{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:19:48Z","timestamp":1750220388460,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"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":[[2022,4,25]]},"DOI":"10.1145\/3477314.3507047","type":"proceedings-article","created":{"date-parts":[[2022,5,7]],"date-time":"2022-05-07T00:37:36Z","timestamp":1651883856000},"page":"49-57","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A better loss for visual-textual grounding"],"prefix":"10.1145","author":[{"given":"Davide","family":"Rigoni","sequence":"first","affiliation":[{"name":"University of Padua, Padua, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luciano","family":"Serafini","sequence":"additional","affiliation":[{"name":"Bruno Kessler Foundation, Povo, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Sperduti","sequence":"additional","affiliation":[{"name":"University of Padua, Padua, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,5,6]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Multi-Level Multimodal Common Semantic Space for Image-Phrase Grounding. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019","author":"Akbari Hassan","year":"2019","unstructured":"Hassan Akbari, Svebor Karaman, Surabhi Bhargava, Brian Chen, Carl Vondrick, and Shih-Fu Chang. 2019. Multi-Level Multimodal Common Semantic Space for Image-Phrase Grounding. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16--20, 2019. Computer Vision Foundation \/ IEEE, 12476--12486."},{"key":"e_1_3_2_1_2_1","volume-title":"Vqa: Visual question answering. In ICCV. 2425--2433.","author":"Antol Stanislaw","year":"2015","unstructured":"Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C Lawrence Zitnick, and Devi Parikh. 2015. Vqa: Visual question answering. In ICCV. 2425--2433."},{"doi-asserted-by":"crossref","unstructured":"Mohit Bajaj Lanjun Wang and Leonid Sigal. 2019. G3raphground: Graph-based language grounding. In ICCV. 4281--4290.","key":"e_1_3_2_1_3_1","DOI":"10.1109\/ICCV.2019.00438"},{"doi-asserted-by":"crossref","unstructured":"Kan Chen Jiyang Gao and Ram Nevatia. 2018. Knowledge aided consistency for weakly supervised phrase grounding. In CVPR. 4042--4050.","key":"e_1_3_2_1_4_1","DOI":"10.1109\/CVPR.2018.00425"},{"key":"e_1_3_2_1_5_1","volume-title":"Query-Guided Regression Network with Context Policy for Phrase Grounding. In IEEE International Conference on Computer Vision, ICCV 2017","author":"Chen Kan","year":"2017","unstructured":"Kan Chen, Rama Kovvuri, and Ram Nevatia. 2017. Query-Guided Regression Network with Context Policy for Phrase Grounding. In IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22--29, 2017. IEEE Computer Society, 824--832."},{"key":"e_1_3_2_1_6_1","volume-title":"Cops-Ref: A New Dataset and Task on Compositional Referring Expression Comprehension. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"Chen Zhenfang","year":"2020","unstructured":"Zhenfang Chen, Peng Wang, Lin Ma, Kwan-Yee K. Wong, and Qi Wu. 2020. Cops-Ref: A New Dataset and Task on Compositional Referring Expression Comprehension. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13--19, 2020. Computer Vision Foundation \/ IEEE, 10083--10092."},{"volume-title":"Visual Grounding via Accumulated Attention","author":"Deng Chaorui","unstructured":"Chaorui Deng, Qi Wu, Qingyao Wu, Fuyuan Hu, Fan Lyu, and Mingkui Tan. 2018. Visual Grounding via Accumulated Attention. In CVPR. IEEE Computer Society, 7746--7755.","key":"e_1_3_2_1_7_1"},{"key":"e_1_3_2_1_8_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition, CVPR","author":"Dogan Pelin","year":"2019","unstructured":"Pelin Dogan, Leonid Sigal, and Markus H. Gross. 2019. Neural Sequential Phrase Grounding (SeqGROUND). In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019. Computer Vision Foundation \/ IEEE, 4175--4184."