What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction

[2407.08101] What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2407.08101 (cs) [Submitted on 11 Jul 2024 ( v1 ), last revised 14 Apr 2026 (this version, v5)] Title: What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction Authors: Sunny Panchal , Apratim Bhattacharyya , Guillaume Berger , Antoine Mercier , Cornelius Bohm , Florian Dietrichkeit , Reza Pourreza , Xuanlin Li , Pulkit Madan , Mingu Lee , Mark Todorovich , Ingo Bax , Roland Memisevic View a PDF of the paper titled What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction, by Sunny Panchal and 12 other authors View PDF HTML (experimental) Abstract: Vision-language models have shown impressive progress in recent years. However, existing models are largely limited to turn-based interactions, where each turn must be stepped (i.e., prompted) by the user. Open-ended, asynchronous interactions, where an AI model may proactively deliver timely responses or feedback based on the unfolding situation in real-time, are an open challenge. In this work, we present the QEVD benchmark and dataset, which explores human-AI interaction in the challenging, yet controlled, real-world domain of fitness coaching -- a task which intrinsically requires monitoring live user activity and providing immediate feedback. The benchmark requires vision-language models to recognize complex human actions, identify possible mistakes, and provide appropriate feedback in real-time. Our experiments reveal the limitations of existing state-of-the-art vision-language models for such asynchronous situated interactions. Motivated by this, we propose a simple end-to-end streaming baseline that can respond asynchronously to human actions with appropriate feedback at the appropriate time. Comments: Accepted to the 2024 NeurIPS Datasets and Benchmarks track; Data: this https URL Dataset quick start guide: this https URL and Stream-VLM code: this https URL Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2407.08101 [cs.CV] (or arXiv:2407.08101v5 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2407.08101 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Apratim Bhattacharyya [ view email ] [v1] Thu, 11 Jul 2024 00:10:45 UTC (7,135 KB) [v2] Mon, 25 Nov 2024 20:25:06 UTC (15,613 KB) [v3] Mon, 23 Dec 2024 17:06:20 UTC (15,613 KB) [v4] Mon, 13 Apr 2026 01:30:09 UTC (15,613 KB) [v5] Tue, 14 Apr 2026 18:39:42 UTC (15,613 KB) Full-text links: Access Paper: View a PDF of the paper titled What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction, by Sunny Panchal and 12 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2024-07 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Interventions in Nutrition Education and Skills#803554
• A New Foundation for the Propensity Interpretation of Fitness#489270
• Dynamic coupling of motivation, flow, and psychological resilience: a career narrative case study of a Chinese male aerobic gymnastics world champion.#334577
• Promotion of Healthy Eating Habits and Physical Activity Among Children and Their Families.#849194
• Invisible burdens of platform work: a qualitative study of food-delivery riders' lived experiences in urban India.#9575