TY - JOUR
AU - 
TI - Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
JF - Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
DO - 10.18653/v1/2024.emnlp-main.342
DA - 2024-01-01
UR - https://www.deepdyve.com/lp/unpaywall/video-llava-learning-united-visual-representation-by-alignment-before-AKzTePvSit
DP - DeepDyve
ER -