{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:00:57Z","timestamp":1765310457863,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372387,62402402,61802053"],"award-info":[{"award-number":["62372387,62402402,61802053"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","award":["2024NSFSC0508"],"award-info":[{"award-number":["2024NSFSC0508"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"name":"pecial Research Funding under Yibin Municipal-University Dual Agreement","award":["YBSCXY2024010012,YBSCXY2024010006"],"award-info":[{"award-number":["YBSCXY2024010012,YBSCXY2024010006"]}]},{"name":"Fund of National Laboratory on Adaptive Optics, China","award":["FNLAO-24-ZD-O02"],"award-info":[{"award-number":["FNLAO-24-ZD-O02"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755158","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"7835-7843","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Latent Interactiveness Field for Non-Contact Human Object Interaction Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5569-4255","authenticated-orcid":false,"given":"Xiang","family":"Huang","sequence":"first","affiliation":[{"name":"Southwest Jiaotong University, Chengdu, Sichuan, China and Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, Sichuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3494-8062","authenticated-orcid":false,"given":"Ao","family":"Luo","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University, Chengdu, Sichuan, China and Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, Sichuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8322-8558","authenticated-orcid":false,"given":"Xiao","family":"Wu","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University, Chengdu, Sichuan, China and Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, Sichuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4083-5155","authenticated-orcid":false,"given":"Zhaoquan","family":"Yuan","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University, Chengdu, Sichuan, China and Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, Sichuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104617"},{"volume-title":"End-to-End Object Detection with Transformers","author":"Carion Nicolas","key":"e_1_3_2_1_2_1","unstructured":"Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. 2020. End-to-End Object Detection with Transformers. In ECCV. Springer International Publishing, Glasgow, 213-229."},{"key":"e_1_3_2_1_3_1","first-page":"1017","article-title":"HICO: A Benchmark for Recognizing Human-Object Interactions in Images. In ICCV. IEEE, Santiago","author":"Chao Yu-Wei","year":"2015","unstructured":"Yu-Wei Chao, Zhan Wang, Yugeng He, Jiaxuan Wang, and Jia Deng. 2015. HICO: A Benchmark for Recognizing Human-Object Interactions in Images. In ICCV. IEEE, Santiago, Chile, 1017-1025.","journal-title":"Chile"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.23919\/MVA57639.2023.10215534"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104091"},{"key":"e_1_3_2_1_6_1","first-page":"9000","article-title":"Reformulating HOI Detection as Adaptive Set Prediction. In CVPR. IEEE, Nashville","author":"Chen Mingfei","year":"2021","unstructured":"Mingfei Chen, Yue Liao, Si Liu, Zhiyuan Chen, Fei Wang, and Chen Qian. 2021. Reformulating HOI Detection as Adaptive Set Prediction. In CVPR. IEEE, Nashville, TN, USA, 9000-9009.","journal-title":"TN, USA"},{"volume-title":"Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation","author":"Chen Mu","key":"e_1_3_2_1_7_1","unstructured":"Mu Chen, Zhedong Zheng, and Yi Yang. 2024b. Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation. In ACM MM. Association for Computing Machinery, Melbourne, Australia, 399-408."