{"id":"2605.19846","title":"FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding","url":"https://codeofpaper.com/paper/2605.19846","arxiv_url":"https://arxiv.org/abs/2605.19846","published":"2026-05-19","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":5}