Yu Dai
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
Yu Dai has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Fanman Meng
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
5 shared publications - Heqian Qiu
University of Electronic Science and Technology of China
4 shared publications - Hongliang Li
University of Electronic Science and Technology of China
4 shared publications - Qingbo Wu
University of Electronic Science and Technology of China
4 shared publications - Lanxiao Wang
University of Electronic Science and Technology of China, Chengdu, China
3 shared publications - Taijin Zhao
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
3 shared publications
Latest Publications
- Open Access
- 28 October 2026
- Published by MDPI AG in Electronics
- Vol. 15 (21) , 5007
Learning a Video Neural Memory with Bias Mitigation for Video Class-Incremental Learning
Video class-incremental learning retains old knowledge while learning new actions under limited replay memory. Temporal compression stores more videos but may lose temporal details and introduce discrepancies between compressed and original videos. We propose Video Neural Memory with Bias Mitigation, combining a Spatio-Temporal Neural Memorizer and Contrastive Bias Correction. The Spatio-Temporal Neural Memorizer preserves temporal and task-related information in compact neural video representations. Contrastive Bias Correction uses class-wise adaptation prompts and contrastive learning to reduce compression-induced feature bias. Experiments on three action recognition benchmarks show higher average incremental accuracy than the compared methods under the same replay-memory budgets, including a gain of 9.18% over the strongest baseline on Something-Something V2 with 18 steps.
- 28 October 2026
- Published by MDPI AG in Electronics
- Vol. 15 (21) , 5007
Open AccessLearning a Video Neural Memory with Bias Mitigation for Video Class-Incremental Learning
Video class-incremental learning retains old knowledge while learning new actions under limited replay memory. Temporal compression stores more videos but may lose temporal details and introduce discrepancies between compressed and original videos. We propose Video Neural Memory with Bias Mitigation, combining a Spatio-Temporal Neural Memorizer and Contrastive Bias Correction. The Spatio-Temporal Neural Memorizer preserves temporal and task-related information in compact neural video representations. Contrastive Bias Correction uses class-wise adaptation prompts and contrastive learning to reduce compression-induced feature bias. Experiments on three action recognition benchmarks show higher average incremental accuracy than the compared methods under the same replay-memory budgets, including a gain of 9.18% over the strongest baseline on Something-Something V2 with 18 steps.
- 18 September 2026
- Published by Springer Nature in Machine Intelligence Research
- Vol. 23 (6) , 1382-1397
Continual Egocentric Activity Recognition by Multi-level Multimodal Feature Calibration and Temporal Aggregation
- 18 September 2026
- Published by Springer Nature in Machine Intelligence Research
- Vol. 23 (6) , 1382-1397
Continual Egocentric Activity Recognition by Multi-level Multimodal Feature Calibration and Temporal Aggregation
- 19 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 1995-2007
Geodesic-Aligned Gradient Projection for Continual Task Learning
Deep networks notoriously suffer from performance deterioration on previous tasks when learning from sequential tasks, i.e., catastrophic forgetting. Recent methods of gradient projection show that the forgetting is resulted from the gradient interference on old tasks and accordingly propose to update the network in an orthogonal direction to the task space. However, these methods assume the task space is invariant and neglect the gradual change between tasks, resulting in sub-optimal gradient projection and a compromise of the continual learning capacity. To tackle this problem, we propose to embed each task subspace into a non-Euclidean manifold, which can naturally capture the change of tasks since the manifold is intrinsically non-static compared to the Euclidean space. Subsequently, we analytically derive the accumulated projection between any two subspaces on the manifold along the geodesic path by integrating an infinite number of intermediate subspaces. Building upon this derivation, we propose a novel geodesic-aligned gradient projection (GAGP) method that harnesses the accumulated projection to mitigate catastrophic forgetting. The proposed method utilizes the geometric structure information on the task manifold by capturing the gradual change between the new and the old tasks. Empirical studies on image classification demonstrate that the proposed method alleviates catastrophic forgetting and achieves on-par or better performance compared to the state-of-the-art approaches.
