{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T05:44:15Z","timestamp":1785822255547,"version":"3.56.0"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032319357","type":"print"},{"value":"9783032319364","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-31936-4_7","type":"book-chapter","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T04:50:33Z","timestamp":1785819033000},"page":"92-107","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EgoAfford: Affordance-Aware Zero-Shot Open-Vocabulary Egocentric Action Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5666-8471","authenticated-orcid":false,"given":"Davide","family":"Gesualdi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6344-408X","authenticated-orcid":false,"given":"Riccardo","family":"Santambrogio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1862-4853","authenticated-orcid":false,"given":"Francesca","family":"Palermo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4984-7432","authenticated-orcid":false,"given":"Chiara","family":"Plizzari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7059-413X","authenticated-orcid":false,"given":"Simone","family":"Mentasti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8306-6739","authenticated-orcid":false,"given":"Matteo","family":"Matteucci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"key":"7_CR1","doi-asserted-by":"publisher","first-page":"23716","DOI":"10.52202\/068431-1723","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Bambach, S., Lee, S., Crandall, D.J., Yu, C.: Lending a hand: detecting hands and recognizing activities in complex egocentric interactions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1949\u20131957 (2015)","DOI":"10.1109\/ICCV.2015.226"},{"key":"7_CR3","doi-asserted-by":"publisher","first-page":"33174","DOI":"10.52202\/075280-1440","volume":"36","author":"D Chatterjee","year":"2023","unstructured":"Chatterjee, D., Sener, F., Ma, S., Yao, A.: Opening the vocabulary of egocentric actions. Adv. Neural. Inf. Process. Syst. 36, 33174\u201333187 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, S., et al.: EgoThink: evaluating first-person perspective thinking capability of vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14291\u201314302 (2024)","DOI":"10.1109\/CVPR52733.2024.01355"},{"key":"7_CR5","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities (2025). arXiv:2507.06261 arXiv preprint"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Damen, D., et al.: Scaling egocentric vision: the epic-kitchens dataset. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 720\u2013736 (2018)","DOI":"10.1007\/978-3-030-01225-0_44"},{"key":"7_CR7","unstructured":"Damen, D., et al.: The epic-kitchens dataset: collection, challenges and baselines. Int. J. Comput. Vision 127, 1255\u20131274 (2021)"},{"issue":"1","key":"7_CR8","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11263-021-01531-2","volume":"130","author":"D Damen","year":"2022","unstructured":"Damen, D., et al.: Rescaling egocentric vision: collection, pipeline and challenges for epic-kitchens-100. Int. J. Comput. Vision 130(1), 33\u201355 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Fathi, A., Rehg, J.M.: Modeling actions through state changes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2579\u20132586 (2013)","DOI":"10.1109\/CVPR.2013.333"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Favero, A., et al.: Multi-modal hallucination control by visual information grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14303\u201314312 (2024)","DOI":"10.1109\/CVPR52733.2024.01356"},{"issue":"11","key":"7_CR11","doi-asserted-by":"publisher","first-page":"4021","DOI":"10.1109\/TPAMI.2020.2992889","volume":"43","author":"A Furnari","year":"2020","unstructured":"Furnari, A., Farinella, G.M.: Rolling-unrolling LSTMs for action anticipation from first-person video. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 4021\u20134036 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR12","unstructured":"Gibson, J.J.: The Ecological Approach to Visual Perception, Houghton Mifflin (1979)"},{"key":"7_CR13","unstructured":"Grauman, K., et al.: EGO-EXO4D: understanding skilled human activity from first-and third-person perspectives. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19383\u201319400 (2024)"},{"key":"7_CR14","unstructured":"Gu, J., et al.: A survey on LLM-as-a-judge (2025). https:\/\/arxiv.org\/abs\/2411.15594"},{"issue":"1","key":"7_CR15","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TCDS.2016.2594134","volume":"10","author":"L Jamone","year":"2016","unstructured":"Jamone, L., et al.: Affordances in psychology, neuroscience, and robotics: a survey. IEEE Trans. Cogni. Develop. Syst. 10(1), 4\u201325 (2016)","journal-title":"IEEE Trans. Cogni. Develop. Syst."},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, H., Grauman, K.: Seeing invisible poses: estimating 3D body pose from egocentric video. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3501\u20133509. IEEE (2017)","DOI":"10.1109\/CVPR.2017.373"},{"issue":"2","key":"7_CR17","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1109\/MPRV.2012.28","volume":"11","author":"K Kitani","year":"2012","unstructured":"Kitani, K.: Ego-action analysis for first-person sports videos. IEEE Pervasive Comput. 11(2), 92\u201395 (2012)","journal-title":"IEEE Pervasive Comput."