},{"key":"e_1_3_2_1_8_1","volume-title":"iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection. CoRR","author":"Gao Chen","year":"2018","unstructured":"Chen Gao, Yuliang Zou, and Jia-Bin Huang. 2018. iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection. CoRR, Vol. abs\/1808.10437 (2018), 1-13."},{"key":"e_1_3_2_1_9_1","volume-title":"Visual semantic role labeling. arXiv preprint arXiv:1505.04474","author":"Gupta Saurabh","year":"2015","unstructured":"Saurabh Gupta and Jitendra Malik. 2015. Visual semantic role labeling. arXiv preprint arXiv:1505.04474, Vol. arXiv:1505.04474 (2015), 1-11."},{"volume-title":"Domain-Specific Conditional Jigsaw Adaptation for Enhancing transferability and Discriminability","author":"He Qi","key":"e_1_3_2_1_10_1","unstructured":"Qi He, Zhaoquan Yuan, Xiao Wu, and Jun-Yan He. 2022. Domain-Specific Conditional Jigsaw Adaptation for Enhancing transferability and Discriminability. In ACM MM. Association for Computing Machinery, Lisbon, Portugal, 6327-6336."},{"key":"e_1_3_2_1_11_1","first-page":"495","article-title":"Affordance Transfer Learning for Human-Object Interaction Detection. In CVPR. IEEE, Nashville","author":"Hou Zhi","year":"2021","unstructured":"Zhi Hou, Baosheng Yu, Yu Qiao, Xiaojiang Peng, and Dacheng Tao. 2021a. Affordance Transfer Learning for Human-Object Interaction Detection. In CVPR. IEEE, Nashville, TN, USA, 495-504.","journal-title":"TN, USA"},{"key":"e_1_3_2_1_12_1","first-page":"14641","article-title":"Detecting Human-Object Interaction via Fabricated Compositional Learning. In CVPR. IEEE, Nashville","author":"Hou Zhi","year":"2021","unstructured":"Zhi Hou, Baosheng Yu, Yu Qiao, Xiaojiang Peng, and Dacheng Tao. 2021b. Detecting Human-Object Interaction via Fabricated Compositional Learning. In CVPR. IEEE, Nashville, TN, USA, 14641-14650.","journal-title":"TN, USA"},{"key":"e_1_3_2_1_13_1","first-page":"2925","article-title":"Relational Context Learning for Human-Object Interaction Detection. In CVPR. IEEE, Vancouver, BC","author":"Kim Sanghyun","year":"2023","unstructured":"Sanghyun Kim, Deunsol Jung, and Minsu Cho. 2023. Relational Context Learning for Human-Object Interaction Detection. In CVPR. IEEE, Vancouver, BC, Canada, 2925-2934.","journal-title":"Canada"},{"key":"e_1_3_2_1_14_1","first-page":"1","article-title":"Neural-logic human-object interaction detection","volume":"36","author":"Li Liulei","year":"2024","unstructured":"Liulei Li, Jianan Wei, Wenguan Wang, and Yi Yang. 2024. Neural-logic human-object interaction detection. NeurIPS, Vol. 36 (2024), 1-14.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_15_1","first-page":"5011","volume-title":"NeurIPS","volume":"33","author":"Li Yong-Lu","year":"2020","unstructured":"Yong-Lu Li, Xinpeng Liu, Xiaoqian Wu, Yizhuo Li, and Cewu Lu. 2020. HOI Analysis: Integrating and Decomposing Human-Object Interaction. In NeurIPS, Vol. 33. Curran Associates, Inc., Vancouver, BC, Canada, 5011-5022."},{"key":"e_1_3_2_1_16_1","volume-title":"PPDM: Parallel Point Detection and Matching for Real-Time Human-Object Interaction Detection","author":"Liao Yue","year":"2020","unstructured":"Yue Liao, Si Liu, Fei Wang, Yanjie Chen, Chen Qian, and Jiashi Feng. 2020. PPDM: Parallel Point Detection and Matching for Real-Time Human-Object Interaction Detection. In CVPR. IEEE, Seattle, WA, USA, 479-487."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"e_1_3_2_1_18_1","first-page":"964","article-title":"Ernet: An efficient and reliable human-object interaction detection network","volume":"32","author":"Tistarelli Massimo","year":"2023","unstructured":"JunYi Lim, Vishnu Monn Baskaran, Joanne Mun-Yee Lim, KokSheik Wong, John See, and Massimo Tistarelli. 