{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T06:05:01Z","timestamp":1789538701985,"version":"build-2803163510"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>\n                    Persuasive systems must detect user engagement in real time in order to adapt their strategy. Existing methods rely primarily on facial expressions or voice signals. Both raise privacy concerns and degrade under low video quality, motion blur, and ambient noise. Body gestures offer a privacy-preserving alternative, since skeleton representations do not encode identifiable facial features. What is missing is a method that localizes the specific moments at which gesture matters, rather than averaging behavior across the whole interaction. We introduce Dyadic Cross-Sparse Pooling (DXSP), a gesture-only neural architecture that localizes sparse decisive moments in dyadic persuasion without using face, voice, or verbal content. DXSP models both participants through cross-attention, weights candidate moments by interpersonal synchrony through a concordance gate, and selects exactly\n                    <jats:italic>k<\/jats:italic>\n                    = 3 windows per dyad through a hard top-\n                    <jats:italic>k<\/jats:italic>\n                    mechanism. We evaluate DXSP on 46 Japanese dyadic persuasion dialogues using upper-body pose data from the Sapiens Goliath foundation model. First, decisive moments are distributed across the full interaction rather than concentrated in any single phase. A three-component mixture fits the selected positions, but random selection of the same number of windows reproduces this evidence at every value of\n                    <jats:italic>k<\/jats:italic>\n                    from 1 to 10. Second, the relative concentration of decisive moments across phases differs between successful and failed outcomes. Successful dyads place 49.1% of their peaks in the opening phase. Failed dyads place 42.0% in the middle phase. Three tests converge on this contrast, including a permutation test that accounts for within-dyad clustering. Only the opening-phase comparison survives correction, and the association is not stable across values of\n                    <jats:italic>k<\/jats:italic>\n                    . Third, joint-level differences did not reach significance after correction across the seven joints, and the joint ranking is exploratory. The study contributes a mechanism that returns explicit decisive positions, evidence that mixture-based clustering claims require calibration against a matched null, and a preliminary phase-level link between decisive-moment placement and outcome. Gesture-only sensing therefore relates to persuasion at the level of phase distribution rather than detecting three-phase structure. This offers preliminary guidance for phase-aware intervention timing.\n                  <\/jats:p>","DOI":"10.3389\/frai.2026.1928901","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:32:59Z","timestamp":1789536779000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DXSP: gesture-only temporal localization of decisive moments in dyadic persuasion"],"prefix":"10.3389","volume":"9","author":[{"given":"Pakpoom","family":"Chaimook","sequence":"first","affiliation":[{"name":"Graduate School of Systems Information Science, Future University Hakodate","place":["Hakodate, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaoru","family":"Sumi","sequence":"additional","affiliation":[{"name":"Graduate School of Systems Information Science, Future University Hakodate","place":["Hakodate, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"200171","DOI":"10.1016\/j.iswa.2022.200171","article-title":"A systematic survey on multimodal emotion recognition using learning algorithms","volume":"17","author":"Ahmed","year":"2023","journal-title":"Intell. Syst. Applic"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1891903.1891910","article-title":"\u201cFacilitating multiparty dialog with gaze, gesture, and speech,\u201d","author":"Bohus","year":"2010","journal-title":"International conference on multimodal interfaces and the workshop on machine learning for multimodal interaction (ICMI-MLMI)"},{"key":"B3","doi-asserted-by":"publisher","first-page":"e70031","DOI":"10.1111\/psyp.70031","article-title":"Interpersonal physiological synchrony during dyadic joint action is increased by task novelty and reduced by social anxiety","volume":"62","author":"Boukarras","year":"2025","journal-title":"Psychophysiology"},{"key":"B4","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.ijhcs.2016.02.002","article-title":"Application of expectancy violations theory to communication with and judgments about embodied agents during a