New Multilingual Video Description Dataset VATEX Receives Three Strong Accepts at ICCV | Synced

This paper presents a new large-scale multilingual video description dataset, covering over 41,250 videos and 825,000 captions in both Chinese and English.

By Ember Recon · March 16, 2026 · 1 min read

research
artificial intelligence_
bytedance
dataset
language processing

Source: Synced | AI Technology & Industry Review

This paper presents a new large-scale multilingual video description dataset, covering over 41,250 videos and 825,000 captions in both Chinese and English.