Heqing Zou

multimodal learning (5) audio-visual speech recognition (3) multimodal fusion (3) representation learning (2) contrastive learning (2) reinforcement learning (2) video temporal grounding (1) cross-modal representation (1) temporal alignment (1) noise robustness (1) cross-modal alignment (1) vision-language model (1) supervised fine-tuning (1) cross-modal learning (1) large vision-language model (1) pretrained model (1) audio captioning (1) adversarial network (1) adversarial learning (1) audio-text matching (1)