Jianguo Jiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jianguo Jiang has a total of 57 co-authors. Here are the top co-authors by number of shared publications:
- Meibin Qi
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China
17 shared publications - Jingjing Wu
Hefei University of Technology, Hefei, China
8 shared publications - Hao Liu
AIRC, Midea Group
4 shared publications - Jiashi Feng
Bytedance Inc
3 shared publications - Shuicheng Yan
National University of Singapore
3 shared publications - Cuiqun Chen
School of Computer Science and Technology, Anhui University, Hefei, China
2 shared publications
Latest Publications
- 30 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 5600-5614
SYRER: Synergistic Relational Reasoning for RGB-D Cross-Modal Re-Identification
RGB-D cross-modal person re-identification is designed to match the people across the RGB and depth image modalities, where the large modality discrepancy makes this task intractable to tackle. To alleviate the negative effect brought by the discrepancy, this paper proposes a novel SYnergistic RElational Reasoning (SYRER) method, which targets at exploring the synergy between hetero-modalities for recognizing persons. We design a heterogeneous relationship contrast branch to establish intra-class and inter-class cross-modal relationships, which implements the cross-modal relation contrast learning to cope with imperceptible cross-modal inter-class differences and large cross-modal intra-class discrepancy. Additionally, in order to adequately represent the irregular depth images, we propose a point-wise depth extractor to extract non-uniform discriminative point features from depth images. Experimental results on two public datasets indicate the proposed SYRER surpasses the state-of-the-arts. And we also perform a series of analytic experiments to verify the effectiveness of each submodule of our SYRER.
- 30 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 5600-5614
SYRER: Synergistic Relational Reasoning for RGB-D Cross-Modal Re-Identification
RGB-D cross-modal person re-identification is designed to match the people across the RGB and depth image modalities, where the large modality discrepancy makes this task intractable to tackle. To alleviate the negative effect brought by the discrepancy, this paper proposes a novel SYnergistic RElational Reasoning (SYRER) method, which targets at exploring the synergy between hetero-modalities for recognizing persons. We design a heterogeneous relationship contrast branch to establish intra-class and inter-class cross-modal relationships, which implements the cross-modal relation contrast learning to cope with imperceptible cross-modal inter-class differences and large cross-modal intra-class discrepancy. Additionally, in order to adequately represent the irregular depth images, we propose a point-wise depth extractor to extract non-uniform discriminative point features from depth images. Experimental results on two public datasets indicate the proposed SYRER surpasses the state-of-the-arts. And we also perform a series of analytic experiments to verify the effectiveness of each submodule of our SYRER.
- Open Access
- 1 April 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1880 (1) , 012020
Pyramid and Similarity Based Feature Enhancement Network for Person Re-identification
Person re-identifification (Re-ID) has becomes an increasingly important task due to its wide applications in the field of intelligent video surveillance. However, Because of the camera shooting angle, the different proportions and pose changes of pedestrians in images are also different, such problem substantially hinders the model’s capability on further improving feature extraction. In this paper, we propose a new end-to-end architecture named Pyramid and Similarity Based Feature Enhancement Network (PS-Net) which includes Pyramid Joint Attention(PJA) and Similarity Feature Fusion Branch(SFF) to enhance the feature maps performance. Among them, PJA contains spatial attention at different receptive fields and channel attention to enhances the discriminative area of pedestrian features by combining the advantages of two different attentions. SFF fuses the features which have different levels of information but have congruent relationships, enriches the information contained in pedestrian features and generates more robust feature. Extensive experiments have been conducted to validate the superiority of our PS-Net for Re-ID over a wide variety of state-of-the-art methods on two large-scale datasets: Market-1501 and DukeMTMC-ReID.
