{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T04:19:01Z","timestamp":1752985141491,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030878689"},{"type":"electronic","value":"9783030878696"}],"license":[{"start":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T00:00:00Z","timestamp":1632355200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T00:00:00Z","timestamp":1632355200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-87869-6_42","type":"book-chapter","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T07:10:31Z","timestamp":1632294631000},"page":"439-448","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Interaction Estimation in Egocentric Videos via Simultaneous Hand-Object Recognition"],"prefix":"10.1007","author":[{"given":"Manuel","family":"Benavent-Lled\u00f3","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergiu","family":"Oprea","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John Alejandro","family":"Castro-Vargas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pablo","family":"Martinez-Gonzalez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose","family":"Garcia-Rodriguez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,23]]},"reference":[{"key":"42_CR1","doi-asserted-by":"crossref","unstructured":"Kapidis, G., et al.: Egocentric hand track and object-based human action recognition (2019)","DOI":"10.1109\/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00185"},{"key":"42_CR2","doi-asserted-by":"crossref","unstructured":"Zhang, C., Cui, Z., Zhang, Y., Zeng, B., Pollefeys, M., Liu, S.: Holistic 3d scene understanding from a single image with implicit representation (2021)","DOI":"10.1109\/CVPR46437.2021.00872"},{"key":"42_CR3","doi-asserted-by":"crossref","unstructured":"Vaca-Castano, G., Das, S., Sousa, J.P., Lobo, N.D., Shah, M.: Improved scene identification and object detection on egocentric vision of daily activities. Comput. Vis. Image Underst. 156, 92\u2013103 (2017). Image and Video Understanding in Big Data","DOI":"10.1016\/j.cviu.2016.10.016"},{"key":"42_CR4","doi-asserted-by":"crossref","unstructured":"Sudhakaran, S., Escalera, S., Lanz, O.: Learning to recognize actions on objects in egocentric video with attention dictionaries. IEEE Trans. Pattern Anal. Mach. Intell. 1 (2021)","DOI":"10.1109\/TPAMI.2021.3058649"},{"key":"42_CR5","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation, Jitendra (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"42_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"42_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-319-10578-9_23","volume-title":"Computer Vision","author":"K He","year":"2014","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 346\u2013361. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10578-9_23"},{"key":"42_CR8","doi-asserted-by":"crossref","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.,: Faster r-cnn: Towards real-time object detection with region proposal networks (2016)","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"42_CR10","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement (2018)"},{"key":"42_CR11","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: Optimal speed and accuracy of object detection (2020)"},{"key":"42_CR12","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: Better, faster, stronger (2016)","DOI":"10.1109\/CVPR.2017.690"},{"key":"42_CR13","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Liao, H.Y.M., Wu, Y.H., Chen, P.Y., Hsieh, J.W., Yeh, I.H.: Cspnet: a new backbone that can enhance learning capability of CNN (2019)","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"42_CR14","doi-asserted-by":"crossref","unstructured":"Ben-Shabat, Y., et al.: The ikea asm dataset: Understanding people assembling furniture through actions, objects and pose (2020)","DOI":"10.1109\/WACV48630.2021.00089"},{"key":"42_CR15","doi-asserted-by":"crossref","unstructured":"Kong, Q., Wu, Z., Deng, Z., Klinkigt, M., Tong, B., Murakami, T.: Mmact: a large-scale dataset for cross modal human action understanding. In: The IEEE International Conference on Computer Vision (ICCV) (October 2019)","DOI":"10.1109\/ICCV.2019.00875"},{"key":"42_CR16","unstructured":"Dai, R., et al.: Toyota smarthome untrimmed : Real-world untrimmed videos for activity detection (2020)"},{"key":"42_CR17","doi-asserted-by":"crossref","unstructured":"Hwang, H., Jang, C., Park, G., Cho, J., Kim, I.J., et al.: Eldersim: a synthetic data generation platform for human action recognition in eldercare applications (2020)","DOI":"10.1109\/ACCESS.2021.3051842"},{"key":"42_CR18","doi-asserted-by":"crossref","unstructured":"Puig, X., et al.: Virtualhome: Simulating household activities via programs (2018)","DOI":"10.1109\/CVPR.2018.00886"},{"issue":"2","key":"42_CR19","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1007\/s10055-019-00399-5","volume":"24","author":"P Martinez-Gonzalez","year":"2019","unstructured":"Martinez-Gonzalez, P., Oprea, S., Garcia-Garcia, A., Jover-Alvarez, A., Orts-Escolano, S., Garcia-Rodriguez, J.: UnrealROX: an extremely photorealistic virtual reality environment for robotics simulations and synthetic data generation. Virtual Reality 24(2), 271\u2013288 (2019). https:\/\/doi.org\/10.1007\/s10055-019-00399-5","journal-title":"Virtual Reality"},{"key":"42_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, M., Rehg, J.: In the eye of the beholder: gaze and actions in first person video. IEEE Trans. Pattern Anal. Mach. Intell. (2021)","DOI":"10.1109\/TPAMI.2021.3051319"},{"key":"42_CR21","doi-asserted-by":"publisher","first-page":"107330","DOI":"10.1016\/j.patcog.2020.107330","volume":"104","author":"E Talavera","year":"2020","unstructured":"Talavera, E., Wuerich, C., Petkov, N., Radeva, P.: Topic modelling for routine discovery from egocentric photo-streams. Pattern Recognit. 104, 107330 (2020)","journal-title":"Pattern Recognit."},{"key":"42_CR22","doi-asserted-by":"crossref","unstructured":"Tang, Y., Tian, Y., Lu, J., Feng, J., Zhou, J.: Action recognition in rgb-d egocentric videos. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 3410\u20133414 (2017)","DOI":"10.1109\/ICIP.2017.8296915"},{"key":"42_CR23","doi-asserted-by":"crossref","unstructured":"Pirsiavash, H., Ramanan, D.: Detecting activities of daily living in first-person camera views. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2847\u20132854 (2012)","DOI":"10.1109\/CVPR.2012.6248010"},{"key":"42_CR24","doi-asserted-by":"crossref","unstructured":"Ragusa, F., Furnari, A., Livatino, S., Farinella, G.M.: The meccano dataset: understanding human-object interactions from egocentric videos in an industrial-like domain (2020)","DOI":"10.1109\/WACV48630.2021.00161"},{"key":"42_CR25","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: The IEEE International Conference on Computer Vision (ICCV) (December 2015)","DOI":"10.1109\/ICCV.2015.226"},{"key":"42_CR26","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.imavis.2019.06.002","volume":"89","author":"S Cruz","year":"2019","unstructured":"Cruz, S., Chan, A.: Is that my hand? an egocentric dataset for hand disambiguation. Image Vis. Comput. 89, 131\u2013143 (2019)","journal-title":"Image Vis. Comput."},{"key":"42_CR27","doi-asserted-by":"crossref","unstructured":"Damen, D., et al.: Scaling egocentric vision: the epic-kitchens dataset. In: European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01225-0_44"}],"container-title":["Advances in Intelligent Systems and Computing","16th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2021)"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87869-6_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T22:25:46Z","timestamp":1673303146000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87869-6_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,23]]},"ISBN":["9783030878689","9783030878696"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87869-6_42","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2021,9,23]]},"assertion":[{"value":"23 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SOCO","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Soft Computing Models in Industrial and Environmental Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bilbao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"socomoin2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2021.sococonference.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}