},{"key":"e_1_3_2_1_9_1","volume-title":"Jointly Linking Visual and Textual Entity Mentions with Background Knowledge. In International Conference on Applications of Natural Language to Information Systems. Springer, 264--276","author":"Dost Shahi","year":"2020","unstructured":"Shahi Dost, Luciano Serafini, Marco Rospocher, Lamberto Ballan, and Alessandro Sperduti. 2020. Jointly Linking Visual and Textual Entity Mentions with Background Knowledge. In International Conference on Applications of Natural Language to Information Systems. Springer, 264--276."},{"volume-title":"On Visual-Textual-Knowledge Entity Linking","author":"Dost Shahi","unstructured":"Shahi Dost, Luciano Serafini, Marco Rospocher, Lamberto Ballan, and Alessandro Sperduti. 2020. On Visual-Textual-Knowledge Entity Linking. In ICSC. IEEE, 190--193.","key":"e_1_3_2_1_10_1"},{"doi-asserted-by":"crossref","unstructured":"Shahi Dost Luciano Serafini Marco Rospocher Lamberto Ballan and Alessandro Sperduti. 2020. VTKEL: a resource for visual-textual-knowledge entity linking. In ACM. 2021--2028.","key":"e_1_3_2_1_11_1","DOI":"10.1145\/3341105.3373958"},{"key":"e_1_3_2_1_12_1","volume-title":"RFIAP 2018-Congr\u00e8s Reconnaissance des Formes, Image, Apprentissage et Perception.","author":"Engilberge Martin","year":"2018","unstructured":"Martin Engilberge, Louis Chevallier, Patrick P\u00e9rez, and Matthieu Cord. 2018. Deep semantic-visual embedding with localization. In RFIAP 2018-Congr\u00e8s Reconnaissance des Formes, Image, Apprentissage et Perception."},{"unstructured":"Andrea Frome Gregory S. Corrado Jonathon Shlens Samy Bengio Jeffrey Dean Marc'Aurelio Ranzato and Tom\u00e1s Mikolov. 2013. DeViSE: A Deep Visual-Semantic Embedding Model. In NeurIPS Christopher J. C. Burges L\u00e9on Bottou Zoubin Ghahramani and Kilian Q. Weinberger (Eds.). 2121--2129.","key":"e_1_3_2_1_13_1"},{"key":"e_1_3_2_1_14_1","volume-title":"Daylen Yang, Anna Rohrbach, Trevor Darrell, and Marcus Rohrbach.","author":"Fukui Akira","year":"2016","unstructured":"Akira Fukui, Dong Huk Park, Daylen Yang, Anna Rohrbach, Trevor Darrell, and Marcus Rohrbach. 2016. Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding. In EMNLP, Jian Su, Xavier Carreras, and Kevin Duh (Eds.). The Association for Computational Linguistics, 457--468."},{"volume-title":"ECCV (Lecture Notes in Computer Science), Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (Eds.)","author":"Gupta Tanmay","unstructured":"Tanmay Gupta, Arash Vahdat, Gal Chechik, Xiaodong Yang, Jan Kautz, and Derek Hoiem. 2020. Contrastive Learning for Weakly Supervised Phrase Grounding. In ECCV (Lecture Notes in Computer Science), Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (Eds.), Vol. 12348. Springer, 752--768.","key":"e_1_3_2_1_15_1"},{"key":"e_1_3_2_1_16_1","volume-title":"Long short-term memory. Neural computation 9, 8","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780."},{"unstructured":"Ronghang Hu Huazhe Xu Marcus Rohrbach Jiashi Feng Kate Saenko and Trevor Darrell. 2016. Natural language object retrieval. In CVPR. 4555--4564.","key":"e_1_3_2_1_17_1"},{"key":"e_1_3_2_1_18_1","volume-title":"Referitgame: Referring to objects in photographs of natural scenes. In EMNLP. 787--798.","author":"Kazemzadeh Sahar","year":"2014","unstructured":"Sahar Kazemzadeh, Vicente Ordonez, Mark Matten, and Tamara Berg. 2014. Referitgame: Referring to objects in photographs of natural scenes. In EMNLP. 787--798."},{"key":"e_1_3_2_1_19_1","volume-title":"Berg","author":"Kazemzadeh Sahar","year":"2014","unstructured":"Sahar Kazemzadeh, Vicente Ordonez, Mark Matten, and Tamara L. Berg. 2014. ReferIt Game: Referring to Objects in Photographs of Natural Scenes. In EMNLP."