{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T10:04:52Z","timestamp":1770545092322,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":81,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T00:00:00Z","timestamp":1745539200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSFC","award":["U22A2032"],"award-info":[{"award-number":["U22A2032"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,26]]},"DOI":"10.1145\/3706598.3713741","type":"proceedings-article","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T04:35:25Z","timestamp":1745469325000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["ProTAL: A Drag-and-Link Video Programming Framework for Temporal Action Localization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1035-4347","authenticated-orcid":false,"given":"Yuchen","family":"He","sequence":"first","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9833-7741","authenticated-orcid":false,"given":"Jianbing","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Software Technology, Zhejiang University, Ningbo, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8868-5101","authenticated-orcid":false,"given":"Liqi","family":"Cheng","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1662-1840","authenticated-orcid":false,"given":"Lingyu","family":"Meng","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9057-8353","authenticated-orcid":false,"given":"Dazhen","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Software Technology, Zhejiang University, Ningbo, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1119-3237","authenticated-orcid":false,"given":"Yingcai","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, Zhejiang, China"}]}],"member":"320","published-online":{"date-parts":[[2025,4,25]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","unstructured":"Maya Antoun and Daniel Asmar. 2023. Human object interaction detection: Design and survey. Image and Vision Computing 130 C (2023) 104617. 10.1016\/J.IMAVIS.2022.104617","DOI":"10.1016\/J.IMAVIS.2022.104617"},{"key":"e_1_3_3_3_3_2","first-page":"273","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"Bach Stephen\u00a0H.","year":"2017","unstructured":"Stephen\u00a0H. Bach, Bryan\u00a0Dawei He, Alexander Ratner, and Christopher R\u00e9. 2017. Learning the Structure of Generative Models without Labeled Data. In Proceedings of the 34th International Conference on Machine Learning. 273\u2013282."},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","unstructured":"Djamila\u00a0Romaissa Beddiar Brahim Nini Mohammad Sabokrou and Abdenour Hadid. 2020. Vision-based human activity recognition: a survey. Multimedia Tools and Applications 79 41-42 (2020) 30509\u201330555. 10.1007\/S11042-020-09004-3","DOI":"10.1007\/S11042-020-09004-3"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00124"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","unstructured":"Changjian Chen Jiashu Chen Weikai Yang Haoze Wang Johannes Knittel Xibin Zhao Steffen Koch Thomas Ertl and Shixia Liu. 2024. Enhancing Single-Frame Supervision for Better Temporal Action Localization. IEEE Transactions on Visualization and Computer Graphics 30 6 (2024) 2903\u20132915. 10.1109\/TVCG.2024.3388521","DOI":"10.1109\/TVCG.2024.3388521"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","unstructured":"Lu Chen Sida Peng and Xiaowei Zhou. 2021. Towards efficient and photorealistic 3D human reconstruction: A brief survey. Visual Informatics 5 4 (2021) 11\u201319. 10.1016\/j.visinf.2021.10.003","DOI":"10.1016\/j.visinf.2021.10.003"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442442.3458602"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","unstructured":"L.\u00a0Minh Dang Kyungbok Min Hanxiang Wang Md.\u00a0Jalil Piran Cheol\u00a0Hee Lee and Hyeonjoon Moon. 2020. Sensor-based and vision-based human activity recognition: A comprehensive survey. Pattern Recognition 108 (2020) 107561. 10.1016\/J.PATCOG.2020.107561","DOI":"10.1016\/J.PATCOG.2020.107561"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445431"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_47"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020.FINDINGS-EMNLP.181"},{"key":"e_1_3_3_3_15_2","first-page":"961","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Victor\u00a0Escorcia Bernard\u00a0Ghanem Fabian Caba\u00a0Heilbron,","year":"2015","unstructured":"Bernard\u00a0Ghanem Fabian Caba\u00a0Heilbron, Victor\u00a0Escorcia and Juan\u00a0Carlos Niebles. 2015. ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 961\u2013970."},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00334"},{"key":"e_1_3_3_3_17_2","unstructured":"Yutong Feng Jianwen Jiang Ziyuan Huang Zhiwu Qing Xiang Wang Shiwei Zhang Mingqian Tang and Yue Gao. 2021. Relation Modeling in Spatio-Temporal Action Localization."