Shangdong Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shangdong Zhu has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Yunzhou Zhang
College of Information Science and Engineering, Northeastern University, Shenyang, China
8 shared publications - Yixiu Liu
Hangzhou Dianzi University
3 shared publications - Chenggang Yan
Hangzhou Dianzi University, Hangzhou, China
2 shared publications - Fawei Ge
College of Mechanical and Electronic Engineering, Dalian Minzu University, Dalian, China
2 shared publications - He Cao
Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China
2 shared publications - Lei Wang
Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China
2 shared publications
Latest Publications
- 9 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 8875-8887
TrackletGait: A Robust Framework for Gait Recognition in the Wild
Gait recognition aims to identify individuals based on their body shape and walking patterns. Though much progress has been achieved driven by deep learning, gait recognition in real-world surveillance scenarios remains quite challenging to current methods. Conventional approaches, which rely on periodic gait cycles and controlled environments, struggle with the non-periodic and occluded silhouette sequences encountered in the wild. In this paper, we propose a novel framework, TrackletGait, designed to address these challenges in the wild. We propose Random Tracklet Sampling, a generalization of existing sampling methods, which strikes a balance between robustness and representation in capturing diverse walking patterns. Next, we introduce Haar Wavelet-based Downsampling to preserve information during spatial downsampling. Finally, we present a Hardness Exclusion Triplet Loss, designed to exclude low-quality silhouettes by discarding hard triplet samples. TrackletGait achieves state-of-the-art results, with 77.8% and 80.4% rank-1 accuracy on the Gait3D and GREW datasets, respectively, while using only 10.3M backbone parameters. Extensive experiments are also conducted to further investigate the factors affecting gait recognition in the wild.
- 9 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 8875-8887
TrackletGait: A Robust Framework for Gait Recognition in the Wild
Gait recognition aims to identify individuals based on their body shape and walking patterns. Though much progress has been achieved driven by deep learning, gait recognition in real-world surveillance scenarios remains quite challenging to current methods. Conventional approaches, which rely on periodic gait cycles and controlled environments, struggle with the non-periodic and occluded silhouette sequences encountered in the wild. In this paper, we propose a novel framework, TrackletGait, designed to address these challenges in the wild. We propose Random Tracklet Sampling, a generalization of existing sampling methods, which strikes a balance between robustness and representation in capturing diverse walking patterns. Next, we introduce Haar Wavelet-based Downsampling to preserve information during spatial downsampling. Finally, we present a Hardness Exclusion Triplet Loss, designed to exclude low-quality silhouettes by discarding hard triplet samples. TrackletGait achieves state-of-the-art results, with 77.8% and 80.4% rank-1 accuracy on the Gait3D and GREW datasets, respectively, while using only 10.3M backbone parameters. Extensive experiments are also conducted to further investigate the factors affecting gait recognition in the wild.
- Open Access
- 12 August 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (16) , 2580
Improving Person Re-Identification via Feature Erasing-Driven Data Augmentation
Person re-identification (Re-ID) has attracted considerable attention in the field of computer vision, primarily due to its critical role in video surveillance and public security applications. However, most existing Re-ID approaches rely on image-level erasing techniques, which may inadvertently remove fine-grained visual cues that are essential for accurate identification. To mitigate this limitation, we propose an effective feature erasing-based data augmentation framework that aims to explore discriminative information within individual samples and improve overall recognition performance. Specifically, we first introduce a diagonal swapping augmentation strategy to increase the diversity of the training samples. Secondly, we design a feature erasing-driven method applied to the extracted pedestrian feature to capture identity-relevant information at the feature level. Finally, extensive experiments demonstrate that our method achieves competitive performance compared to many representative approaches.
