate the effectiveness and robustness of our method in various VAD scenarios.
- 1 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34  (10577149) , 6432-6445
Dual-Space Normalizing Flow for Unsupervised Video Anomaly Detection
Conventional reconstruction-based video anomaly detection (VAD) methods implicitly model normality in latent spaces, which is limited by the generalization ability of latent features. Normalizing Flow (NF)-based methods have been introduced to address this issue, as they explicitly model the distribution of input data and achieve significant performance in VAD. However, existing NF-based methods are confined to Euclidean space, limiting their ability to model action hierarchies. While effective at capturing local joint dynamics and short-term temporal variations, they fail to encode kinematic dependencies and long-term pose evolution, ultimately struggling to discern ambiguous anomalies that deviate minimally from normal motion. In contrast, hyperbolic representation learning, with its ability to model hierarchical and complex relationships among actions, offers a promising solution to enhance the discriminative power between similar skeletal actions. Motivated by this, we propose a novel Dual-Space Normalizing Flow (DSNF) method. Specifically, we design a Dual-Space Parallel Graph Convolutional Network (DSPGCN) that synergistically integrates the strengths of both Euclidean and hyperbolic geometries to simultaneously capture local detail features of poses and intrinsic hierarchical relationships of actions. To enhance the model’s focus on discriminative features, we design an Adaptive Weighted Approximation Mass (AWAM) loss that dynamically adjusts weights to impose stronger constraints on regions with low discriminability in the dual space, encouraging the model to focus more on key discriminative features in hyperbolic space that reflect complex relationships between actions. Extensive experiments on public datasets demonstrate the effectiveness and robustness of our method in various VAD scenarios.
- 13 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (1) , 861-873
HandJoKe: Joint-Guided Keypoint Denoising Transformer for Depth-Based 3D Hand Pose Estimation
Existing depth-based 3D hand pose estimation methods typically estimate hand joints from either 2D depth images or 3D point clouds, whereas the approaches that fuse multimodal data remain underexplored. Furthermore, previous methods often struggle to learn geometric-facilitated features and precise joint correlations, especially for occluded hands, due to the lack of explicit prior guidance and insufficient cross-dimensional interaction. By taking advantage of multi-modal fusion, cross-dimensional interaction, and prior guidance, we propose a novel joint-guided keypoint denoising Transformer (named HandJoKe) to achieve more precise hand pose estimation, which can iteratively estimate hand poses based on keypoint features from both 2D depth images and 3D point clouds under explicit joint guidance within only several denoising steps. Rather than directly applying existing multi-modal fusion to perform redundant interactions among many background pixels and irrelevant points, HandJoKe focuses on modeling correlations and capturing dependencies among local informative hand regions (i.e., keypoints), thus attaining higher learning capability with lower computation redundancy. Moreover, a novel joint-guided denoising estimation strategy is introduced to adequately fuse cross-modal keypoint features under explicit joint guidance, achieving geometric-facilitated cross-modal keypoint interaction in both 2D and 3D spaces. The effectiveness of joint guidance can be further strengthened through iterative denoising, since it can subsequently update cross-modal keypoint features based on previous denoised hand poses and thus can help better locate confused joints, especially for occluded hands. Extensive experiments show that HandJoKe has achieved state-of-the-art performance on four public challenging benchmarks, including single-hand datasets NYU and ICVL, and hand-object datasets DexYCB and HO3D.
- 13 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (1) , 861-873
HandJoKe: Joint-Guided Keypoint Denoising Transformer for Depth-Based 3D Hand Pose Estimation
Existing depth-based 3D hand pose estimation methods typically estimate hand joints from either 2D depth images or 3D point clouds, whereas the approaches that fuse multimodal data remain underexplored. Furthermore, previous methods often struggle to learn geometric-facilitated features and precise joint correlations, especially for occluded hands, due to the lack of explicit prior guidance and insufficient cross-dimensional interaction. By taking advantage of multi-modal fusion, cross-dimensional interaction, and prior guidance, we propose a novel joint-guided keypoint denoising Transformer (named HandJoKe) to achieve more precise hand pose estimation, which can iteratively estimate hand poses based on keypoint features from both 2D depth images and 3D point clouds under explicit joint guidance within only several denoising steps. Rather than directly applying existing multi-modal fusion to perform redundant interactions among many background pixels and irrelevant points, HandJoKe focuses on modeling correlations and capturing dependencies among local informative hand regions (i.e., keypoints), thus attaining higher learning capability with lower computation redundancy. Moreover, a novel joint-guided denoising estimation strategy is introduced to adequately fuse cross-modal keypoint features under explicit joint guidance, achieving geometric-facilitated cross-modal keypoint interaction in both 2D and 3D spaces. The effectiveness of joint guidance can be further strengthened through iterative denoising, since it can subsequently update cross-modal keypoint features based on previous denoised hand poses and thus can help better locate confused joints, especially for occluded hands. Extensive experiments show that HandJoKe has achieved state-of-the-art performance on four public challenging benchmarks, including single-hand datasets NYU and ICVL, and hand-object datasets DexYCB and HO3D.