},{"key":"e_1_3_2_1_20_1","volume-title":"Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539","author":"Kiros Ryan","year":"2014","unstructured":"Ryan Kiros, Ruslan Salakhutdinov, and Richard S Zemel. 2014. Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)."},{"key":"e_1_3_2_1_21_1","volume-title":"Fisher vectors derived from hybrid gaussian-laplacian mixture models for image annotation. arXiv preprint arXiv:1411.7399","author":"Klein Benjamin","year":"2014","unstructured":"Benjamin Klein, Guy Lev, Gil Sadeh, and Lior Wolf. 2014. Fisher vectors derived from hybrid gaussian-laplacian mixture models for image annotation. arXiv preprint arXiv:1411.7399 (2014)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_22_1","DOI":"10.1145\/3123266.3123439"},{"volume-title":"EMNLP-IJCNLP","author":"Liu Jiacheng","unstructured":"Jiacheng Liu and Julia Hockenmaier. 2019. Phrase Grounding by Soft-Label Chain Conditional Random Field. In EMNLP-IJCNLP, Kentaro Inui, Jing Jiang, Vincent Ng, and Xiaojun Wan (Eds.). Association for Computational Linguistics, 5111--5121.","key":"e_1_3_2_1_23_1"},{"key":"e_1_3_2_1_24_1","volume-title":"Ssd: Single shot multibox detector","author":"Liu Wei","year":"2016","unstructured":"Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg. 2016. Ssd: Single shot multibox detector. In ECCV. Springer, 21--37."},{"doi-asserted-by":"crossref","unstructured":"Xihui Liu Zihao Wang Jing Shao Xiaogang Wang and Hongsheng Li. 2019. Improving referring expression grounding with cross-modal attention-guided erasing. In CVPR. 1950--1959.","key":"e_1_3_2_1_25_1","DOI":"10.1109\/CVPR.2019.00205"},{"volume-title":"Learning Cross-Modal Context Graph for Visual Grounding","author":"Liu Yongfei","unstructured":"Yongfei Liu, Bo Wan, Xiaodan Zhu, and Xuming He. 2020. Learning Cross-Modal Context Graph for Visual Grounding. In AAAI. AAAI Press, 11645--11652.","key":"e_1_3_2_1_26_1"},{"key":"e_1_3_2_1_27_1","volume-title":"Generation and Comprehension of Unambiguous Object Descriptions. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016","author":"Mao Junhua","year":"2016","unstructured":"Junhua Mao, Jonathan Huang, Alexander Toshev, Oana Camburu, Alan L. Yuille, and Kevin Murphy. 2016. Generation and Comprehension of Unambiguous Object Descriptions. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27--30, 2016. IEEE Computer Society, 11--20."},{"key":"e_1_3_2_1_28_1","volume-title":"Yuille","author":"Mao Junhua","year":"2015","unstructured":"Junhua Mao, Wei Xu, Yi Yang, Jiang Wang, and Alan L. Yuille. 2015. Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN). In ICLR, Yoshua Bengio and Yann LeCun (Eds.)."},{"doi-asserted-by":"crossref","unstructured":"Duy-Kien Nguyen and Takayuki Okatani. 2018. Improved fusion of visual and language representations by dense symmetric co-attention for visual question answering. In CVPR. 6087--6096.","key":"e_1_3_2_1_29_1","DOI":"10.1109\/CVPR.2018.00637"},{"volume-title":"Computer Vision - ECCV2018 - 15th European Conference (Lecture Notes in Computer Science)","author":"Plummer Bryan A.","unstructured":"Bryan A. Plummer, Paige Kordas, M. Hadi Kiapour, Shuai Zheng, Robinson Piramuthu, and Svetlana Lazebnik. 2018. Conditional Image-Text Embedding Networks. In Computer Vision - ECCV2018 - 15th European Conference (Lecture Notes in Computer Science), Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss (Eds.), Vol. 11216. Springer, 258--274.","key":"e_1_3_2_1_30_1"},{"key":"e_1_3_2_1_31_1","volume-title":"Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues","author":"Plummer Bryan A.","year":"1946","unstructured":"Bryan A. Plummer, Arun Mallya, Christopher M. Cervantes, Julia Hockenmaier, and Svetlana Lazebnik. 2017. Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues. In ICCV. IEEE Computer Society, 1946--1955."