Jiayin Cai

video understanding (2) video question answering (2) question answering (1) information retrieval (1) multimodal learning (1) multi-modal learning (1) visual grounding (1) multimodal retrieval (1) large multimodal model (1) vision-language model (1) multimodal large language model (1) feature augmentation (1) multimodal reasoning (1) memory network (1) neural network (1) listwise reranking (1) pointwise reranking (1) object referring (1) zero-shot learning (1) cross-video reasoning (1)