- 17 July 2025
- Published by Springer Nature
- p. 452-463
Attention-Modulated Transformer for In-Air Handwriting Recognition
- 17 July 2025
- Published by Springer Nature
- p. 452-463
Attention-Modulated Transformer for In-Air Handwriting Recognition
- 16 May 2025
- Published by Elsevier in Neural Networks
- Vol. 189, 107570
GCapNet-FSD: A heterogeneous Graph Capsule Network for Few-Shot object Detection
- 16 May 2025
- Published by Elsevier in Neural Networks
- Vol. 189, 107570
GCapNet-FSD: A heterogeneous Graph Capsule Network for Few-Shot object Detection
- 27 January 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133  (6) , 3667-3688
Dual-Space Video Person Re-identification
- 27 January 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133  (6) , 3667-3688
Dual-Space Video Person Re-identification
- 25 November 2024
- Published by Elsevier in Neural Networks
- Vol. 182, 106911
RC-DETR: Improving DETRs in crowded pedestrian detection via rank-based contrastive learning
- 25 November 2024
- Published by Elsevier in Neural Networks
- Vol. 182, 106911
RC-DETR: Improving DETRs in crowded pedestrian detection via rank-based contrastive learning
- 9 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36  (7) , 13080-13093
Difficulty-Guided Variant Degradation Learning for Blind Image Super-Resolution
Recent blind super-resolution (BSR) methods are explored to handle unknown degradations and achieve impressive performance. However, the prevailing assumption in most BSR methods is the spatial invariance of degradation kernels across the entire image, which leads to significant performance declines when faced with spatially variant degradations caused by object motion or defocusing. Additionally, these methods do not account for the human visual system’s tendency to focus differently on areas of varying perceptual difficulty, as they uniformly process each pixel during reconstruction. To cope with these issues, we propose a difficulty-guided variant degradation learning network for BSR, named difficulty-guided degradation learning (DDL)-BSR, which explores the relationship between reconstruction difficulty and degradation estimation. Accordingly, the proposed DDL-BSR consists of three customized networks: reconstruction difficulty prediction (RDP), space-variant degradation estimation (SDE), and degradation and difficulty-informed reconstruction (DDR). Specifically, RDP learns the reconstruction difficulty with the proposed reconstruction-distance supervision. Then, SDE is designed to estimate space-variant degradation kernels according to the difficulty map. Finally, both degradation kernels and reconstruction difficulty are fed into DDR, which takes into account such two prior knowledge information to guide super-resolution (SR). Experimental analysis on various synthetic datasets demonstrates that DDL-BSR invariably surpasses state-of-the-art (SOTA) methods, producing SR images with enhanced realism and texture quality. Code is available at https://github.com/JiaWang0704/DDL-BSR.
- 9 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36  (7) , 13080-13093
Difficulty-Guided Variant Degradation Learning for Blind Image Super-Resolution
Recent blind super-resolution (BSR) methods are explored to handle unknown degradations and achieve impressive performance. However, the prevailing assumption in most BSR methods is the spatial invariance of degradation kernels across the entire image, which leads to significant performance declines when faced with spatially variant degradations caused by object motion or defocusing. Additionally, these methods do not account for the human visual system’s tendency to focus differently on areas of varying perceptual difficulty, as they uniformly process each pixel during reconstruction. To cope with these issues, we propose a difficulty-guided variant degradation learning network for BSR, named difficulty-guided degradation learning (DDL)-BSR, which explores the relationship between reconstruction difficulty and degradation estimation. Accordingly, the proposed DDL-BSR consists of three customized networks: reconstruction difficulty prediction (RDP), space-variant degradation estimation (SDE), and degradation and difficulty-informed reconstruction (DDR). Specifically, RDP learns the reconstruction difficulty with the proposed reconstruction-distance supervision. Then, SDE is designed to estimate space-variant degradation kernels according to the difficulty map. Finally, both degradation kernels and reconstruction difficulty are fed into DDR, which takes into account such two prior knowledge information to guide super-resolution (SR). Experimental analysis on various synthetic datasets demonstrates that DDL-BSR invariably surpasses state-of-the-art (SOTA) methods, producing SR images with enhanced realism and texture quality. Code is available at https://github.com/JiaWang0704/DDL-BSR.
- Open Access
- 25 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 56  (12) , 1-36
Recent Advances for Aerial Object Detection: A Survey
Aerial object detection, as object detection in aerial images captured from an overhead perspective, has been widely applied in urban management, industrial inspection, and other aspects. However, the performance of existing aerial object detection algorithms is hindered by variations in object scales and orientations attributed to the aerial perspective. This survey presents a comprehensive review of recent advances in aerial object detection. We start with some basic concepts of aerial object detection and then summarize the five imbalance problems of aerial object detection, including scale imbalance, spatial imbalance, objective imbalance, semantic imbalance, and class imbalance. Moreover, we classify and analyze relevant methods and especially introduce the applications of aerial object detection in practical scenarios. Finally, the performance evaluation is presented on two popular aerial object detection datasets VisDrone-DET and DOTA, and we discuss several future directions that could facilitate the development of aerial object detection.
- 25 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 56  (12) , 1-36
Open AccessRecent Advances for Aerial Object Detection: A Survey
Aerial object detection, as object detection in aerial images captured from an overhead perspective, has been widely applied in urban management, industrial inspection, and other aspects. However, the performance of existing aerial object detection algorithms is hindered by variations in object scales and orientations attributed to the aerial perspective. This survey presents a comprehensive review of recent advances in aerial object detection. We start with some basic concepts of aerial object detection and then summarize the five imbalance problems of aerial object detection, including scale imbalance, spatial imbalance, objective imbalance, semantic imbalance, and class imbalance. Moreover, we classify and analyze relevant methods and especially introduce the applications of aerial object detection in practical scenarios. Finally, the performance evaluation is presented on two popular aerial object detection datasets VisDrone-DET and DOTA, and we discuss several future directions that could facilitate the development of aerial object detection.