{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/actalign-zero-shot-fine-grained-video","title":"ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment","arxiv_id":"2506.22967","date":"2025-06-28","proceeding":null,"authors":["Amir Aghdam","Vincent Tao Hu"],"abstract":"We address the task of zero-shot fine-grained video classification, where no video examples or temporal annotations are available for unseen action classes. While contrastive vision-language models such as SigLIP demonstrate strong open-set recognition via mean-pooled image-text similarity, they fail to capture the temporal structure critical for distinguishing fine-grained activities. We introduce ActAlign, a zero-shot framework that formulates video classification as sequence alignment. For each class, a large language model generates an ordered sub-action sequence, which is aligned with video frames using Dynamic Time Warping (DTW) in a shared embedding space. Without any video-text supervision or fine-tuning, ActAlign achieves 30.5% accuracy on the extremely challenging ActionAtlas benchmark, where human accuracy is only 61.6%. ActAlign outperforms billion-parameter video-language models while using approximately 8x less parameters. These results demonstrate that structured language priors, combined with classical alignment techniques, offer a scalable and general approach to unlocking the open-set recognition potential of vision-language models for fine-grained video understanding.","url_abs":"https://arxiv.org/abs/2506.22967v1","url_pdf":"https://arxiv.org/pdf/2506.22967v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"actalign-zero-shot-fine-grained-video","repo_url":"https://github.com/aghdamamir/actalign","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"actalign-zero-shot-fine-grained-video","repo_url":"https://github.com/amir-aghdam/ActAlign","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"dynamic-time-warping","task_name":"Dynamic Time Warping"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"open-set-learning","task_name":"Open Set Learning"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"text-similarity","task_name":"text similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}