- 12 August 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (16) , 2580
Open AccessImproving Person Re-Identification via Feature Erasing-Driven Data Augmentation
Person re-identification (Re-ID) has attracted considerable attention in the field of computer vision, primarily due to its critical role in video surveillance and public security applications. However, most existing Re-ID approaches rely on image-level erasing techniques, which may inadvertently remove fine-grained visual cues that are essential for accurate identification. To mitigate this limitation, we propose an effective feature erasing-based data augmentation framework that aims to explore discriminative information within individual samples and improve overall recognition performance. Specifically, we first introduce a diagonal swapping augmentation strategy to increase the diversity of the training samples. Secondly, we design a feature erasing-driven method applied to the extracted pedestrian feature to capture identity-relevant information at the feature level. Finally, extensive experiments demonstrate that our method achieves competitive performance compared to many representative approaches.
- 13 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
Improving Grasp Pose Detection by Implicitly Utilizing Geometric Information and Spatial Relations of Objects in Clutter
6-DoF grasp pose detection in clutter is an essential but challenging task in the vision measurement. However, most current detection methods often fail to consider the geometric information and partial occlusions of objects in clutter, resulting in inaccurate robotic grasping and potential collisions. In this work, we propose an end-to-end grasping system to directly generate 6-DoF grasp poses from point clouds in clutter. Our system first selects the most feasible positions as the grasp centers, and then determines their grasp parameters, such as approaching vectors and in-plane rotations. Specifically, we design an optimality criterion based on the geometric information of objects to extract rich object features from the scene and identify high-graspablity areas. To alleviate the collision problem caused by occlusions, we focus on the spatial relations among objects and explicitly train a collision predictor to directly select collision-free points as grasp centers from high-graspablity areas. Based on these grasp centers, our model can easily generate diverse sets of collision- free and robust grasp poses for successful grasping. To efficiently determine grasp parameters, we exploit neighbor search to capture the local context around each grasp center and then implicitly learn relations among objects using the self-attention mechanism. Compared with previous methods, our grasping system improves performance by a large margin (>10%), and achieves state-of-the-art results on GraspNet-1Billion, a largescale dataset. Besides, our method has a high success rate for grasping in simulation and real-world experiments, verifying the validity in clutter.
- 13 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
Improving Grasp Pose Detection by Implicitly Utilizing Geometric Information and Spatial Relations of Objects in Clutter
6-DoF grasp pose detection in clutter is an essential but challenging task in the vision measurement. However, most current detection methods often fail to consider the geometric information and partial occlusions of objects in clutter, resulting in inaccurate robotic grasping and potential collisions. In this work, we propose an end-to-end grasping system to directly generate 6-DoF grasp poses from point clouds in clutter. Our system first selects the most feasible positions as the grasp centers, and then determines their grasp parameters, such as approaching vectors and in-plane rotations. Specifically, we design an optimality criterion based on the geometric information of objects to extract rich object features from the scene and identify high-graspablity areas. To alleviate the collision problem caused by occlusions, we focus on the spatial relations among objects and explicitly train a collision predictor to directly select collision-free points as grasp centers from high-graspablity areas. Based on these grasp centers, our model can easily generate diverse sets of collision- free and robust grasp poses for successful grasping. To efficiently determine grasp parameters, we exploit neighbor search to capture the local context around each grasp center and then implicitly learn relations among objects using the self-attention mechanism. Compared with previous methods, our grasping system improves performance by a large margin (>10%), and achieves state-of-the-art results on GraspNet-1Billion, a largescale dataset. Besides, our method has a high success rate for grasping in simulation and real-world experiments, verifying the validity in clutter.
- 10 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 9 (5) , 3518-3532
AE-Net: Appearance-Enriched Neural Network With Foreground Enhancement for Person Re-Identification
Person re-identification (Re-ID) in environments subject to intensive appearance and background variations due to seasons, weather conditions, illumination and human factors is a challenging task. A wide variety of existing algorithms address this problem either for appearance changes or background clutter, but neglect to explore a powerful framework to consider solving both cases simultaneously. To overcome this limitation, this research introduces an effective appearance-enriched neural network (AE-Net) with foreground enhancement based on generative adversarial nets (GANs) and an attention mechanism to enrich the appearance of person images while suppressing the influence of the background. Specifically, a channel-grouped convolution and squeeze weighted (CGCSW) module is first proposed to extract the powerful feature representation of individuals. Secondly, a foreground-enhanced and background-suppressed (FEBS) module is proposed to enhance the foreground of individual samples while weakening the impact of the background. Thirdly, A stage-wise consistency loss is presented to enable our model maintain consistent foreground-enhanced and background-suppressed stages. Finally, this study evaluates the proposed method and compares it with state-of-the-art approaches on three public datasets. The experimental results demonstrate the effectiveness and improvements achieved by using the presented architecture.
