 DINO as a von Mises-Fisher mixture modelInternational Conference on Learning Representations (ICLR), 2024 |
 Enhancing Semantics in Multimodal Chain of Thought via Soft Negative
SamplingInternational Conference on Language Resources and Evaluation (LREC), 2024 |
 Logit Calibration and Feature Contrast for Robust Federated Learning on
Non-IID DataIEEE Transactions on Network Science and Engineering (TNSE), 2024 |
 Decoupling Static and Hierarchical Motion Perception for Referring Video
SegmentationComputer Vision and Pattern Recognition (CVPR), 2024 Shuting He Henghui Ding |
 Representation Alignment Contrastive Regularization for Multi-Object
TrackingIET Computer Vision (ICV), 2024 |
 DELAN: Dual-Level Alignment for Vision-and-Language Navigation by
Cross-Modal Contrastive LearningInternational Conference on Language Resources and Evaluation (LREC), 2024 |
