Chenchen Tao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chenchen Tao has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Chong Wang
Ningbo University
4 shared publications - Jiangbo Qian
Ningbo University
3 shared publications - Di Li
Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, China
1 shared publication - Haohe Li
Faculty of Electrical Engineering and Computer Science, Ningbo University, China
1 shared publication Jiafei Wu
Zhejiang Laboratory, Hangzhou, China
1 shared publication- Jiafei Wu
Zhejiang University, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 20 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (5) , 1-20
Learning Suspected Anomalies from Event Prompts for Video Anomaly Detection
Most models for Weakly Supervised Video Anomaly Detection (WS-VAD) rely on multiple instance learning, aiming to distinguish normal and abnormal snippets without specifying the type of anomaly. However, the ambiguous nature of anomaly definitions across contexts may introduce inaccuracy in discriminating abnormal and normal events. To show the model what is anomalous, a novel framework is proposed to guide the learning of suspected anomalies from event prompts. Given a textual prompt dictionary of potential anomaly events and the captions generated from anomaly videos, the semantic anomaly similarity between them could be calculated to identify the suspected events for each video snippet. It enables a new multi-prompt learning process to constrain the visual-semantic features across all videos, as well as provides a new way to label pseudo anomalies for self-training. To demonstrate its effectiveness, comprehensive experiments and detailed ablation studies are conducted on four datasets, namely XD-Violence, UCF-Crime, TAD, and ShanghaiTech. Our proposed model outperforms most state-of-the-art methods in terms of AP or AUC (86.5%, 90.4%, 94.4%, and 97.4%). Furthermore, it shows promising performance in open-set and cross-dataset cases. The data, code, and models can be found at: https://github.com/shiwoaz/lap .
- 20 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (5) , 1-20
Open AccessLearning Suspected Anomalies from Event Prompts for Video Anomaly Detection
Most models for Weakly Supervised Video Anomaly Detection (WS-VAD) rely on multiple instance learning, aiming to distinguish normal and abnormal snippets without specifying the type of anomaly. However, the ambiguous nature of anomaly definitions across contexts may introduce inaccuracy in discriminating abnormal and normal events. To show the model what is anomalous, a novel framework is proposed to guide the learning of suspected anomalies from event prompts. Given a textual prompt dictionary of potential anomaly events and the captions generated from anomaly videos, the semantic anomaly similarity between them could be calculated to identify the suspected events for each video snippet. It enables a new multi-prompt learning process to constrain the visual-semantic features across all videos, as well as provides a new way to label pseudo anomalies for self-training. To demonstrate its effectiveness, comprehensive experiments and detailed ablation studies are conducted on four datasets, namely XD-Violence, UCF-Crime, TAD, and ShanghaiTech. Our proposed model outperforms most state-of-the-art methods in terms of AP or AUC (86.5%, 90.4%, 94.4%, and 97.4%). Furthermore, it shows promising performance in open-set and cross-dataset cases. The data, code, and models can be found at: https://github.com/shiwoaz/lap .
- 24 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 5551-5563
Restructuring the Teacher and Student in Self-Distillation
Knowledge distillation aims to achieve model compression by transferring knowledge from complex teacher models to lightweight student models. To reduce reliance on pre-trained teacher models, self-distillation methods utilize knowledge from the model itself as additional supervision. However, their performance is limited by the same or similar network architecture between the teacher and student. In order to increase architecture variety, we propose a new self-distillation framework called restructured self-distillation (RSD), which involves restructuring both the teacher and student networks. The self-distilled model is expanded into a multi-branch topology to create a more powerful teacher. During training, diverse student sub-networks are generated by randomly discarding the teacher’s branches. Additionally, the teacher and student models are linked by a randomly inserted feature mixture block, introducing additional knowledge distillation in the mixed feature space. To avoid extra inference costs, the branches of the teacher model are then converted back to its original structure equivalently. Comprehensive experiments have demonstrated the effectiveness of our proposed framework for most architectures on CIFAR-10/100 and ImageNet datasets. Code is available at https://github.com/YujieZheng99/RSD.
- 24 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 5551-5563
Restructuring the Teacher and Student in Self-Distillation
Knowledge distillation aims to achieve model compression by transferring knowledge from complex teacher models to lightweight student models. To reduce reliance on pre-trained teacher models, self-distillation methods utilize knowledge from the model itself as additional supervision. However, their performance is limited by the same or similar network architecture between the teacher and student. In order to increase architecture variety, we propose a new self-distillation framework called restructured self-distillation (RSD), which involves restructuring both the teacher and student networks. The self-distilled model is expanded into a multi-branch topology to create a more powerful teacher. During training, diverse student sub-networks are generated by randomly discarding the teacher’s branches. Additionally, the teacher and student models are linked by a randomly inserted feature mixture block, introducing additional knowledge distillation in the mixed feature space. To avoid extra inference costs, the branches of the teacher model are then converted back to its original structure equivalently. Comprehensive experiments have demonstrated the effectiveness of our proposed framework for most architectures on CIFAR-10/100 and ImageNet datasets. Code is available at https://github.com/YujieZheng99/RSD.