- 1 April 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1880 (1) , 012020
Open AccessPyramid and Similarity Based Feature Enhancement Network for Person Re-identification
Person re-identifification (Re-ID) has becomes an increasingly important task due to its wide applications in the field of intelligent video surveillance. However, Because of the camera shooting angle, the different proportions and pose changes of pedestrians in images are also different, such problem substantially hinders the model’s capability on further improving feature extraction. In this paper, we propose a new end-to-end architecture named Pyramid and Similarity Based Feature Enhancement Network (PS-Net) which includes Pyramid Joint Attention(PJA) and Similarity Feature Fusion Branch(SFF) to enhance the feature maps performance. Among them, PJA contains spatial attention at different receptive fields and channel attention to enhances the discriminative area of pedestrian features by combining the advantages of two different attentions. SFF fuses the features which have different levels of information but have congruent relationships, enriches the information contained in pedestrian features and generates more robust feature. Extensive experiments have been conducted to validate the superiority of our PS-Net for Re-ID over a wide variety of state-of-the-art methods on two large-scale datasets: Market-1501 and DukeMTMC-ReID.
- 10 February 2021
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (12) , 17645-17666
Mask-guided dual attention-aware network for visible-infrared person re-identification
- 10 February 2021
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (12) , 17645-17666
Mask-guided dual attention-aware network for visible-infrared person re-identification
- Open Access
- 1 April 2020
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1518 (1) , 012026
Deep-Shallow Occlusion Parallelism Network for Person Re-Identification
In recent years, the progress of person re-identification has advanced significantly, but person in real scenes are often obscured by various objects. This problem has been ignored or solved based on an incomplete assumption by the previous person re-ID methods. This paper proposes a new training mechanism, Deep-Shallow Occlusion Parallelism network, which responds to multi-scale occlusion in a more universal case and alleviate the negative impact of occlusion effectively. Specifically, the proposed consists of shallow occlusion and deep occlusion, to which are applied with shielding simulation to enhance the difficulty of training samples. What’s more, channel-spatial attention is applied to various positions in each branch to concentrate on discriminative features afteqr occlusion. In the end, the weighted fusion of the two branches not only informs the network of the information of changes before and after occlusion, but also complements the deep and shallow information effectively. It makes the network more robust. This method has excellent performance on the three basic re-ID datasets and the largest partial re-ID dataset, with the state-of-the-art reached to or even surpassed.
- 1 April 2020
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1518 (1) , 012026
Open AccessDeep-Shallow Occlusion Parallelism Network for Person Re-Identification
In recent years, the progress of person re-identification has advanced significantly, but person in real scenes are often obscured by various objects. This problem has been ignored or solved based on an incomplete assumption by the previous person re-ID methods. This paper proposes a new training mechanism, Deep-Shallow Occlusion Parallelism network, which responds to multi-scale occlusion in a more universal case and alleviate the negative impact of occlusion effectively. Specifically, the proposed consists of shallow occlusion and deep occlusion, to which are applied with shielding simulation to enhance the difficulty of training samples. What’s more, channel-spatial attention is applied to various positions in each branch to concentrate on discriminative features afteqr occlusion. In the end, the weighted fusion of the two branches not only informs the network of the information of changes before and after occlusion, but also complements the deep and shallow information effectively. It makes the network more robust. This method has excellent performance on the three basic re-ID datasets and the largest partial re-ID dataset, with the state-of-the-art reached to or even surpassed.
- Open Access
- 1 May 2019
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1229 (1) , 012009
Video-based Person Re-identification Based on Feature Learning of Valid Regions and Distance Fusion
Video-based person re-identification (re-id) is a very challenging problem because of the occlusion and the changes of viewpoints, pedestrian postures and illumination. Most existing methods of video-based person re-id usually concatenates the extracted appearance and space-time features directly, which do not consider the discrepancy of different features fully. In order to deal with this problem well, we propose a simple but effective method based on feature learning of valid regions and distance fusion, which combines three distances. The first distance is local distance of valid regions calculated using the Gaussian of Gaussian(GOG) feature. Pedestrian images are divided in horizontal directions, and then regions with smaller distances are selected as valid ones to be reserved and regions with larger distances are as invalid ones to be removed due to occlusions and posture changes. The other two distances are obtained by independent metric learning using the histogram of oriented gradient 3D (HOG3D) feature and the Local Maximal Occurrence (LOMO) feature. The three distances are added as the final distance between pedestrian pair, so the matching rank of gallery is obtained. Extensive experiments are performed on the iLIDS-VID and PRID-2011 datasets, and the results prove the effectiveness of our methods.
