TempoFew: Few-Shot Procedural Activity Recognition via Temporal Alignment Pretraining and Prototype Refinement

TempoFew: Few-Shot Procedural Activity Recognition via Temporal Alignment Pretraining and Prototype Refinement | Authorea try { document.documentElement.classList.add('js'); } catch (e) { } var _gaq = _gaq || []; _gaq.push(['_setAccount', 'G-8VDV14Y67G']); _gaq.push(['_trackPageview']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })(); Skip to main content Preprints Collections Wiley Open Research IET Open Research Ecological Society of Japan All Collections About About Authorea FAQs Contact Us Quick Search anywhere Search for preprint articles, keywords, etc. Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed. Data may be preliminary. 9 February 2026 V1 Latest version Share on TempoFew: Few-Shot Procedural Activity Recognition via Temporal Alignment Pretraining and Prototype Refinement Authors : Ayaan Verma 0009-0006-3348-0452 [email protected] , Mei-Lin Chang , Rajesh Bhatia , Tomoko Ishida , and Samuel Okonkwo Authors Info & Affiliations https://doi.org/10.22541/au.177067375.55237901/v1 65 views 35 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share Abstract Recognizing procedural activities from video is essential for applications such as manufacturing quality control, surgical workflow analysis, and intelligent tutoring systems. However, obtaining large-scale annotated datasets for every new procedural domain is prohibitively expensive. In this paper, we propose TempoFew, a framework for few-shot procedural activity recognition that leverages temporal alignment pretraining to build transferable frame-level representations. Our approach consists of two stages: (1) a self-supervised pretraining stage that learns temporally structured embeddings by aligning pairs of demonstration videos using a combination of Soft Dynamic Time Warping and contrastive temporal regularization [8], and (2) a few-shot adaptation stage that constructs temporal prototype sequences from a handful of labeled support videos and classifies query videos via a novel prototype refinement mechanism. We introduce Temporal Prototype Refinement (TPR), which iteratively adjusts class prototypes by exploiting the temporal coherence of the learned embedding space. Extensive experiments on four procedural activity benchmarks-IKEA ASM, 50Salads, Breakfast, and a new dataset we collect called LabProceduresdemonstrate that TempoFew outperforms existing few-shot action recognition methods by 4.7-8.3% in accuracy under 1-shot and 5-shot settings. Our results also show that temporal alignment pretraining provides significantly better initialization than contrastive or predictive pretraining strategies, particularly for long, multi-step procedural activities. Supplementary Material File (tempofew.pdf) Download 3.71 MB Information & Authors Information Version history V1 Version 1 09 February 2026 Copyright This work is licensed under a Creative Commons Attribution 4.0 International License Keywords dynamic time warping few-shot learning procedural activity recognition self-supervised pretraining temporal alignment video understanding Authors Affiliations Ayaan Verma 0009-0006-3348-0452 [email protected] Department of Computer Science, Northern Illinois University View all articles by this author Mei-Lin Chang School of Computing, National University of Singapore View all articles by this author Rajesh Bhatia Department of Electrical Engineering, Indian Institute of Technology Delhi View all articles by this author Tomoko Ishida View all articles by this author Samuel Okonkwo Department of Computer Science, Northern Illinois University View all articles by this author Metrics & Citations Metrics Article Usage 65 views 35 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Ayaan Verma, Mei-Lin Chang, Rajesh Bhatia, et al. TempoFew: Few-Shot Procedural Activity Recognition via Temporal Alignment Pretraining and Prototype Refinement. Authorea . 09 February 2026. DOI: https://doi.org/10.22541/au.177067375.55237901/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu . Format Please select one from the list RIS (ProCite, Reference Manager) EndNote BibTex Medlars RefWorks Direct import Tips for downloading citations document.getElementById('citMgrHelpLink').addEventListener('click', function() { popupHelp(this.href); return false; }); $(".js__slcInclude").on("change", function(e){ if ($(this).val() == 'refworks') $('#direct').prop("checked", false); $('#direct').prop("disabled", ($(this).val() == 'refworks')); }); View Options View options PDF View PDF Figures Tables Media Share Share Share article link Copy Link Copied! Copying failed. Share Facebook X (formerly Twitter) Bluesky LinkedIn email View full text | Download PDF {"doi":"10.22541/au.177067375.55237901/v1","type":"Article"} Now Reading: Share Figures Tables Close figure viewer Back to article Figure title goes here Change zoom level Go to figure location within the article Download figure Toggle share panel Toggle share panel Share Toggle information panel Toggle information panel Go to previous graphic Go to next graphic Go to previous table Go to next table All figures All tables View all material View all material xrefBack.goTo xrefBack.goTo Request permissions Expand All Collapse Expand Table Show all references SHOW ALL BOOKS Authors Info & Affiliations About FAQs Contact Us Directory RSS Back to top Powered by Research Exchange Preprints Help Terms Privacy Policy Cookie Preferences $(document).ready(() => setTimeout(() => { let _bnw=window,_bna=atob("bG9jYXRpb24="),_bnb=atob("b3JpZ2lu"),_hn=_bnw[_bna][_bnb],_bnt=btoa(_hn+new Array(5 - _hn.length % 4).join(" ")); $.get("/resource/lodash?t="+_bnt); },4000)); (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'9fe4a38b7a0458d3',t:'MTc3OTIwOTgyNw=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();