Tao Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tao Wang has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Hong Liu
State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China
2 shared publications - Chengwei Zhang
National Key Laboratory of Microwave Imaging, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China
1 shared publication - Guoquan Wang
State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China
1 shared publication - Haizhou Li
The Chinese University of Hong Kong, Shenzhen, China
1 shared publication - Jianbing Wu
Peking University, Shenzhen, China
1 shared publication - Jun Tang
School of Systems Engineering, National University of Defense Technology, Changsha, China
1 shared publication
Latest Publications
- 20 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 8529-8542
Feature Completion Transformer for Occluded Person Re-Identification
Occluded person re-identification is a challenging problem due to the destruction of occluders in different camera views. Most existing paradigms focus on visible human body parts through some external models to reduce noise interference. However, the feature misalignment problem caused by discarded occlusions negatively affects the performance of the network. Different from most previous works that discard the occluded regions, we present Feature Completion Transformer (FCFormer) that reduces noise interference and complements missing features in occluded parts. Specifically, Occlusion Instance Augmentation is proposed to simulate real and diverse occlusion situations on the holistic image, which enlarges the occlusion samples in the training set and forms aligned occluded-holistic pairs. To reduce the interference of noise, a two-stream architecture is proposed to learn pairwise discriminative features from aligned image pairs, while obtaining self-aligned occluded-holistic feature level sample-label pairs without additional auxiliary models. To complement the features of occluded regions, a Feature Completion Decoder is designed to aggregate possible information from self-generated occluded features in a self-supervised manner. Further, in order to correlate the completion features with identity information, Feature Completion Consistency loss is introduced to enforce the distribution of the generated completion features to be consistent with the real holistic feature distribution. In addition, we propose the Cross Hard Triplet loss to further bridge the gap between completion features and extracting features under the same ID. Extensive experiments over five challenging datasets demonstrate that the proposed FCFormer achieves superior performance and outperforms the state-of-theart methods by significant margins on Occluded-Duke dataset.
- 20 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 8529-8542
Feature Completion Transformer for Occluded Person Re-Identification
Occluded person re-identification is a challenging problem due to the destruction of occluders in different camera views. Most existing paradigms focus on visible human body parts through some external models to reduce noise interference. However, the feature misalignment problem caused by discarded occlusions negatively affects the performance of the network. Different from most previous works that discard the occluded regions, we present Feature Completion Transformer (FCFormer) that reduces noise interference and complements missing features in occluded parts. Specifically, Occlusion Instance Augmentation is proposed to simulate real and diverse occlusion situations on the holistic image, which enlarges the occlusion samples in the training set and forms aligned occluded-holistic pairs. To reduce the interference of noise, a two-stream architecture is proposed to learn pairwise discriminative features from aligned image pairs, while obtaining self-aligned occluded-holistic feature level sample-label pairs without additional auxiliary models. To complement the features of occluded regions, a Feature Completion Decoder is designed to aggregate possible information from self-generated occluded features in a self-supervised manner. Further, in order to correlate the completion features with identity information, Feature Completion Consistency loss is introduced to enforce the distribution of the generated completion features to be consistent with the real holistic feature distribution. In addition, we propose the Cross Hard Triplet loss to further bridge the gap between completion features and extracting features under the same ID. Extensive experiments over five challenging datasets demonstrate that the proposed FCFormer achieves superior performance and outperforms the state-of-theart methods by significant margins on Occluded-Duke dataset.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 8730-8739
Semantic-aware Consistency Network for Cloth-changing Person Re-Identification
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 8730-8739
Open AccessSemantic-aware Consistency Network for Cloth-changing Person Re-Identification
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 747-756
Slow-Fast Time Parameter Aggregation Network for Class-Incremental Lip Reading
Class incremental learning has yet to be explored in the field of lip-reading, which can circumvent data privacy issues and avoid the high training costs associated with joint training. In this paper, we introduce a benchmark for Class-Incremental Lip-Reading (CILR). To simultaneously improve the plasticity for new classes and stability for old classes in incremental learning, we propose a Slow-Fast Time Parameter Aggregation Network (TPAN) that decouples representation learning of new and old knowledge, taking into account the task characteristics of lip-reading. The TPAN comprises two dynamically evolving branches: one that uses fast gradient descent and the other employs slow momentum updates to retain old knowledge while adapting to new knowledge. Additionally, to achieve efficient knowledge transfer of the incremental model, we design a Hybrid Sequence-Distribution Distillation (HSDD) strategy to transfer knowledge in temporal feature view and classification probability view. We present a comprehensive comparison of the proposed method and previous state-of-the-art class incremental learning methods on the most commonly used lip-reading datasets LRW and LRW1000. The experimental result show that the proposed method can reduce the effect of catastrophic forgetting and improve the incremental accuracy.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 747-756
Open AccessSlow-Fast Time Parameter Aggregation Network for Class-Incremental Lip Reading
Class incremental learning has yet to be explored in the field of lip-reading, which can circumvent data privacy issues and avoid the high training costs associated with joint training. In this paper, we introduce a benchmark for Class-Incremental Lip-Reading (CILR). To simultaneously improve the plasticity for new classes and stability for old classes in incremental learning, we propose a Slow-Fast Time Parameter Aggregation Network (TPAN) that decouples representation learning of new and old knowledge, taking into account the task characteristics of lip-reading. The TPAN comprises two dynamically evolving branches: one that uses fast gradient descent and the other employs slow momentum updates to retain old knowledge while adapting to new knowledge. Additionally, to achieve efficient knowledge transfer of the incremental model, we design a Hybrid Sequence-Distribution Distillation (HSDD) strategy to transfer knowledge in temporal feature view and classification probability view. We present a comprehensive comparison of the proposed method and previous state-of-the-art class incremental learning methods on the most commonly used lip-reading datasets LRW and LRW1000. The experimental result show that the proposed method can reduce the effect of catastrophic forgetting and improve the incremental accuracy.