Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTube.

Jack Hessel Zhenhai Zhu Bo Pang Radu Soricut

Published in: EMNLP (1) (2020)

Keyphrases

instructional videos
visual content
visual features
visual information
user generated
content analysis
low level
multimedia
action recognition
key frames
social media
information retrieval
computer vision
visual cues