activity
20232025
most citedDistilling Vision-Language Models on Millions of Videos

2 citations · 2 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2025

Neptune: The Long Orbit to Benchmarking Long Video Understanding

Arsha Nagrani, Mingda Zhang, Ramin Mehran +10

We introduce Neptune, a benchmark for long video understanding that requires reasoning over long time horizons and across different modalities. Many existing video datasets and mod…