- 27 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 10160-10173
Feature Reconstruction With Disruption for Unsupervised Video Anomaly Detection
Unsupervised video anomaly detection (UVAD) has gained significant attention due to its label-free nature. Typically, UVAD methods can be categorized into two branches, i.e. the one-class classification (OCC) methods and fully UVAD ones. However, the former may suffer from data imbalance and high false alarm rates, while the latter relies heavily on feature representation and pseudo-labels. In this paper, a novel feature reconstruction and disruption model (FRD-UVAD) is proposed for effective feature refinement and better pseudo-label generation in fully UVAD, based on cascade cross-attention transformers, a latent anomaly memory bank and an auxiliary scorer. The clip features are reconstructed using the space-time intra-clip information, as well as cross-inter-clip knowledge. Moreover, instead of blindly reconstructing all training features as OCC methods, a new disruption process is proposed to cooperate with the feature reconstruction simultaneously. Using the collected pseudo anomaly samples, it is able to emphasize the feature differences between normal and abnormal events. Additionally, a pre-trained UVAD scorer is utilized as a different criteria for anomaly prediction, which further refines the pseudo-labels. To demonstrate its effectiveness, comprehensive experiments and detailed ablation studies are conducted on three video benchmarks, namely CUHK Avenue, ShanghaiTech and UCF-Crime. Our proposed model (FRD-UVAD) achieves the best AUC performance (91.23%, 80.14%, and 82.12%) on all three datasets, surpassing other state-of-the-art OCC and fully UVAD methods. Furthermore, it obtains the lowest false alarm rate with a lower scene dependency, compared with other OCC methods. The code is available at https://github.com/tcc-power/FRD-unsupervised-video-anomaly-detection .
- 27 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 10160-10173
Feature Reconstruction With Disruption for Unsupervised Video Anomaly Detection
Unsupervised video anomaly detection (UVAD) has gained significant attention due to its label-free nature. Typically, UVAD methods can be categorized into two branches, i.e. the one-class classification (OCC) methods and fully UVAD ones. However, the former may suffer from data imbalance and high false alarm rates, while the latter relies heavily on feature representation and pseudo-labels. In this paper, a novel feature reconstruction and disruption model (FRD-UVAD) is proposed for effective feature refinement and better pseudo-label generation in fully UVAD, based on cascade cross-attention transformers, a latent anomaly memory bank and an auxiliary scorer. The clip features are reconstructed using the space-time intra-clip information, as well as cross-inter-clip knowledge. Moreover, instead of blindly reconstructing all training features as OCC methods, a new disruption process is proposed to cooperate with the feature reconstruction simultaneously. Using the collected pseudo anomaly samples, it is able to emphasize the feature differences between normal and abnormal events. Additionally, a pre-trained UVAD scorer is utilized as a different criteria for anomaly prediction, which further refines the pseudo-labels. To demonstrate its effectiveness, comprehensive experiments and detailed ablation studies are conducted on three video benchmarks, namely CUHK Avenue, ShanghaiTech and UCF-Crime. Our proposed model (FRD-UVAD) achieves the best AUC performance (91.23%, 80.14%, and 82.12%) on all three datasets, surpassing other state-of-the-art OCC and fully UVAD methods. Furthermore, it obtains the lowest false alarm rate with a lower scene dependency, compared with other OCC methods. The code is available at https://github.com/tcc-power/FRD-unsupervised-video-anomaly-detection .
- Open Access
- 13 January 2023
- Published by Association for Computing Machinery (ACM)
- p. 24-28
Action Recognition with Non-Uniform Key Frame Selector
Current approaches for spatiotemporal action recognition have achieved impressive progress, especially in temporal information processing. Meanwhile, the power of spatial information may be underestimated. Thus, a non-uniform key frame selector is proposed to pick the most representative frames according to the relationship between frames along the temporal dimension. Specifically, the reweight high-level frame features are used to generate an importance score sequence, while the key frames, in each temporal section, are selected based on the above scores. Such selected frames have richer semantic information, which has positive impact on the network training. The proposed model is evaluated on two action recognition, namely datasets HMDB51 and UCF101, and promising accuracy improvement is achieved.
- 13 January 2023
- Published by Association for Computing Machinery (ACM)
- p. 24-28
Open AccessAction Recognition with Non-Uniform Key Frame Selector
Current approaches for spatiotemporal action recognition have achieved impressive progress, especially in temporal information processing. Meanwhile, the power of spatial information may be underestimated. Thus, a non-uniform key frame selector is proposed to pick the most representative frames according to the relationship between frames along the temporal dimension. Specifically, the reweight high-level frame features are used to generate an importance score sequence, while the key frames, in each temporal section, are selected based on the above scores. Such selected frames have richer semantic information, which has positive impact on the network training. The proposed model is evaluated on two action recognition, namely datasets HMDB51 and UCF101, and promising accuracy improvement is achieved.