decision-making task","volume":"91","author":"Burgoon","year":"2016","journal-title":"Int. J. Hum. Comput. Stud"},{"key":"B5","doi-asserted-by":"publisher","first-page":"13339","DOI":"10.1109\/ICCV48922.2021.01311","article-title":"\u201cChannel-wise topology refinement graph convolution for skeleton-based action recognition,\u201d","author":"Chen","year":"2021","journal-title":"2021 IEEE\/CVF international conference on computer vision (ICCV)"},{"key":"B6","volume-title":"Statistical Power Analysis for the Behavioral Sciences, 2nd Edn","author":"Cohen","year":"1988"},{"key":"B7","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1007\/978-3-031-72940-9_23","article-title":"\u201cSkateformer: skeletal-temporal transformer for human action recognition,\u201d","author":"Do","year":"2025","journal-title":"Computer vision-ECCV 2024, lecture notes in computer science"},{"key":"B8","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1080\/02699939208411068","article-title":"An argument for basic emotions","volume":"6","author":"Ekman","year":"1992","journal-title":"Cogn. Emot"},{"key":"B9","doi-asserted-by":"publisher","first-page":"e0309831","DOI":"10.1371\/journal.pone.0309831","article-title":"From unimodal to multimodal dynamics of verbal and nonverbal cues during unstructured conversation","volume":"19","author":"Fauviaux","year":"2024","journal-title":"PLoS ONE"},{"key":"B10","volume-title":"Persuasive Technology: Using Computers to Change What We Think and Do","author":"Fogg","year":"2002"},{"key":"B11","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1145\/3678957.3685757","article-title":"\u201cMultilingual dyadic interaction corpus NoXi+J: Toward understanding Asian-European non-verbal cultural characteristics and their influences on engagement,\u201d","author":"Funk","year":"2024","journal-title":"Proceedings of the 26th international conference on multimodal interaction (ICMI '24)"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2567","DOI":"10.1109\/TAFFC.2023.3285777","article-title":"WiFE: WiFi and vision based unobtrusive emotion recognition via gesture and facial expression","volume":"14","author":"Gu","year":"2023","journal-title":"IEEE Trans. Affect. Comput"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2409.07388","article-title":"Recent trends of multimodal affective computing: a survey from NLP perspective","author":"Hu","year":"2024","journal-title":"arXiv [Preprint"},{"key":"B14","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1080\/01621459.1995.10476572","article-title":"Bayes factors","volume":"90","author":"Kass","year":"1995","journal-title":"J. Am. Stat. Assoc"},{"key":"B15","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1007\/978-3-031-73235-5_12","article-title":"\u201cSapiens: foundation for human vision models,\u201d","author":"Khirodkar","year":"2024","journal-title":"Computer vision-ECCV 2024, volume 15062 of lecture notes in computer science"},{"key":"B16","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1038\/s44159-023-00172-1","article-title":"The role of facial movements in emotion recognition","volume":"2","author":"Krumhuber","year":"2023","journal-title":"Nat. Rev. Psychol"},{"key":"B17","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1007\/978-3-031-19778-9_30","article-title":"\u201cPrivacy-preserving action recognition via motion difference quantization,\u201d","author":"Kumawat","year":"2022","journal-title":"Computer vision-ECCV 2022, volume 13673 of lecture notes in computer science"},{"key":"B18","doi-asserted-by":"publisher","first-page":"10410","DOI":"10.1109\/ICCV51070.2023.00958","article-title":"\u201cHierarchically decomposed graph convolutional networks for skeleton-based action recognition,\u201d","author":"Lee","year":"2023","journal-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)"},{"key":"B19","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/978-3-031-35915-6_8","article-title":"\u201cInter-person intra-modality attention based model for dyadic interaction engagement prediction,\u201d","author":"Li","year":"2023","journal-title":"Social computing and social media, volume 14025 of lecture notes in computer science"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3656580","article-title":"Foundations and trends in multimodal machine learning: principles, challenges, and open questions","volume":"56","author":"Liang","year":"2024","journal-title":"ACM Comput. Surv"},{"key":"B21","doi-asserted-by":"publisher","first-page":"29248","DOI":"10.1109\/CVPR52734.2025.02723","article-title":"\u201cRevealing key details to see differences: a novel prototypical perspective for skeleton-based action recognition,\u201d","author":"Liu","year":"2025","journal-title":"2025 