{"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/how-do-you-do-it-fine-grained-action","title":"How Do You Do It? Fine-Grained Action Understanding with Pseudo-Adverbs","arxiv_id":"2203.12344","date":"2022-03-23","proceeding":"CVPR 2022 1","authors":["Hazel Doughty","Cees G. M. Snoek"],"abstract":"We aim to understand how actions are performed and identify subtle differences, such as 'fold firmly' vs. 'fold gently'. To this end, we propose a method which recognizes adverbs across different actions. However, such fine-grained annotations are difficult to obtain and their long-tailed nature makes it challenging to recognize adverbs in rare action-adverb compositions. Our approach therefore uses semi-supervised learning with multiple adverb pseudo-labels to leverage videos with only action labels. Combined with adaptive thresholding of these pseudo-adverbs we are able to make efficient use of the available data while tackling the long-tailed distribution. Additionally, we gather adverb annotations for three existing video retrieval datasets, which allows us to introduce the new tasks of recognizing adverbs in unseen action-adverb compositions and unseen domains. Experiments demonstrate the effectiveness of our method, which outperforms prior work in recognizing adverbs and semi-supervised works adapted for adverb recognition. We also show how adverbs can relate fine-grained actions.","url_abs":"https://arxiv.org/abs/2203.12344v2","url_pdf":"https://arxiv.org/pdf/2203.12344v2.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":"how-do-you-do-it-fine-grained-action","repo_url":"https://github.com/hazeld/pseudoadverbs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"video-adverb-retrieval","task_name":"Video-Adverb Retrieval"},{"task_slug":"video-adverb-retrieval-unseen-compositions","task_name":"Video-Adverb Retrieval (Unseen Compositions)"}],"methods":[],"datasets_introduced":[{"slug":"activitynet-adverbs","name":"ActivityNet Adverbs","full_name":""},{"slug":"msr-vtt-adverbs","name":"MSR-VTT Adverbs","full_name":""},{"slug":"vatex-adverbs","name":"VATEX Adverbs","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.12344","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}