{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T00:34:57Z","timestamp":1778891697847,"version":"3.51.4"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["MCIN\/AEI\/1O.13039\/501100011033"],"award-info":[{"award-number":["MCIN\/AEI\/1O.13039\/501100011033"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892910","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-7","source":"Crossref","is-referenced-by-count":5,"title":["Predicting Human-Object Interactions in Egocentric Videos"],"prefix":"10.1109","author":[{"given":"Manuel","family":"Benavent-Lledo","sequence":"first","affiliation":[{"name":"University of Alicante,Department of Computer Technology,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergiu","family":"Oprea","sequence":"additional","affiliation":[{"name":"University of Alicante,Department of Computer Technology,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John Alejandro","family":"Castro-Vargas","sequence":"additional","affiliation":[{"name":"University of Alicante,Department of Computer Technology,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Mulero-Perez","sequence":"additional","affiliation":[{"name":"University of Alicante,Department of Computer Technology,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose","family":"Garcia-Rodriguez","sequence":"additional","affiliation":[{"name":"University of Alicante,Department of Computer Technology,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","author":"wang","year":"2019","journal-title":"CSPNet A New Backbone that can Enhance Learning Capability of CNN"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2019.06.002"},{"key":"ref11","article-title":"Ego4d: Around the World in 3,000 Hours of Egocentric Video","volume":"abs 2110 7058","author":"grauman","year":"2021","journal-title":"CoRR"},{"key":"ref12","author":"vaswani","year":"2017","journal-title":"Attention is all you need"},{"key":"ref13","author":"bertasius","year":"2021","journal-title":"Is space-time attention all you need for video understanding?"},{"key":"ref14","author":"akbari","year":"2021","journal-title":"Vatt Transformers for multimodal self-supervised learning from raw video audio and text"},{"key":"ref15","author":"jaegle","year":"2021","journal-title":"Perceiver General perception with iterative attention"},{"key":"ref16","author":"zhang","year":"2021","journal-title":"Holistic 3d scene understanding from a single image with implicit representation"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.016"},{"key":"ref18","author":"li","year":"2021","journal-title":"Ego-exo Transferring visual representations from third-person to first-person videos"},{"key":"ref19","author":"nagarajan","year":"2020","journal-title":"Ego-topo Environment affordances from egocentric video"},{"key":"ref28","author":"bochkovskiy","year":"2020","journal-title":"YOLOv4 Optimal Speed and Accuracy of Object Detection"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3051319"},{"key":"ref27","author":"redmon","year":"2018","journal-title":"YOLOv3 An Incremental Improvement"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87869-6_42"},{"key":"ref6","article-title":"Scaling egocentric vision: The epic-kitchens dataset","author":"damen","year":"0","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref29","author":"redmon","year":"2016","journal-title":"YOLO9000 Better Faster Stronger"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296915"},{"key":"ref8","article-title":"Rescaling egocentric vision: Collection, pipeline and challenges for epic-kitchens-l00","author":"damen","year":"2021","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248010"},{"key":"ref2","author":"girdhar","year":"2021","journal-title":"Anticipative video transformer"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.226"},{"key":"ref1","author":"kapidis","year":"2019","journal-title":"Egocentric hand track and object-based human action recognition"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3058649"},{"key":"ref22","author":"girshick","year":"2014","journal-title":"Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1007\/978-3-319-10578-9_23","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","author":"he","year":"2014","journal-title":"Computer Vision - ECCV 2014"},{"key":"ref23","author":"girshick","year":"2015","journal-title":"Fast r-cnn"},{"key":"ref26","author":"redmon","year":"2016","journal-title":"You only look once Unified real-time object detection"},{"key":"ref25","author":"ren","year":"2016","journal-title":"Faster r-cnn Towards real-time object detection with region proposal networks"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","location":"Padua, Italy","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892910.pdf?arnumber=9892910","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:58:11Z","timestamp":1667516291000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892910\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892910","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}