LLaVA-Video-178K is a new synthetic video instruction dataset that, when combined with existing data to train LLaVA-Video, produces strong results on video understanding benchmarks.
Panda-70m: Captioning 70m videos with multiple cross-modality teachers
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
fields
cs.CV 3representative citing papers
VideoPhy benchmark shows state-of-the-art text-to-video models follow physical commonsense and text prompts in only 39.6% of cases for the best model.
VideoLLaMA3 uses a vision-centric training paradigm and token-reduction design to reach competitive results on image and video benchmarks.
citing papers explorer
-
LLaVA-Video: Video Instruction Tuning With Synthetic Data
LLaVA-Video-178K is a new synthetic video instruction dataset that, when combined with existing data to train LLaVA-Video, produces strong results on video understanding benchmarks.
-
VideoPhy: Evaluating Physical Commonsense for Video Generation
VideoPhy benchmark shows state-of-the-art text-to-video models follow physical commonsense and text prompts in only 39.6% of cases for the best model.
-
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
VideoLLaMA3 uses a vision-centric training paradigm and token-reduction design to reach competitive results on image and video benchmarks.