Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Video Captioning on ViTT benchmark leaderboard · SOTA2 Research

Research Benchmarks

Video Captioning on ViTT

37.89BLEU-1MV-GPT

Updated 5mo ago

Evaluation Results

Method	Links
MV-GPT2022.01		37.89	1.04	26.75	34.76
M-MASS2022.01		22.37	0.82	11	31.4

SOTA Paper

MV-GPT

End-to-end Generative Pretraining for Multimodal Video Captioning

Dataset

ViTT

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Video Question Answering on ActivityNet-QA (test)Video Captioning on ActivityNet-Captions (test)Video Question Answering on OL-VideoQA (test)