},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.52"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","unstructured":"Dongming Han Jiacheng Pan Xiaodong Zhao and Wei Chen. 2021. NetV.js: A web-based library for high-efficiency visualization of large-scale graphs and networks. Visual Informatics 5 1 (2021) 61\u201366. 10.1016\/j.visinf.2021.01.002","DOI":"10.1016\/j.visinf.2021.01.002"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","unstructured":"Jianben He Xingbo Wang Kam\u00a0Kwai Wong Xijie Huang Changjian Chen Zixin Chen Fengjie Wang Min Zhu and Huamin Qu. 2024. VideoPro: A Visual Analytics Approach for Interactive Video Programming. 30 1 (2024) 87\u201397. 10.1109\/TVCG.2023.3326586","DOI":"10.1109\/TVCG.2023.3326586"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","unstructured":"Md\u00a0Naimul Hoque Wenbin He Arvind\u00a0Kumar Shekar Liang Gou and Liu Ren. 2023. Visual concept programming: A visual analytics approach to injecting human intelligence at scale. IEEE Transactions on Visualization and Computer Graphics 29 1 (2023) 74\u201383. 10.1109\/TVCG.2022.3209466","DOI":"10.1109\/TVCG.2022.3209466"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"crossref","unstructured":"Edwin\u00a0L Hutchins James\u00a0D Hollan and Donald\u00a0A Norman. 1985. Direct manipulation interfaces. Human\u2013computer interaction 1 4 (1985) 311\u2013338.","DOI":"10.1207\/s15327051hci0104_2"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","unstructured":"Tao Jiang Peng Lu Li Zhang Ningsheng Ma Rui Han Chengqi Lyu Yining Li and Kai Chen. 2023. RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose. 10.48550\/ARXIV.2303.07399","DOI":"10.48550\/ARXIV.2303.07399"},{"key":"e_1_3_3_3_26_2","unstructured":"Y.-G. Jiang J. Liu A. Roshan\u00a0Zamir G. Toderici I. Laptev M. Shah and R. Sukthankar. 2014. \"THUMOS Challenge: Action Recognition with a Large Number of Classes\". http:\/\/crcv.ucf.edu\/THUMOS14\/."},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","unstructured":"Pushpajit Khaire and Praveen Kumar. 2022. Deep learning and RGB-D based human action human-human and human-object interaction recognition: A survey. Journal of Visual Communication and Image Representation 86 C (2022) 103531. 10.1016\/J.JVCIR.2022.103531","DOI":"10.1016\/J.JVCIR.2022.103531"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","unstructured":"Bumsoo Kim Junhyun Lee Jaewoo Kang Eun-Sol Kim and Hyunwoo\u00a0J. Kim. 2021. HOTR: End-to-End Human-Object Interaction Detection with Transformers. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021) 74\u201383. 10.1109\/CVPR46437.2021.00014","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","unstructured":"Kuno Kurzhals Marcel Hlawatsch Christof Seeger and Daniel Weiskopf. 2017. Visual Analytics for Mobile Eye Tracking. IEEE Transactions on Visualization and Computer Graphics 23 1 (2017) 301\u2013310. 10.1109\/TVCG.2016.2598695","DOI":"10.1109\/TVCG.2016.2598695"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00826"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","unstructured":"Zhengyang Li Jie Li and Xinying Ma. 2025. Representing multi-dimensional data as graph to visualize and analyze subset communities. Journal of Visualization (2025). 10.1007\/s12650-025-01045-w","DOI":"10.1007\/s12650-025-01045-w"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","unstructured":"Qinying Liu Zilei Wang and Shenghai Rong. 2023. Improve Temporal Action Proposals using Hierarchical Context. Pattern Recognition 140 (2023) 109560. 10.1016\/j.patcog.2023.109560","DOI":"10.1016\/j.patcog.2023.109560"},{"key":"e_1_3_3_3_33_2","unstructured":"Shilong Liu Zhaoyang Zeng Tianhe Ren Feng Li Hao Zhang Jie Yang Chunyuan Li Jianwei Yang Hang Su Jun Zhu et\u00a0al. 2023. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.05499 (2023)."},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"crossref","unstructured":"Shuming Liu Chen-Lin Zhang Chen Zhao and Bernard Ghanem. 2023. End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames. arXiv preprint arXiv:2311.17241 (2023) 18591\u201318601.","DOI":"10.1109\/CVPR52733.2024.01759"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00611"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","unstructured":"Ziao Liu Xiao Xie Moqi He Wenshuo Zhao Yihong Wu Liqi Cheng Hui Zhang and Yingcai Wu. 2024. Smartboard: Visual Exploration of Team Tactics with LLM Agent. IEEE Transactions on Visualization and Computer Graphics (2024) 1\u201311. 10.1109\/TVCG.2024.3456200","DOI":"10.1109\/TVCG.2024.3456200"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","unstructured":"J\u00falio\u00a0Castro Lopes and Rui\u00a0Pedro Lopes. 