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_32_1","DOI":"10.1109\/ICCV.2015.303"},{"doi-asserted-by":"crossref","unstructured":"Joseph Redmon Santosh Divvala Ross Girshick and Ali Farhadi. 2016. You only look once: Unified real-time object detection. In CVPR. 779--788.","key":"e_1_3_2_1_33_1","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_34_1","volume-title":"Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)."},{"unstructured":"Shaoqing Ren Kaiming He Ross B. Girshick and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In NeurIPS Corinna Cortes Neil D. Lawrence Daniel D. Lee Masashi Sugiyama and Roman Garnett (Eds.). 91--99.","key":"e_1_3_2_1_35_1"},{"volume-title":"Computer Vision - ECCV 2016 - 14th European Conference (Lecture Notes in Computer Science)","author":"Rohrbach Anna","unstructured":"Anna Rohrbach, Marcus Rohrbach, Ronghang Hu, Trevor Darrell, and Bernt Schiele. 2016. Grounding of Textual Phrases in Images by Reconstruction. In Computer Vision - ECCV 2016 - 14th European Conference (Lecture Notes in Computer Science), Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.), Vol. 9905. Springer, 817--834.","key":"e_1_3_2_1_36_1"},{"doi-asserted-by":"crossref","unstructured":"Arka Sadhu Kan Chen and Ram Nevatia. 2019. Zero-shot grounding of objects from natural language queries. In ICCV. 4694--4703.","key":"e_1_3_2_1_37_1","DOI":"10.1109\/ICCV.2019.00479"},{"doi-asserted-by":"crossref","unstructured":"Kevin J Shih Saurabh Singh and Derek Hoiem. 2016. Where to look: Focus regions for visual question answering. In CVPR. 4613--4621.","key":"e_1_3_2_1_38_1","DOI":"10.1109\/CVPR.2016.499"},{"key":"e_1_3_2_1_39_1","volume-title":"Theo Gevers, and Arnold WM Smeulders.","author":"Uijlings Jasper RR","year":"2013","unstructured":"Jasper RR Uijlings, Koen EA Van De Sande, Theo Gevers, and Arnold WM Smeulders. 2013. Selective search for object recognition. International journal of computer vision 104, 2 (2013), 154--171."},{"volume-title":"Phrase Localization Without Paired Training Examples","author":"Wang Josiah","unstructured":"Josiah Wang and Lucia Specia. 2019. Phrase Localization Without Paired Training Examples. In ICCV. IEEE, 4662--4671.","key":"e_1_3_2_1_40_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_41_1","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"e_1_3_2_1_42_1","volume-title":"Learning Deep Structure-Preserving Image-Text Embeddings. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR","author":"Wang Liwei","year":"2016","unstructured":"Liwei Wang, Yin Li, and Svetlana Lazebnik. 2016. Learning Deep Structure-Preserving Image-Text Embeddings. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 5005--5013."},{"volume-title":"Computer Vision - ECCV 2016 - 14th European Conference (Lecture Notes in Computer Science)","author":"Wang Mingzhe","unstructured":"Mingzhe Wang, Mahmoud Azab, Noriyuki Kojima, Rada Mihalcea, and Jia Deng. 2016. Structured Matching for Phrase Localization. In Computer Vision - ECCV 2016 - 14th European Conference (Lecture Notes in Computer Science), Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.), Vol. 9912. Springer, 696--711.","key":"e_1_3_2_1_43_1"},{"key":"e_1_3_2_1_44_1","volume-title":"An end-to-end approach to natural language object retrieval via context-aware deep reinforcement learning. arXiv preprint arXiv:1703.07579","author":"Wu Fan","year":"2017","unstructured":"Fan Wu, Zhongwen Xu, and Yi Yang. 2017. An end-to-end approach to natural language object retrieval via context-aware deep reinforcement learning. arXiv preprint arXiv:1703.07579 (2017)."