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

EMNLP 2020  ·  Jack Hessel, Zhenhai Zhu, Bo Pang, Radu Soricut ·

Pretraining from unlabelled web videos has quickly become the de-facto means of achieving high performance on many video understanding tasks. Features are learned via prediction of grounded relationships between visual content and automatic speech recognition (ASR) tokens. However, prior pretraining work has been limited to only instructional videos; a priori, we expect this domain to be relatively "easy:" speakers in instructional videos will often reference the literal objects/actions being depicted. We ask: can similar models be trained on more diverse video corpora? And, if so, what types of videos are "grounded" and what types are not? We fit a representative pretraining model to the diverse YouTube8M dataset, and study its success and failure cases. We find that visual-textual grounding is indeed possible across previously unexplored video categories, and that pretraining on a more diverse set results in representations that generalize to both non-instructional and instructional domains.

PDF Abstract EMNLP 2020 PDF EMNLP 2020 Abstract


Introduced in the Paper:


Used in the Paper:

Kinetics HowTo100M CrossTask

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here