Chengbin Quan

attention mechanism (2) multi-modal learning (2) temporal modeling (1) transfer learning (1) computer vision (1) multimodal learning (1) cross-modal learning (1) video understanding (1) instance segmentation (1) deepfake detection (1) instruction tuning (1) parameter-efficient fine-tuning (1) parameter efficient fine-tuning (1) video question answering (1) parameter-efficient finetuning (1) semantic extraction (1) visual instruction (1) large language model (1) multi-scale aggregation (1) vision-language pretraining (1)