{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T13:43:58Z","timestamp":1779111838308,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,8]],"date-time":"2020-06-08T00:00:00Z","timestamp":1591574400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,8]]},"DOI":"10.1145\/3379175.3391712","type":"proceedings-article","created":{"date-parts":[[2020,6,6]],"date-time":"2020-06-06T04:12:53Z","timestamp":1591416773000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Cooking Activity Recognition in Egocentric Videos with a Hand Mask Image Branch in the Multi-stream CNN"],"prefix":"10.1145","author":[{"given":"Shinya","family":"Michibata","sequence":"first","affiliation":[{"name":"Osaka Prefecture University, Osaka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katsufumi","family":"Inoue","sequence":"additional","affiliation":[{"name":"Osaka Prefecture University, Osaka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michifumi","family":"Yoshioka","sequence":"additional","affiliation":[{"name":"Osaka Prefecture University, Osaka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsushi","family":"Hashimoto","sequence":"additional","affiliation":[{"name":"OMRON SINIC X Corporation, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,6,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.226"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Gunnar Farneb\u00e4ck. 2003. Two-Frame Motion Estimation Based on Polynomial Expansion. Image analysis 2749 363--370.  Gunnar Farneb\u00e4ck. 2003. Two-Frame Motion Estimation Based on Polynomial Expansion. Image analysis 2749 363--370.","DOI":"10.1007\/3-540-45103-X_50"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01096"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00622"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceeding of the Asian Conference on Information Systems. 14--21","author":"Inoue Katsufumi","year":"2016","unstructured":"Katsufumi Inoue , Misa Ono , and Michifumi Yoshioka . 2016 . Hand Detection and Cooking Activities Recognition in Egocentric Videos . In Proceeding of the Asian Conference on Information Systems. 14--21 . Katsufumi Inoue, Misa Ono, and Michifumi Yoshioka. 2016. Hand Detection and Cooking Activities Recognition in Egocentric Videos. In Proceeding of the Asian Conference on Information Systems. 14--21."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351020"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2901707"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceeding of the British Machine Vision Conference.","author":"Nekrasov Vladimir","year":"2018","unstructured":"Vladimir Nekrasov , Chunhua Shen , and Ian Reid . 2018 . Light-Weight RefineNet for Real-Time Semantic Segmentation . In Proceeding of the British Machine Vision Conference. Vladimir Nekrasov, Chunhua Shen, and Ian Reid. 2018. Light-Weight RefineNet for Real-Time Semantic Segmentation. In Proceeding of the British Machine Vision Conference."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the Advances in neural information processing systems. 568--576","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014 . Two-stream convolutional networks for action recognition in videos . In Proceedings of the Advances in neural information processing systems. 568--576 . Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. In Proceedings of the Advances in neural information processing systems. 568--576."},{"key":"e_1_3_2_1_15_1","volume-title":"Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition. 2620--2628","author":"Singh Suriya","unstructured":"Suriya Singh , Chetan Arora , and C. Jawahar . 2016. First Person Action Recognition Using Deep Learned Descriptors . In Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition. 2620--2628 . Suriya Singh, Chetan Arora, and C. Jawahar. 2016. First Person Action Recognition Using Deep Learned Descriptors. In Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition. 2620--2628."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the IEEE International Conference on Image Processing. 3410--3414","author":"Tang Yansong","year":"2017","unstructured":"Yansong Tang , Yi Tian , Jiwen Lu , Jianjiang Feng , and Jie Zhou . 2017 . Actionrecognition in rgb-d egocentric videos . In Proceedings of the IEEE International Conference on Image Processing. 3410--3414 . Yansong Tang, Yi Tian, Jiwen Lu, Jianjiang Feng, and Jie Zhou. 2017. Actionrecognition in rgb-d egocentric videos. In Proceedings of the IEEE International Conference on Image Processing. 3410--3414."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230519.3230584"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4710--4719","author":"Urooj Aisha","year":"2018","unstructured":"Aisha Urooj and Ali Borji . 2018 . Analysis of hand segmentation in the wild . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4710--4719 . Aisha Urooj and Ali Borji. 2018. Analysis of hand segmentation in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4710--4719."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.210"}],"event":{"name":"ICMR '20: International Conference on Multimedia Retrieval","location":"Dublin Ireland","acronym":"ICMR '20","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 12th Workshop on Multimedia for Cooking and Eating Activities"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3379175.3391712","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3379175.3391712","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:02Z","timestamp":1750200062000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3379175.3391712"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,8]]},"references-count":19,"alternative-id":["10.1145\/3379175.3391712","10.1145\/3379175"],"URL":"https:\/\/doi.org\/10.1145\/3379175.3391712","relation":{},"subject":[],"published":{"date-parts":[[2020,6,8]]},"assertion":[{"value":"2020-06-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}