},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Kokic, M., Stork, J.A., Haustein, J.A., Kragic, D.: Affordance detection for task-specific grasping using deep learning. In: IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids), pp. 91\u201398. IEEE (2017)","DOI":"10.1109\/HUMANOIDS.2017.8239542"},{"issue":"1","key":"7_CR19","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TPAMI.2015.2430335","volume":"38","author":"HS Koppula","year":"2015","unstructured":"Koppula, H.S., Saxena, A.: Anticipating human activities using object affordances for reactive robotic response. IEEE Trans. Pattern Anal. Mach. Intell. 38(1), 14\u201329 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Kundu, S., Trehan, S., Aakur, S.N.: Discovering novel actions from open world egocentric videos with object-grounded visual commonsense reasoning. In: European Conference on Computer Vision, pp. 39\u201356. Springer (2024)","DOI":"10.1007\/978-3-031-73202-7_3"},{"key":"7_CR21","doi-asserted-by":"publisher","first-page":"7575","DOI":"10.52202\/068431-0550","volume":"35","author":"KQ Lin","year":"2022","unstructured":"Lin, K.Q., et al.: Egocentric video-language pretraining. Adv. Neural. Inf. Process. Syst. 35, 7575\u20137586 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Lyu, H., Chen, C., Ji, Y., Xu, C.: EgoPrompt: prompt learning for egocentric action recognition. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 2762\u20132770 (2025)","DOI":"10.1145\/3746027.3754749"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Ma, M., Fan, H., Kitani, K.M.: Going deeper into first-person activity recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1894\u20131903 (2016)","DOI":"10.1109\/CVPR.2016.209"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Nagarajan, T., Feichtenhofer, C., Grauman, K.: Grounded human-object interaction hotspots from video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8688\u20138697 (2019)","DOI":"10.1109\/ICCV.2019.00878"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Nagarajan, T., Li, Y., Feichtenhofer, C., Grauman, K.: Ego-Topo: environment affordances from egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 163\u2013172 (2020)","DOI":"10.1109\/CVPR42600.2020.00024"},{"key":"7_CR26","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.patrec.2024.12.008","volume":"188","author":"SA Peirone","year":"2025","unstructured":"Peirone, S.A., Goletto, G., Planamente, M., Bottino, A., Caputo, B., Averta, G.: Egocentric zone-aware action recognition across environments. Pattern Recogn. Lett. 188, 140\u2013147 (2025)","journal-title":"Pattern Recogn. Lett."},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Perrett, T., et al.: HD-EPIC: a highly-detailed egocentric video dataset. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 23901\u201323913 (2025)","DOI":"10.1109\/CVPR52734.2025.02226"},{"key":"7_CR28","doi-asserted-by":"publisher","first-page":"119336","DOI":"10.52202\/079017-3792","volume":"37","author":"R Qian","year":"2024","unstructured":"Qian, R., et al.: Streaming long video understanding with large language models. Adv. Neural. Inf. Process. Syst. 37, 119336\u2013119360 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR29","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Speer, R., Chin, J., Havasi, C.: ConceptNet 5.5: an open multilingual graph of general knowledge, AAAI (2017)","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Sudhakaran, S., Lanz, O.: Attention is all we need: nailing down object-centric attention for egocentric activity recognition (2018). arXiv:1807.11794 arXiv preprint","DOI":"10.1109\/CVPR.2019.01019"},{"issue":"10","key":"7_CR32","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1145\/2629489","volume":"57","author":"D Vrande\u010di\u0107","year":"2014","unstructured":"Vrande\u010di\u0107, D., Kr\u00f6tzsch, M.: WikiData: a free collaborative knowledgebase. Commun. ACM 57(10), 78\u201385 (2014)","journal-title":"Commun. ACM"},{"key":"7_CR33","unstructured":"Wang, M., Xing, J., Liu, Y.: ActionClip: a new paradigm for video action recognition (2021). arXiv:2109.08472 arXiv preprint"},{"key":"7_CR34","unstructured":"Ye, S., Qi, H., Mathis, A., Mathis, M.W.: LLaVaction: evaluating and training multi-modal large language models for action recognition. arXiv preprint (2025)"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Yu, Z., Huang, Y., Furuta, R., Yagi, T., Goutsu, Y., Sato, Y.: Fine-grained affordance annotation for egocentric hand-object interaction videos. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2155\u20132163 (2023)","DOI":"10.1109\/WACV56688.2023.00219"},{"key":"7_CR36","unstructured":"Zhang, B., et\u00a0al.: VideoLLama 3: frontier multimodal foundation models for image and video understanding. arXiv preprint arXiv:2501.13106 (2025)"},{"key":"7_CR37","unstructured":"Zhang, Y., et al.: video instruction tuning with synthetic data. arXiv preprint arXiv:2410.02713 (2024)"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Misra, I., Kr\u00e4henb\u00fchl, P., Girdhar, R.: Learning video representations from large language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6586\u20136597 (2023)","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"7_CR39","doi-asserted-by":"publisher","first-page":"46595","DOI":"10.52202\/075280-2020","volume":"36","author":"L Zheng","year":"2023","unstructured":"Zheng, L., et al.: Judging LLM-as-a-judge with mt-bench and chatbot arena. Adv. Neural. Inf. Process. Syst. 36, 46595\u201346623 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31936-4_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T04:50:45Z","timestamp":1785819045000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31936-4_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"ISBN":["9783032319357","9783032319364"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31936-4_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]},"assertion":[{"value":"5 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}