- 10 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 9 (5) , 3518-3532
AE-Net: Appearance-Enriched Neural Network With Foreground Enhancement for Person Re-Identification
Person re-identification (Re-ID) in environments subject to intensive appearance and background variations due to seasons, weather conditions, illumination and human factors is a challenging task. A wide variety of existing algorithms address this problem either for appearance changes or background clutter, but neglect to explore a powerful framework to consider solving both cases simultaneously. To overcome this limitation, this research introduces an effective appearance-enriched neural network (AE-Net) with foreground enhancement based on generative adversarial nets (GANs) and an attention mechanism to enrich the appearance of person images while suppressing the influence of the background. Specifically, a channel-grouped convolution and squeeze weighted (CGCSW) module is first proposed to extract the powerful feature representation of individuals. Secondly, a foreground-enhanced and background-suppressed (FEBS) module is proposed to enhance the foreground of individual samples while weakening the impact of the background. Thirdly, A stage-wise consistency loss is presented to enable our model maintain consistent foreground-enhanced and background-suppressed stages. Finally, this study evaluates the proposed method and compares it with state-of-the-art approaches on three public datasets. The experimental results demonstrate the effectiveness and improvements achieved by using the presented architecture.
- 2 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (1) , 785-795
Shrink and Expose: Locate Edge Coarse-to-Fine for Camouflaged Object Detection
Precisely locating the edges of objects camouflaged as background is an exceedingly complicated task. Existing camouflaged object detection (COD) methods can accurately pinpoint the positions of objects, but the edges remain ambiguous. To tackle this challenge, we propose a multi-stage refinement framework to locate the precise edges of camouflaged objects coarse-to-fine, coined SAE, which integrates “shrink" and “expose" in each stage. In this paper, we transform the process by which humans capture object edges into a multi-stage shrinking process. Firstly, we obtain the edge probability distribution by subtracting a negative prediction result from a positive prediction result, thus proposing the positive-negative edge shrink module. The edge probability distribution from the previous stage is then explicitly propagated to the current stage to enhance the edge texture details. Second, we introduce edge exposure attention to expose significant edges, which also reflects the impact of the previous stage’s edge state and edge probability distribution on the current stage’s edge state. Finally, to eliminate state transition and edge deformation anomalies, we propose the abnormal localization restriction to ensure the proper execution of “shrink” and “expose”. Experimental results show that our model significantly outperforms recent SOTA methods on three COD benchmarks.
- 2 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (1) , 785-795
Shrink and Expose: Locate Edge Coarse-to-Fine for Camouflaged Object Detection
Precisely locating the edges of objects camouflaged as background is an exceedingly complicated task. Existing camouflaged object detection (COD) methods can accurately pinpoint the positions of objects, but the edges remain ambiguous. To tackle this challenge, we propose a multi-stage refinement framework to locate the precise edges of camouflaged objects coarse-to-fine, coined SAE, which integrates “shrink" and “expose" in each stage. In this paper, we transform the process by which humans capture object edges into a multi-stage shrinking process. Firstly, we obtain the edge probability distribution by subtracting a negative prediction result from a positive prediction result, thus proposing the positive-negative edge shrink module. The edge probability distribution from the previous stage is then explicitly propagated to the current stage to enhance the edge texture details. Second, we introduce edge exposure attention to expose significant edges, which also reflects the impact of the previous stage’s edge state and edge probability distribution on the current stage’s edge state. Finally, to eliminate state transition and edge deformation anomalies, we propose the abnormal localization restriction to ensure the proper execution of “shrink” and “expose”. Experimental results show that our model significantly outperforms recent SOTA methods on three COD benchmarks.