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)"},{"key":"B22","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1515\/text.1.1988.8.3.243","article-title":"Rhetorical structure theory: toward a functional theory of text organization","volume":"8","author":"Mann","year":"1988","journal-title":"Text-Interdiscipl. J. Study Discourse"},{"key":"B23","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1140.001.0001","volume-title":"Affective Computing","author":"Picard","year":"1997"},{"key":"B24","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1017\/S0140525X04000056","article-title":"Toward a mechanistic psychology of dialogue","volume":"27","author":"Pickering","year":"2004","journal-title":"Behav. Brain Sci"},{"key":"B25","doi-asserted-by":"publisher","first-page":"103219","DOI":"10.1016\/j.cviu.2021.103219","article-title":"Skeleton-based action recognition via spatial and temporal transformer networks","volume":"209","author":"Plizzari","year":"2021","journal-title":"Comput. Vision Image Underst"},{"key":"B26","doi-asserted-by":"publisher","first-page":"e1563","DOI":"10.1002\/widm.1563","article-title":"Multimodal emotion recognition: a comprehensive review, trends, and challenges","volume":"14","author":"Ramaswamy","year":"2024","journal-title":"WIREs Data Mining Knowl. Discov"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2411.06837","article-title":"Persuasion with large language models: a survey","author":"Rogiers","year":"2024","journal-title":"arXiv [Preprint"},{"key":"B28","doi-asserted-by":"publisher","first-page":"148","DOI":"10.21437\/Interspeech.2013-56","article-title":"\u201cThe INTERSPEECH 2013 computational paralinguistics challenge: Social signals, conflict, emotion, autism,\u201d","author":"Schuller","year":"2013","journal-title":"Proceedings of interspeech 2013"},{"key":"B29","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1145\/3129340","article-title":"Speech emotion recognition: two decades in a nutshell, benchmarks, and ongoing trends","volume":"61","author":"Schuller","year":"2018","journal-title":"Commun. ACM"},{"key":"B30","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1214\/aos\/1176344136","article-title":"Estimating the dimension of a model","volume":"6","author":"Schwarz","year":"1978","journal-title":"Ann. Stat"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3664815","article-title":"From CNNs to transformers in multimodal human action recognition: a survey","volume":"20","author":"Shaikh","year":"2024","journal-title":"ACM Trans. Multimedia Comput. Commun. Applic"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1474","DOI":"10.1109\/TPAMI.2022.3157033","article-title":"Constructing stronger and faster baselines for skeleton-based action recognition","volume":"45","author":"Song","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.3389\/fpsyg.2014.01323","article-title":"Nonverbal synchrony and affect in dyadic interactions","volume":"5","author":"Tschacher","year":"2014","journal-title":"Front. Psychol"},{"key":"B34","doi-asserted-by":"publisher","first-page":"e0168306","DOI":"10.1371\/journal.pone.0168306","article-title":"Beyond synchrony: joint action in a complex production task reveals beneficial effects of decreased interpersonal synchrony","volume":"12","author":"Wallot","year":"2017","journal-title":"PLOS ONE"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3544548.3581425","article-title":"\u201cModeling the trade-off of privacy preservation and activity recognition on low-resolution images,\u201d","author":"Wang","year":"2023","journal-title":"Proceedings of the 2023 CHI conference on human factors in computing systems"},{"key":"B36","doi-asserted-by":"publisher","first-page":"7444","DOI":"10.1609\/aaai.v32i1.12328","article-title":"\u201cSpatial temporal graph convolutional networks for skeleton-based action recognition,\u201d","author":"Yan","year":"2018","journal-title":"Thirty-second AAAI conference on artificial intelligence"},{"key":"B37","doi-asserted-by":"publisher","first-page":"2049","DOI":"10.1109\/CVPR52733.2024.00200","article-title":"\u201cBlockgcn: redefine topology awareness for skeleton-based action recognition,\u201d","author":"Zhou","year":"2024","journal-title":"2024 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1928901\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:33:02Z","timestamp":1789536782000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1928901\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,16]]},"references-count":37,"alternative-id":["10.3389\/frai.2026.1928901"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1928901","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,16]]},"article-number":"1928901"}}