Back

VIOLIN

A Large-Scale Dataset for Video-and-Language Inference

VIOLIN

A new large-scale dataset, named VIOLIN (VIdeO-and-Language INference), is introduced for this task, which consists of 95,322 videohypothesis pairs from 15,887 video clips, spanning over 582 hours of video. These video clips contain rich content with diverse temporal dynamics, event shifts, and people interactions, collected from two sources: (i) popular TV shows, and (ii) movie clips from YouTube channels.Video-and-Language Inference, for joint multimodal understanding of video and text. Given a video clip with aligned subtitles as premise, paired with a natural language hypothesis based on the video content, a model needs to infer whether the hypothesis is entailed or contradicted by the given video clip.

Try V7 now
->
View author website
Task
Scene Understanding
Annotation Types
Instance Segmentation
95322
Items
10
Classes
95322
Labels
Models using this dataset
Last updated on 
October 31, 2023
Licensed under 
Research Only
Blog
Learn about machine learning and latests advancements in AI.
Read More
Playbooks
Discover how to optimize AI for your business.
Learn more
Case Studies
Discover how V7 empowers AI industry greats.
Explore now
Webinars
Explore AI topics, gain insights, and learn from experts.
Watch now