},{"doi-asserted-by":"crossref","unstructured":"Fanyi Xiao Leonid Sigal and Yong Jae Lee. 2017. Weakly-supervised visual grounding of phrases with linguistic structures. In CVPR. 5945--5954.","key":"e_1_3_2_1_45_1","DOI":"10.1109\/CVPR.2017.558"},{"doi-asserted-by":"crossref","unstructured":"Zhengyuan Yang Boqing Gong Liwei Wang Wenbing Huang Dong Yu and Jiebo Luo. 2019. A fast and accurate one-stage approach to visual grounding. In ICCV. 4683--4693.","key":"e_1_3_2_1_46_1","DOI":"10.1109\/ICCV.2019.00478"},{"key":"e_1_3_2_1_47_1","volume-title":"Schwing","author":"Yeh Raymond A.","year":"2017","unstructured":"Raymond A. Yeh, Jinjun Xiong, Wen-Mei W. Hwu, Minh N. Do, and Alexander G. Schwing. 2017. Interpretable and Globally Optimal Prediction for Textual Grounding using Image Concepts. In NeurIPS, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 1912--1922."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_48_1","DOI":"10.1162\/tacl_a_00166"},{"doi-asserted-by":"crossref","unstructured":"Zhou Yu Jun Yu Chenchao Xiang Zhou Zhao Qi Tian and Dacheng Tao. 2018. Rethinking Diversified and Discriminative Proposal Generation for Visual Grounding. In IJCAI J\u00e9r\u00f4me Lang (Ed.). ijcai.org 1114--1120.","key":"e_1_3_2_1_49_1","DOI":"10.24963\/ijcai.2018\/155"},{"doi-asserted-by":"crossref","unstructured":"Hanwang Zhang Yulei Niu and Shih-Fu Chang. 2018. Grounding referring expressions in images by variational context. In CVPR. 4158--4166.","key":"e_1_3_2_1_50_1","DOI":"10.1109\/CVPR.2018.00437"},{"doi-asserted-by":"crossref","unstructured":"Fang Zhao Jianshu Li Jian Zhao and Jiashi Feng. 2018. Weakly supervised phrase localization with multi-scale anchored transformer network. In CVPR. 5696--5705.","key":"e_1_3_2_1_51_1","DOI":"10.1109\/CVPR.2018.00597"},{"key":"e_1_3_2_1_52_1","volume-title":"Enhancing geometric factors in model learning and inference for object detection and instance segmentation. arXiv preprint arXiv:2005.03572","author":"Zheng Zhaohui","year":"2020","unstructured":"Zhaohui Zheng, Ping Wang, Dongwei Ren, Wei Liu, Rongguang Ye, Qinghua Hu, and Wangmeng Zuo. 2020. Enhancing geometric factors in model learning and inference for object detection and instance segmentation. arXiv preprint arXiv:2005.03572 (2020)."},{"unstructured":"Zhaohui Zheng Ping Wang Dongwei Ren Wei Liu Rongguang Ye Qinghua Hu and Wangmeng Zuo. 2020. Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation. CoRR abs\/2005.03572. arXiv:2005.03572","key":"e_1_3_2_1_53_1"},{"key":"e_1_3_2_1_54_1","volume-title":"Simple baseline for visual question answering. arXiv preprint arXiv:1512.02167","author":"Zhou Bolei","year":"2015","unstructured":"Bolei Zhou, Yuandong Tian, Sainbayar Sukhbaatar, Arthur Szlam, and Rob Fergus. 2015. Simple baseline for visual question answering. arXiv preprint arXiv:1512.02167 (2015)."},{"volume-title":"Edge boxes: Locating object proposals from edges","author":"Lawrence Zitnick C","unstructured":"C Lawrence Zitnick and Piotr Doll\u00e1r. 2014. Edge boxes: Locating object proposals from edges. In ECCV. Springer, 391--405.","key":"e_1_3_2_1_55_1"}],"event":{"sponsor":["SIGAPP ACM Special Interest Group on Applied Computing"],"acronym":"SAC '22","name":"SAC '22: The 37th ACM\/SIGAPP Symposium on Applied Computing","location":"Virtual Event"},"container-title":["Proceedings of the 37th ACM\/SIGAPP Symposium on Applied Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477314.3507047","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477314.3507047","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:33Z","timestamp":1750191513000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477314.3507047"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":55,"alternative-id":["10.1145\/3477314.3507047","10.1145\/3477314"],"URL":"https:\/\/doi.org\/10.1145\/3477314.3507047","relation":{},"subject":[],"published":{"date-parts":[[2022,4,25]]},"assertion":[{"value":"2022-05-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}