- 1 May 2019
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1229 (1) , 012009
Open AccessVideo-based Person Re-identification Based on Feature Learning of Valid Regions and Distance Fusion
Video-based person re-identification (re-id) is a very challenging problem because of the occlusion and the changes of viewpoints, pedestrian postures and illumination. Most existing methods of video-based person re-id usually concatenates the extracted appearance and space-time features directly, which do not consider the discrepancy of different features fully. In order to deal with this problem well, we propose a simple but effective method based on feature learning of valid regions and distance fusion, which combines three distances. The first distance is local distance of valid regions calculated using the Gaussian of Gaussian(GOG) feature. Pedestrian images are divided in horizontal directions, and then regions with smaller distances are selected as valid ones to be reserved and regions with larger distances are as invalid ones to be removed due to occlusions and posture changes. The other two distances are obtained by independent metric learning using the histogram of oriented gradient 3D (HOG3D) feature and the Local Maximal Occurrence (LOMO) feature. The three distances are added as the final distance between pedestrian pair, so the matching rank of gallery is obtained. Extensive experiments are performed on the iLIDS-VID and PRID-2011 datasets, and the results prove the effectiveness of our methods.
- 3 January 2019
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 78 (20) , 29323-29341
Independent metric learning with aligned multi-part features for video-based person re-identification
- 3 January 2019
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 78 (20) , 29323-29341
Independent metric learning with aligned multi-part features for video-based person re-identification
- Open Access
Sequence-based Person Attribute Recognition with Joint CTC-Attention Model
Attribute recognition has become crucial because of its wide applications in many computer vision tasks, such as person re-identification. Like many object recognition problems, variations in viewpoints, illumination, and recognition at far distance, all make this task challenging. In this work, we propose a joint CTC-Attention model (JCM), which maps attribute labels into sequences to learn the semantic relationship among attributes. Besides, this network uses neural network to encode images into sequences, and employs connectionist temporal classification (CTC) loss to train the network with the aim of improving the encoding performance of the network. At the same time, it adopts the attention model to decode the sequences, which can realize aligning the sequences and better learning the semantic information from attributes. Extensive experiments on three public datasets, i.e., Market-1501 attribute dataset, Duke attribute dataset and PETA dataset, demonstrate the effectiveness of the proposed method.
Open AccessSequence-based Person Attribute Recognition with Joint CTC-Attention Model
Attribute recognition has become crucial because of its wide applications in many computer vision tasks, such as person re-identification. Like many object recognition problems, variations in viewpoints, illumination, and recognition at far distance, all make this task challenging. In this work, we propose a joint CTC-Attention model (JCM), which maps attribute labels into sequences to learn the semantic relationship among attributes. Besides, this network uses neural network to encode images into sequences, and employs connectionist temporal classification (CTC) loss to train the network with the aim of improving the encoding performance of the network. At the same time, it adopts the attention model to decode the sequences, which can realize aligning the sequences and better learning the semantic information from attributes. Extensive experiments on three public datasets, i.e., Market-1501 attribute dataset, Duke attribute dataset and PETA dataset, demonstrate the effectiveness of the proposed method.
- 2 November 2018
- Published by Springer Nature
- p. 50-61
Feature Fusion and Ellipse Segmentation for Person Re-identification
- 2 November 2018
- Published by Springer Nature
- p. 50-61
Feature Fusion and Ellipse Segmentation for Person Re-identification
- 19 September 2018
- Published by Springer Nature
- p. 768-779
Re-Ranking Person Re-Identification with Forward and Reverse Sorting Constraints
- 19 September 2018
- Published by Springer Nature
- p. 768-779
Re-Ranking Person Re-Identification with Forward and Reverse Sorting Constraints
- 19 September 2018
- Published by Springer Nature
- p. 115-125
Video-Based Person Re-identification with Adaptive Multi-part Features Learning
- 19 September 2018
- Published by Springer Nature
- p. 115-125
Video-Based Person Re-identification with Adaptive Multi-part Features Learning