{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:22:52Z","timestamp":1743121372459,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819787012"},{"type":"electronic","value":"9789819787029"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-8702-9_14","type":"book-chapter","created":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T14:47:14Z","timestamp":1738939634000},"page":"201-215","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Egocentric View Hand Action Recognition by\u00a0Leveraging Hand Surface and\u00a0Hand Grasp Type"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2679-4961","authenticated-orcid":false,"given":"DongYoon","family":"Seo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5454-3404","authenticated-orcid":false,"given":"Hyunggun","family":"Chi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5872-7569","authenticated-orcid":false,"given":"Sunghee","family":"Hong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0465-3266","authenticated-orcid":false,"given":"Byoung Soo","family":"Koh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8639-5135","authenticated-orcid":false,"given":"Karthik","family":"Ramani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7349-0018","authenticated-orcid":false,"given":"Sangpil","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,8]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Aksoy, E.E., Abramov, A., W\u00f6rg\u00f6tter, F., Dellen, B.: Categorizing object-action relations from semantic scene graphs. In: 2010 IEEE International Conference on Robotics and Automation, pp. 398\u2013405. IEEE (2010)","DOI":"10.1109\/ROBOT.2010.5509319"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Baek, S., Kim, K.I., Kim, T.K.: Pushing the envelope for rgb-based dense 3d hand pose estimation via neural rendering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1067\u20131076 (2019)","DOI":"10.1109\/CVPR.2019.00116"},{"key":"14_CR3","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"14_CR4","unstructured":"Cai, M., Kitani, K.M., Sato, Y.: Understanding hand-object manipulation with grasp types and object attributes. In: Robotics: Science and Systems, vol.\u00a03. Ann Arbor, Michigan (2016)"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Chang, C.C., Chen, I.Y., Huang, Y.S.: Hand pose recognition using curvature scale space. In: Object Recognition Supported by User Interaction for Service Robots, vol.\u00a02, pp. 386\u2013389. IEEE (2002)","DOI":"10.1109\/ICPR.2002.1048320"},{"issue":"3","key":"14_CR6","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1007\/s10791-009-9110-3","volume":"13","author":"O Chapelle","year":"2010","unstructured":"Chapelle, O., Wu, M.: Gradient descent optimization of smoothed information retrieval metrics. Inf. Retrieval 13(3), 216\u2013235 (2010)","journal-title":"Inf. Retrieval"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Chen, H., Chirikjian, G.S.: Curvature: a signature for action recognition in video sequences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 858\u2013859 (2020)","DOI":"10.1109\/CVPRW50498.2020.00437"},{"issue":"3","key":"14_CR8","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1109\/70.34763","volume":"5","author":"MR Cutkosky","year":"1989","unstructured":"Cutkosky, M.R., et al.: On grasp choice, grasp models, and the design of hands for manufacturing tasks. IEEE Trans. Robot. Autom. 5(3), 269\u2013279 (1989)","journal-title":"IEEE Trans. Robot. Autom."},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Damen, D., et\u00a0al.: 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"},{"issue":"1","key":"14_CR10","first-page":"630","volume":"2015","author":"F Deboeverie","year":"2015","unstructured":"Deboeverie, F., De Geest, R., Tuytelaars, T., Veelaert, P., Philips, W.: Curvature-based human body parts segmentation in physiotherapy. Proc. VISAPP 2015(1), 630\u2013637 (2015)","journal-title":"Proc. VISAPP"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Fathi, A., Ren, X., Rehg, J.M.: Learning to recognize objects in egocentric activities. In: CVPR 2011, pp. 3281\u20133288. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"issue":"1","key":"14_CR13","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/THMS.2015.2470657","volume":"46","author":"T Feix","year":"2015","unstructured":"Feix, T., Romero, J., Schmiedmayer, H.B., Dollar, A.M., Kragic, D.: The grasp taxonomy of human grasp types. IEEE Trans. Hum.-Mach. Syst. 46(1), 66\u201377 (2015)","journal-title":"IEEE Trans. Hum.-Mach. Syst."},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Garcia-Hernando, G., Yuan, S., Baek, S., Kim, T.K.: First-person hand action benchmark with rgb-d videos and 3d hand pose annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 409\u2013419 (2018)","DOI":"10.1109\/CVPR.2018.00050"},{"key":"14_CR15","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256 (2010)"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Hu, J.F., Zheng, W.S., Lai, J., Zhang, J.: Jointly learning heterogeneous features for rgb-d activity recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5344\u20135352 (2015)","DOI":"10.1109\/CVPR.2015.7299172"},{"issue":"10","key":"14_CR18","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1109\/TPAMI.2003.1233911","volume":"25","author":"P Laskov","year":"2003","unstructured":"Laskov, P., Kambhamettu, C.: Curvature-based algorithms for nonrigid motion and correspondence estimation. IEEE Trans. Pattern Anal. Mach. Intell. 