Chang-Wen Chen

object detection (2) transformer architecture (1) zero-shot learning (1) transfer learning (1) multi-instance learning (1) motion synthesis (1) open-vocabulary detection (1) weakly supervised learning (1) multi-modal learning (1) video understanding (1) scene graph generation (1) visual grounding (1) spatial structure (1) language supervision (1) moment retrieval (1) human-object interaction detection (1) video query (1) backdoor adjustment (1) structure-aware learning (1) keypoint detection (1)