- 19 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 1995-2007
Geodesic-Aligned Gradient Projection for Continual Task Learning
Deep networks notoriously suffer from performance deterioration on previous tasks when learning from sequential tasks, i.e., catastrophic forgetting. Recent methods of gradient projection show that the forgetting is resulted from the gradient interference on old tasks and accordingly propose to update the network in an orthogonal direction to the task space. However, these methods assume the task space is invariant and neglect the gradual change between tasks, resulting in sub-optimal gradient projection and a compromise of the continual learning capacity. To tackle this problem, we propose to embed each task subspace into a non-Euclidean manifold, which can naturally capture the change of tasks since the manifold is intrinsically non-static compared to the Euclidean space. Subsequently, we analytically derive the accumulated projection between any two subspaces on the manifold along the geodesic path by integrating an infinite number of intermediate subspaces. Building upon this derivation, we propose a novel geodesic-aligned gradient projection (GAGP) method that harnesses the accumulated projection to mitigate catastrophic forgetting. The proposed method utilizes the geometric structure information on the task manifold by capturing the gradual change between the new and the old tasks. Empirical studies on image classification demonstrate that the proposed method alleviates catastrophic forgetting and achieves on-par or better performance compared to the state-of-the-art approaches.
- 29 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 256
VLM-guided Explicit-Implicit Complementary novel class semantic learning for few-shot object detection
- 29 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 256
VLM-guided Explicit-Implicit Complementary novel class semantic learning for few-shot object detection
- Open Access
- 21 July 2023
- Published by SPIE-Intl Soc Optical Eng
- Vol. 2017, 60
Bad video classification based on deep learning
SPIE Digital Library Proceedings
- 21 July 2023
- Published by SPIE-Intl Soc Optical Eng
- Vol. 2017, 60
Open AccessBad video classification based on deep learning
SPIE Digital Library Proceedings
- 17 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 2430-2443
Towards Continual Egocentric Activity Recognition: A Multi-Modal Egocentric Activity Dataset for Continual Learning
With the rapid development of wearable cameras, it is now feasible to considerably increase the collection of egocentric video for first-person visual perception. However, the development is hindered by a shortage of multi-modal egocentric activity datasets. Furthermore, the catastrophic forgetting problem of multimodal continual activity learning, as a branch of continual learning, has not been thoroughly explored, which makes accumulating a larger collection of multi-modal activity data more urgent. To address this shortage, we propose a multi-modal egocentric activity dataset for continual activity learning named UESTC-MMEA-CL in this paper. The dataset is collected using our self-developed glasses with a first-person camera and wearable sensors, and it contains synchronized data of video, accelerometers, and gyroscopes for 32 types of daily activities performed by 10 participants who wore our glasses. Statistical analysis of the sensor data is given to show the auxiliary effects of activity recognition. We report the results of egocentric activity recognition of three modalities (RGB, acceleration, and gyroscope) separately and jointly on a base network architecture. We thoroughly evaluated four baseline methods with different multimodal combinations to explore the catastrophic forgetting in continual learning on UESTC-MMEA-CL. We hope that the UESTC-MMEA-CL dataset can act as a facilitator for future studies on continual learning for first-person activity recognition in wearable applications. You can download preliminary data from https://ivipclab.github.io/publication\_uestc-mmea-cl/mmea-cl . The data is currently used to solve the problems of multimodal continual learning of activities.
- 17 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 2430-2443
Towards Continual Egocentric Activity Recognition: A Multi-Modal Egocentric Activity Dataset for Continual Learning
With the rapid development of wearable cameras, it is now feasible to considerably increase the collection of egocentric video for first-person visual perception. However, the development is hindered by a shortage of multi-modal egocentric activity datasets. Furthermore, the catastrophic forgetting problem of multimodal continual activity learning, as a branch of continual learning, has not been thoroughly explored, which makes accumulating a larger collection of multi-modal activity data more urgent. To address this shortage, we propose a multi-modal egocentric activity dataset for continual activity learning named UESTC-MMEA-CL in this paper. The dataset is collected using our self-developed glasses with a first-person camera and wearable sensors, and it contains synchronized data of video, accelerometers, and gyroscopes for 32 types of daily activities performed by 10 participants who wore our glasses. Statistical analysis of the sensor data is given to show the auxiliary effects of activity recognition. We report the results of egocentric activity recognition of three modalities (RGB, acceleration, and gyroscope) separately and jointly on a base network architecture. We thoroughly evaluated four baseline methods with different multimodal combinations to explore the catastrophic forgetting in continual learning on UESTC-MMEA-CL. We hope that the UESTC-MMEA-CL dataset can act as a facilitator for future studies on continual learning for first-person activity recognition in wearable applications. You can download preliminary data from https://ivipclab.github.io/publication\_uestc-mmea-cl/mmea-cl . The data is currently used to solve the problems of multimodal continual learning of activities.