25(10), 1349\u20131354 (2003)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, M., Rehg, J.M.: In the eye of beholder: joint learning of gaze and actions in first person video. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 619\u2013635 (2018)","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Ye, Z., Rehg, J.M.: Delving into egocentric actions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 287\u2013295 (2015)","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"14_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2018.04.002","volume":"172","author":"FA Limberger","year":"2018","unstructured":"Limberger, F.A., Wilson, R.C.: Curvature-based spectral signatures for non-rigid shape retrieval. Comput. Vis. Image Underst. 172, 1\u201311 (2018)","journal-title":"Comput. Vis. Image Underst."},{"issue":"6","key":"14_CR22","doi-asserted-by":"publisher","first-page":"2368","DOI":"10.1109\/TITS.2014.2337331","volume":"15","author":"E Ohn-Bar","year":"2014","unstructured":"Ohn-Bar, E., Trivedi, M.M.: Hand gesture recognition in real time for automotive interfaces: a multimodal vision-based approach and evaluations. IEEE Trans. Intell. Transp. Syst. 15(6), 2368\u20132377 (2014)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Oreifej, O., Liu, Z.: Hon4d: histogram of oriented 4d normals for activity recognition from depth sequences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 716\u2013723 (2013)","DOI":"10.1109\/CVPR.2013.98"},{"key":"14_CR24","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch (2017)"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Piergiovanni, A., Ryoo, M.S.: Representation flow for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9945\u20139953 (2019)","DOI":"10.1109\/CVPR.2019.01018"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Rahmani, H., Mian, A.: 3d action recognition from novel viewpoints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1506\u20131515 (2016)","DOI":"10.1109\/CVPR.2016.167"},{"issue":"6","key":"14_CR27","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1145\/3130800.3130883","volume":"36","author":"J Romero","year":"2017","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. ACM Trans. Graph. (ToG) 36(6), 245 (2017)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Sridhar, S., Mueller, F., Zollh\u00f6fer, M., Casas, D., Oulasvirta, A., Theobalt, C.: Real-time joint tracking of a hand manipulating an object from rgb-d input. In: European Conference on Computer Vision, pp. 294\u2013310. Springer (2016)","DOI":"10.1007\/978-3-319-46475-6_19"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3d shape recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 945\u2013953 (2015)","DOI":"10.1109\/ICCV.2015.114"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Sun, S., Kuang, Z., Sheng, L., Ouyang, W., Zhang, W.: Optical flow guided feature: a fast and robust motion representation for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1390\u20131399 (2018)","DOI":"10.1109\/CVPR.2018.00151"},{"key":"14_CR31","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. IEEE (2017)","DOI":"10.1109\/ICIP.2017.8296915"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Tekin, B., Bogo, F., Pollefeys, M.: H+ o: Unified egocentric recognition of 3d hand-object poses and interactions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4511\u20134520 (2019)","DOI":"10.1109\/CVPR.2019.00464"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Wang, X., Bennamoun, M., Sohel, F., Lei, H.: Diffusion geometry derived keypoints and local descriptors for 3d deformable shape analysis. J. Circ. Syst. Comput. 2150016 (2020)","DOI":"10.1142\/S021812662150016X"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Yang, Y., Fermuller, C., Li, Y., Aloimonos, Y.: Grasp type revisited: a modern perspective on a classical feature for vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 400\u2013408 (2015)","DOI":"10.1109\/CVPR.2015.7298637"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Yi, K.M., Trulls, E., Lepetit, V., Fua, P.: Lift: learned invariant feature transform. In: European Conference on Computer Vision, pp. 467\u2013483. Springer (2016)","DOI":"10.1007\/978-3-319-46466-4_28"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, B., Wang, L., Wang, Z., Qiao, Y., Wang, H.: Real-time action recognition with enhanced motion vector cnns. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2718\u20132726 (2016)","DOI":"10.1109\/CVPR.2016.297"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Ceylan, D., Yang, J., Russell, B., Argus, M., Brox, T.: Freihand: a dataset for markerless capture of hand pose and shape from single rgb images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 813\u2013822 (2019)","DOI":"10.1109\/ICCV.2019.00090"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8702-9_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T14:47:36Z","timestamp":1738939656000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8702-9_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819787012","9789819787029"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8702-9_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"8 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPRAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jeju Island","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icprai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/brain.korea.ac.kr\/icprai2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}