Detecting Moments and Highlights in Videos via Natural Language Queries

By Jie Lei, T. L. Berg, Mohit Bansal. Neural Information Processing Systems, 2021

378 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/18316673291b537b74eee1b369009379688da73a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Andrew Zisserman
2. Cordelia Schmid
3. Kristen Grauman
4. Antoine Miech
5. Arsha Nagrani
6. Luc Van Gool
7. Andrea Vedaldi
8. Ivan Laptev

Citations in the corpus

• Egocentric Video-Language Pretraining (2022, result): “In contrast to the conventional negative sampling from the same video [37, 52], we specifically design our temporally adjacent negative sampling strategy to focus on the frequent appearance changes in egocentric videos, which has not been explored in previous approaches.”
• Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning (2023, background): “[48] Jie Lei, Tamara L Berg, and Mohit Bansal.”