2024. Computer Vision in Augmented Virtual Mixed and Extended Reality environments\u2014A bibliometric review. Visual Informatics 8 4 (2024) 13\u201322. 10.1016\/j.visinf.2024.11.002","DOI":"10.1016\/j.visinf.2024.11.002"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_25"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","unstructured":"Ayana Murakami and Takayuki Itoh. 2025. Flexible optimization of hierarchical graph layout by genetic algorithm with various conditions. Journal of Visualization 28 1 (2025) 181\u2013204. 10.1007\/s12650-024-01018-5","DOI":"10.1007\/s12650-024-01018-5"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_38"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00706"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00560"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300293"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00053"},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412060"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00069"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"publisher","unstructured":"Alexander Ratner Stephen\u00a0H. Bach Henry Ehrenberg Jason Fries Sen Wu and Christopher R\u00e9. 2017. Snorkel: Rapid Training Data Creation with Weak Supervision. Proceedings of the VLDB Endowment 11 3 (2017) 269\u2013282. 10.14778\/3157794.3157797","DOI":"10.14778\/3157794.3157797"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014763"},{"key":"e_1_3_3_3_49_2","volume-title":"Advances in Neural Information Processing Systems","author":"Ratner Alexander\u00a0J","year":"2016","unstructured":"Alexander\u00a0J Ratner, Christopher\u00a0M De\u00a0Sa, Sen Wu, Daniel Selsam, and Christopher R\u00e9. 2016. Data Programming: Creating Large Training Sets, Quickly. In Advances in Neural Information Processing Systems , Vol.\u00a029."},{"key":"e_1_3_3_3_50_2","unstructured":"Tianhe Ren Shilong Liu Ailing Zeng Jing Lin Kunchang Li He Cao Jiayu Chen Xinyu Huang Yukang Chen Feng Yan Zhaoyang Zeng Hao Zhang Feng Li Jie Yang Hongyang Li Qing Jiang and Lei Zhang. 2024. Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks. arxiv:https:\/\/arXiv.org\/abs\/2401.14159\u00a0[cs.CV]"},{"key":"e_1_3_3_3_51_2","unstructured":"Benjamin Renoust Haolin Ren and Guy Melan\u00e7on. 2019. Animated Drag and Drop Interaction for Dynamic Multidimensional Graphs. arXiv preprint arXiv:1902.01564 (2019)."},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"e_1_3_3_3_53_2","unstructured":"Dingfeng Shi Yujie Zhong Qiong Cao Lin Ma Jia Li and Dacheng Tao. 2023. Temporal Action Localization with Enhanced Instant Discriminability. arXiv preprint arXiv:2309.05590 (2023)."},{"key":"e_1_3_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"e_1_3_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"e_1_3_3_3_56_2","doi-asserted-by":"publisher","unstructured":"Alexandros Stergiou and Ronald Poppe. 2019. Analyzing human-human interactions: A survey. Computer Vision and Image Understanding 188 C (2019) 102799. 10.1016\/J.CVIU.2019.102799","DOI":"10.1016\/J.CVIU.2019.102799"},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"publisher","unstructured":"Tan Tang Yanhong Wu Yingcai Wu Lingyun Yu and Yuhong Li. 2022. VideoModerator: A Risk-aware Framework for Multimodal Video Moderation in E-Commerce. IEEE Transactions on Visualization and Computer Graphics 28 1 (2022) 846\u2013856. 10.1109\/TVCG.2021.3114781","DOI":"10.1109\/TVCG.2021.3114781"},{"key":"e_1_3_3_3_58_2","first-page":"10078","volume-title":"Advances in Neural Information Processing Systems","author":"Tong Zhan","year":"2022","unstructured":"Zhan Tong, Yibing Song, Jue Wang, and Limin Wang. 2022. VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training. In Advances in Neural Information Processing Systems. 10078\u201310093."},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_3_3_60_2","first-page":"6418","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Varma Paroma","year":"2019","unstructured":"Paroma Varma, Frederic Sala, Ann He, Alexander Ratner, and Christopher R\u00e9. 2019. Learning Dependency Structures for Weak Supervision Models. In Proceedings of the 36th International Conference on Machine Learning. 6418\u20136427."},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"publisher","unstructured":"Binglu Wang Yongqiang Zhao Le Yang Teng Long and Xuelong Li. 2024. Temporal Action Localization in the Deep Learning Era: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 46 4 (2024) 2171\u20132190. 10.1109\/TPAMI.2023.3330794","DOI":"10.1109\/TPAMI.2023.3330794"},{"key":"e_1_3_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.678"},{"key":"e_1_3_3_3_63_2","doi-asserted-by":"publisher","unstructured":"Limin Wang Yuanjun Xiong Zhe Wang Yu Qiao Dahua Lin Xiaoou Tang and Luc Van\u00a0Gool. 2019. Temporal Segment Networks for Action Recognition in Videos. IEEE Transactions on Pattern Analysis and Machine Intelligence 41 11 (2019) 2740\u20132755. 