Bin Wen

contrastive learning (1) zero-shot learning (1) semantic segmentation (1) benchmark evaluation (1) object detection (1) self-supervised learning (1) in-context learning (1) visual storytelling (1) region proposal (1) vision-language model (1) multimodal large language model (1) instruction fine-tuning (1) temporal understanding (1) video language model (1) image-text alignment (1) open-world object detection (1) vision-language foundation model (1) open-world detection (1) semantic understanding (1) multimodal generation (1)