2023. Ernet: An efficient and reliable human-object interaction detection network. TIP, Vol. 32 (2023), 964-979.","journal-title":"TIP"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01948"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3284380"},{"key":"e_1_3_2_1_21_1","first-page":"2415","article-title":"FGAHOI","volume":"46","author":"Ma Shuailei","year":"2024","unstructured":"Shuailei Ma, Yuefeng Wang, Shanze Wang, and Ying Wei. 2024. FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection. TPAMI, Vol. 46, 4 (2024), 2415-2429.","journal-title":"Fine-Grained Anchors for Human-Object Interaction Detection. TPAMI"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3118077"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICESC60852.2024.10689737"},{"key":"e_1_3_2_1_24_1","volume-title":"Viplo: Vision transformer based pose-conditioned self-loop graph for human-object interaction detection","author":"Park Jeeseung","year":"2023","unstructured":"Jeeseung Park, Jin-Woo Park, and Jong-Seok Lee. 2023. Viplo: Vision transformer based pose-conditioned self-loop graph for human-object interaction detection. In CVPR. IEEE, Vancouver, BC, Canada, 17152-17162."},{"volume-title":"Learning human-object interactions by graph parsing neural networks","author":"Qi Siyuan","key":"e_1_3_2_1_25_1","unstructured":"Siyuan Qi, Wenguan Wang, Baoxiong Jia, Jianbing Shen, and Song-Chun Zhu. 2018. Learning human-object interactions by graph parsing neural networks. In ECCV. Springer International Publishing, Munich, Germany, 401-417."},{"key":"e_1_3_2_1_26_1","first-page":"10405","article-title":"QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information. In CVPR. IEEE, Nashville","author":"Tamura Masato","year":"2021","unstructured":"Masato Tamura, Hiroki Ohashi, and Tomoaki Yoshinaga. 2021. QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information. In CVPR. IEEE, Nashville, TN, USA, 10405-10414.","journal-title":"TN, USA"},{"key":"e_1_3_2_1_27_1","volume-title":"Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows","author":"Tu Danyang","year":"2022","unstructured":"Danyang Tu, Xiongkuo Min, Huiyu Duan, Guodong Guo, Guangtao Zhai, and Wei Shen. 2022. Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows. In ECCV. Springer, Springer International Publishing, Tel-Aviv, 87-103."},{"key":"e_1_3_2_1_28_1","first-page":"21614","article-title":"Agglomerative Transformer for Human-Object Interaction Detection. In ICCV. IEEE, Paris","author":"Tu Danyang","year":"2023","unstructured":"Danyang Tu, Wei Sun, Guangtao Zhai, and Wei Shen. 2023. Agglomerative Transformer for Human-Object Interaction Detection. In ICCV. IEEE, Paris, France, 21614-21624.","journal-title":"France"},{"key":"e_1_3_2_1_29_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In NeurIPS, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc., Long Beach, CA, USA, 11."},{"volume-title":"Distance Matters in Human-Object Interaction Detection","author":"Wang Guangzhi","key":"e_1_3_2_1_30_1","unstructured":"Guangzhi Wang, Yangyang Guo, Yongkang Wong, and Mohan Kankanhalli. 2022. Distance Matters in Human-Object Interaction Detection. In ACM MM. Association for Computing Machinery, Lisbon, Portugal, 4546-4554."},{"key":"e_1_3_2_1_31_1","first-page":"1","article-title":"Learning Human-Object Interaction Detection Using Interaction Points. In CVPR. IEEE, Seattle","author":"Wang Tiancai","year":"2020","unstructured":"Tiancai Wang, Tong Yang, Martin Danelljan, Fahad Shahbaz Khan, Xiangyu Zhang, and Jian Sun. 2020. Learning Human-Object Interaction Detection Using Interaction Points. In CVPR. IEEE, Seattle, WA, USA, 1-10.","journal-title":"WA, USA"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-05324-1"},{"key":"e_1_3_2_1_33_1","first-page":"15275","article-title":"Category query learning for human-object interaction classification. In CVPR. IEEE, Vancouver, BC","author":"Xie