10.1109\/TPAMI.2018.2868668","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"e_1_3_3_3_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"e_1_3_3_3_65_2","doi-asserted-by":"publisher","unstructured":"Yanyan Wang Zhanning Bai Zhifeng Lin Xiaoqing Dong Yingchaojie Feng Jiacheng Pan and Wei Chen. 2021. G6: A web-based library for graph visualization. Visual Informatics 5 4 (2021) 49\u201355. 10.1016\/j.visinf.2021.12.003","DOI":"10.1016\/j.visinf.2021.12.003"},{"key":"e_1_3_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00212"},{"key":"e_1_3_3_3_67_2","first-page":"38571","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Xu Yufei","year":"2024","unstructured":"Yufei Xu, Jing Zhang, Qiming Zhang, and Dacheng Tao. 2024. ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation. In Proceedings of the 36th International Conference on Neural Information Processing Systems. 38571\u201338584."},{"key":"e_1_3_3_3_68_2","doi-asserted-by":"publisher","unstructured":"Katsu Yamane and Yoshihiko Nakamura. 2003. Natural Motion Animation through Constraining and Deconstraining at Will. IEEE Trans. Vis. Comput. Graph. 9 3 (2003) 352\u2013360. 10.1109\/TVCG.2003.1207443","DOI":"10.1109\/TVCG.2003.1207443"},{"key":"e_1_3_3_3_69_2","doi-asserted-by":"publisher","unstructured":"Sijie Yan Yuanjun Xiong and Dahua Lin. 2018. Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition. Proceedings of AAAI Conference on Artificial Intelligence 7444\u20137452. 10.1609\/aaai.v32i1.12328","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_3_3_3_70_2","doi-asserted-by":"publisher","unstructured":"Le Yang Junwei Han Tao Zhao Tianwei Lin Dingwen Zhang and Jianxin Chen. 2022. Background-Click Supervision for Temporal Action Localization. IEEE Transactions on Pattern Analysis and Machine Intelligence 44 12 (2022) 9814\u20139829. 10.1109\/TPAMI.2021.3132058","DOI":"10.1109\/TPAMI.2021.3132058"},{"key":"e_1_3_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"e_1_3_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"e_1_3_3_3_73_2","doi-asserted-by":"publisher","unstructured":"Runhao Zeng Wenbing Huang Mingkui Tan Yu Rong P. Zhao Junzhou Huang and Chuang Gan. 2022. Graph Convolutional Module for Temporal Action Localization in Videos. IEEE Transactions on Pattern Analysis and Machine Intelligence 44 10 (2022) 6209\u20136223. 10.1109\/TPAMI.2021.3090167","DOI":"10.1109\/TPAMI.2021.3090167"},{"key":"e_1_3_3_3_74_2","unstructured":"Daochen Zha Zaid\u00a0Pervaiz Bhat Kwei-Herng Lai Fan Yang Zhimeng Jiang Shaochen Zhong and Xia Hu. 2023. Data-centric Artificial Intelligence: A Survey. arXiv preprint arXiv:2303.10158 (2023)."},{"key":"e_1_3_3_3_75_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"e_1_3_3_3_76_2","doi-asserted-by":"publisher","unstructured":"Yue Zhang Zhenyuan Wang Jinhui Zhang Guihua Shan and Dong Tian. 2023. A survey of immersive visualization: Focus on perception and interaction. Visual Informatics 7 4 (2023) 22\u201335. 10.1016\/j.visinf.2023.10.003","DOI":"10.1016\/j.visinf.2023.10.003"},{"key":"e_1_3_3_3_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01340"},{"key":"e_1_3_3_3_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01340"},{"key":"e_1_3_3_3_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"e_1_3_3_3_80_2","doi-asserted-by":"publisher","unstructured":"Yue Zhao Yuanjun Xiong Limin Wang Zhirong Wu Xiaoou Tang and Dahua Lin. 2020. Temporal Action Detection with Structured Segment Networks. International Journal of Computer Vision 128 1 (2020) 74\u201395. 10.1007\/S11263-019-01211-2","DOI":"10.1007\/S11263-019-01211-2"},{"key":"e_1_3_3_3_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3641927"},{"key":"e_1_3_3_3_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01165"}],"event":{"name":"CHI 2025: CHI Conference on Human Factors in Computing Systems","location":"Yokohama Japan","acronym":"CHI '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706598.3713741","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706598.3713741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:57:19Z","timestamp":1750298239000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706598.3713741"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,25]]},"references-count":81,"alternative-id":["10.1145\/3706598.3713741","10.1145\/3706598"],"URL":"https:\/\/doi.org\/10.1145\/3706598.3713741","relation":{},"subject":[],"published":{"date-parts":[[2025,4,25]]},"assertion":[{"value":"2025-04-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}