 ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot
End-to-End Temporal Action DetectionIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2023 |
 Zero-Shot Temporal Action Detection via Vision-Language PromptingEuropean Conference on Computer Vision (ECCV), 2022 |
 Less than Few: Self-Shot Video Instance SegmentationEuropean Conference on Computer Vision (ECCV), 2022 |
 Pseudo-Q: Generating Pseudo Language Queries for Visual GroundingComputer Vision and Pattern Recognition (CVPR), 2022 |
 Universal Prototype Transport for Zero-Shot Action Recognition and
LocalizationInternational Journal of Computer Vision (IJCV), 2022 |
 Object Priors for Classifying and Localizing Unseen ActionsInternational Journal of Computer Vision (IJCV), 2021 |
