video-retrieval

Composed Video Retrieval (CoVR)

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in video-retrieval

Trend

Dataset

Best Model

Actions

WebVid-CoVR

Libraries

i

Use these libraries to find video-retrieval models and implementations

Datasets

WebVid-CoVR

Subtasks

No subtasks available.

Most implemented papers

Composed Video Retrieval via Enriched Context and Discriminative Embeddings

Muzammal Naseer, M. Felsberg, R. Anwer, Omkar Thawakar, Mubarak Shah, Salman H. Khan, F. Khan•Sun Mar 24 2024

This work introduces a novel CoVR framework that leverages detailed language descriptions to explicitly encode query-specific contextual information and learns discriminative embeddings of vision only, text only and vision-text for better alignment to accurately retrieve matched target videos.

21

Content

0

Paper Graph

CoVR: Learning Composed Video Retrieval from Web Video Captions

Gül Varol, Antoine Yang, Lucas Ventura, Cordelia Schmid•Sat Mar 23 2024

This work proposes a scalable automatic dataset creation methodology that generates triplets given video-caption pairs, while also expanding the scope of the task to include composed video retrieval (CoVR), and uses a large language model to generate the corresponding modification text.

60 0

Paper Graph

Adding a benchmark result helps the community track progress.