Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding in Novel Domains

Zitian Tang, Rohan Myer Krishnan, Zhiqiu Yu, Chen Sun 0002. Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding in Novel Domains. In IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2026, Tucson, AZ, USA, March 6-10, 2026. pages 4472-4482, IEEE, 2026. [doi]

Abstract

Abstract is missing.