Deep multimodal representation learning for generalizable person re-identification.
Mach. Learn., April, 2024
GIST: Improving Parameter Efficient Fine-Tuning via Knowledge Interaction.
Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024
Learning to Floorplan like Human Experts via Reinforcement Learning.
Proceedings of the Design, Automation & Test in Europe Conference & Exhibition, 2024
From Raw Video to Pedagogical Insights: A Unified Framework for Student Behavior Analysis.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024
LAMM: Label Alignment for Multi-Modal Prompt Learning.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024
GIST: Improving Parameter Efficient Fine Tuning via Knowledge Interaction.
CoRR, 2023
Colo-SCRL: Self-Supervised Contrastive Representation Learning for Colonoscopic Video Retrieval.
Proceedings of the IEEE International Conference on Multimedia and Expo, 2023
CC-PoseNet: Towards Human Pose Estimation in Crowded Classrooms.
Proceedings of the IEEE International Conference on Acoustics, 2023
AV-TAD: Audio-Visual Temporal Action Detection With Transformer.
Proceedings of the IEEE International Conference on Acoustics, 2023
Synpose: A Large-Scale and Densely Annotated Synthetic Dataset for Human Pose Estimation in Classroom.
Proceedings of the IEEE International Conference on Acoustics, 2022
Zero-Shot Learning for Skeleton-based Classroom Action Recognition.
Proceedings of the 2021 International Symposium on Computer Science and Intelligent Control, 2021
Unsupervised person re-identification by hierarchical cluster and domain transfer.
Multim. Tools Appl., 2020