- 23 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-18
PRO-CLIP: A CLIP-Based Category Measurement Network Through Prototype and Regularized Optimal Transportation
In unstructured environments, robots are likely to encounter desktop objects that they have never seen before. Classifying these objects precisely is a prerequisite for accomplishing object-specific manipulation tasks. However, it is time-consuming to collect large-scale object classification datasets. Inspired by the prompt tuning methods, we propose the PRO-CLIP network, which is a category measurement method for desktop objects. Specifically, PRO-CLIP performs few-shot classification based on the knowledge from pretrained vision-language model. It utilizes token-level and prompt-level optimal transportations to jointly fine-tune the learnable vision-language prompts. For token-level stage, we propose the image patch reweighting mechanism to make alignments focus on the image patches that are close to the patch prototypes. This allows the patch embeddings have converging category representations, which reduces intra-class differences of visual features. For prompt-level stage, we propose a cascading optimal transportation module to simultaneously consider task-irrelevant knowledge in zero-shot features and task-specific knowledge in few-shot features. Due to the generalization performance of task-irrelevant knowledge, the proposed module achieves feature regularization during optimal transportation. Finally, we propose the UP loss to supervise the whole network. It contains unbalanced logit-level consistency losses and visual prototype loss. The logit-level consistency losses are used to make learnable features close to zero-shot features. The prototype loss makes the visual features approach to the corresponding prototypes in distance. We demonstrate the effectiveness of our method by performing few-shot classification experiments on different datasets including desktop objects. The relevant code will be available at https://github.com/NeuCV-IRMI/proclip.
- 23 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-18
PRO-CLIP: A CLIP-Based Category Measurement Network Through Prototype and Regularized Optimal Transportation
In unstructured environments, robots are likely to encounter desktop objects that they have never seen before. Classifying these objects precisely is a prerequisite for accomplishing object-specific manipulation tasks. However, it is time-consuming to collect large-scale object classification datasets. Inspired by the prompt tuning methods, we propose the PRO-CLIP network, which is a category measurement method for desktop objects. Specifically, PRO-CLIP performs few-shot classification based on the knowledge from pretrained vision-language model. It utilizes token-level and prompt-level optimal transportations to jointly fine-tune the learnable vision-language prompts. For token-level stage, we propose the image patch reweighting mechanism to make alignments focus on the image patches that are close to the patch prototypes. This allows the patch embeddings have converging category representations, which reduces intra-class differences of visual features. For prompt-level stage, we propose a cascading optimal transportation module to simultaneously consider task-irrelevant knowledge in zero-shot features and task-specific knowledge in few-shot features. Due to the generalization performance of task-irrelevant knowledge, the proposed module achieves feature regularization during optimal transportation. Finally, we propose the UP loss to supervise the whole network. It contains unbalanced logit-level consistency losses and visual prototype loss. The logit-level consistency losses are used to make learnable features close to zero-shot features. The prototype loss makes the visual features approach to the corresponding prototypes in distance. We demonstrate the effectiveness of our method by performing few-shot classification experiments on different datasets including desktop objects. The relevant code will be available at https://github.com/NeuCV-IRMI/proclip.
- Open Access
- 29 September 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (6) , 9553
Correction to: Person search via class activation map transferring
- 29 September 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (6) , 9553
Open AccessCorrection to: Person search via class activation map transferring
- 1 October 2021
- Published by Springer Nature in Machine Vision and Applications
- Vol. 32 (6) , 1-16
Semi-supervised learning for person re-identification based on style-transfer-generated data by CycleGANs
- 1 October 2021
- Published by Springer Nature in Machine Vision and Applications
- Vol. 32 (6) , 1-16
Semi-supervised learning for person re-identification based on style-transfer-generated data by CycleGANs