publications
publications by categories in reversed chronological order. generated by jekyll-scholar.
2025
-
Cross-modal Contrastive Masked AutoEncoder for Compressed Video Pre-trainingIEEE Transactions on Image Processing, 2025 - OBJVanish: Physically Realizable Text-to-3D Adversarial Generation of LiDAR-Invisible ObjectsUnder Peer Review, 2025
- CompSOT: Single-Object Tracking in Compressed Video via Progressive Multi-Modal MatchingUnder Peer Review, 2025
-
Towards Benchmarking and Assessing the Safety and Robustness of Autonomous Driving on Safety-critical ScenariosarXiv preprint arXiv:2503.23708, 2025 -
Safety2Drive: Safety-Critical Scenario Benchmark for the Evaluation of Autonomous DrivingarXiv preprint arXiv:2505.13872, 2025
2023
-
Compressed video prompt tuningNeurIPS, 2023
2022
-
Representation learning for compressed video action recognition via attentive cross-modal interaction with motion enhancementIn IJCAI, 2022
2021
-
Towards practical compressed video action recognition: A temporal enhanced multi-stream networkIn ICPR, 2021