Chi","year":"2023","unstructured":"Chi Xie, Fangao Zeng, Yue Hu, Shuang Liang, and Yichen Wei. 2023. Category query learning for human-object interaction classification. In CVPR. IEEE, Vancouver, BC, Canada, 15275-15284.","journal-title":"Canada"},{"key":"e_1_3_2_1_34_1","first-page":"11097","article-title":"CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction. In ICCV. IEEE, Montreal, QC","author":"Yang Lixin","year":"2021","unstructured":"Lixin Yang, Xinyu Zhan, Kailin Li, Wenqiang Xu, Jiefeng Li, and Cewu Lu. 2021. CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction. In ICCV. IEEE, Montreal, QC, Canada, 11097-11106.","journal-title":"Canada"},{"key":"e_1_3_2_1_35_1","first-page":"1","article-title":"Mining the Benefits of Two-stage and One-stage HOI Detection","volume":"34","author":"Zhang Aixi","year":"2021","unstructured":"Aixi Zhang, Yue Liao, Si Liu, Miao Lu, Yongliang Wang, Chen Gao, and Xiaobo Li. 2021. Mining the Benefits of Two-stage and One-stage HOI Detection. NeurIPS, Vol. 34 (2021), 1-12.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01947"},{"key":"e_1_3_2_1_37_1","first-page":"10411","article-title":"Exploring Predicate Visual Context in Detecting of Human-Object Interactions. In ICCV. IEEE, Paris","author":"Zhang Frederic Z","year":"2023","unstructured":"Frederic Z Zhang, Yuhui Yuan, Dylan Campbell, Zhuoyao Zhong, and Stephen Gould. 2023. Exploring Predicate Visual Context in Detecting of Human-Object Interactions. In ICCV. IEEE, Paris, France, 10411-10421.","journal-title":"France"},{"key":"e_1_3_2_1_38_1","first-page":"13234","article-title":"Glance and gaze: Inferring action-aware points for one-stage human-object interaction detection. In CVPR. IEEE, Nashville","author":"Zhong Xubin","year":"2021","unstructured":"Xubin Zhong, Xian Qu, Changxing Ding, and Dacheng Tao. 2021. Glance and gaze: Inferring action-aware points for one-stage human-object interaction detection. In CVPR. IEEE, Nashville, TN, USA, 13234-13243.","journal-title":"TN, USA"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01896"},{"volume-title":"Learning from Easy to Hard Pairs: Multi-step Reasoning Network for Human-Object Interaction Detection","author":"Zhou Yuchen","key":"e_1_3_2_1_40_1","unstructured":"Yuchen Zhou, Guang Tan, Mengtang Li, and Chao Gou. 2023. Learning from Easy to Hard Pairs: Multi-step Reasoning Network for Human-Object Interaction Detection. In ACM MM. Association for Computing Machinery, Ottawa, Canada, 4368-4377."},{"key":"e_1_3_2_1_41_1","first-page":"1","article-title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection. In ICLR. http:\/\/OpenReview.net","author":"Zhu Xizhou","year":"2021","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2021. Deformable DETR: Deformable Transformers for End-to-End Object Detection. In ICLR. http:\/\/OpenReview.net, Austria, 1-16.","journal-title":"Austria"},{"key":"e_1_3_2_1_42_1","first-page":"11820","article-title":"End-to-End Human Object Interaction Detection with HOI Transformer. In CVPR. IEEE, Nashville","author":"Zou Cheng","year":"2021","unstructured":"Cheng Zou, Bohan Wang, Yue Hu, Junqi Liu, Qian Wu, Yu Zhao, Boxun Li, Chenguang Zhang, Chi Zhang, Yichen Wei, and Jian Sun. 2021. End-to-End Human Object Interaction Detection with HOI Transformer. In CVPR. IEEE, Nashville, TN, USA, 11820-11829.","journal-title":"TN, USA"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755158","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:58:44Z","timestamp":1765310324000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755158"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":42,"alternative-id":["10.1145\/3746027.3755158","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755158","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}