Teach a Molmo2Fish: Towards interactive fish tracking with natural language guidance Paper • 2608.18602 • Published Aug 19
The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Counting Paper • 2207.09295 • Published Jul 19, 2022
Align and Distill: Unifying and Improving Domain Adaptive Object Detection Paper • 2403.12029 • Published Mar 18, 2024
VideoPrism: A Foundational Visual Encoder for Video Understanding Paper • 2402.13217 • Published Feb 20, 2024 • 42