{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T16:50:30Z","timestamp":1774716630794,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100007128","name":"Natural Science Foundation of Shaanxi Province","doi-asserted-by":"publisher","award":["No. 2024JC-JCQN-62"],"award-info":[{"award-number":["No. 2024JC-JCQN-62"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100007128","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Nature Science Foundation of China","award":["No. 62272374, No. 62192781, No. 62250009, No. 62137002"],"award-info":[{"award-number":["No. 62272374, No. 62192781, No. 62250009, No. 62137002"]}]},{"name":"Project of Chinese academy of engineering ?The Online and Offline Mixed Educational Service System for ?The Belt and Road? Training in MOOC China?"},{"name":"Project of China Knowledge Center for Engineering Science and Technology"},{"name":"the K. C. Wong Education Foundation"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680690","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"4640-4649","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6921-0303","authenticated-orcid":false,"given":"Chengyou","family":"Jia","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, MOEKLINNS Lab, Xi'an Jiaotong University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0140-7860","authenticated-orcid":false,"given":"Minnan","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, MOEKLINNS Lab, Xi'an Jiaotong University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7778-8807","authenticated-orcid":false,"given":"Xiaojun","family":"Chang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China & Mohamed bin Zayed University of Artificial Intelligence, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3775-3722","authenticated-orcid":false,"given":"Zhuohang","family":"Dang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi'an Jiaotong University & Shaanxi Province Key Laboratory of Big Data Knowledge Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0040-6177","authenticated-orcid":false,"given":"Mingfei","family":"Han","sequence":"additional","affiliation":[{"name":"ReLER Lab, AAII, University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4035-0630","authenticated-orcid":false,"given":"Mengmeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology, College of Computer Science and Technology & SGIT AI Lab, State Grid Corporation of China, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3529-9087","authenticated-orcid":false,"given":"Guang","family":"Dai","sequence":"additional","affiliation":[{"name":"SGIT AI Lab, State Grid Corporation of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5689-6490","authenticated-orcid":false,"given":"Sizhe","family":"Dang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4888-4445","authenticated-orcid":false,"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Zero-Shot Robustification of Zero-Shot Models. In The Twelfth International Conference on Learning Representations.","author":"Adila Dyah","year":"2024","unstructured":"Dyah Adila, Changho Shin, Linrong Cai, and Frederic Sala. 2024. Zero-Shot Robustification of Zero-Shot Models. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_2_1","volume-title":"Vivit: A video vision transformer.","author":"Arnab Anurag","year":"2021","unstructured":"Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun, Mario Luvci\u0107, and Cordelia Schmid. 2021. Vivit: A video vision transformer."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.9"},{"key":"e_1_3_2_1_4_1","unstructured":"Gedas Bertasius Heng Wang and Lorenzo Torresani. 2021. Is Space-Time Attention All You Need for Video Understanding?"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Biagio Brattoli Joseph Tighe Fedor Zhdanov Pietro Perona and Krzysztof Chalupka. 2020. Rethinking zero-shot video classification: End-to-end training for realistic applications.","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"e_1_3_2_1_6_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_7_1","volume-title":"A short note about kinetics-600. arXiv preprint arXiv:1808.01340","author":"Carreira Joao","year":"2018","unstructured":"Joao Carreira, Eric Noland, Andras Banki-Horvath, Chloe Hillier, and Andrew Zisserman. 2018. A short note about kinetics-600. arXiv preprint arXiv:1808.01340 (2018)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Joao Carreira and Andrew Zisserman. 2017. Quo vadis action recognition? a new model and the kinetics dataset.","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Shizhe Chen and Dong Huang. 2021. Elaborative Rehearsal for Zero-shot Action Recognition.","DOI":"10.1109\/ICCV48922.2021.01338"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"R Christoph and Feichtenhofer Axel Pinz. 2016. Spatiotemporal residual networks for video action recognition. (2016).","DOI":"10.1109\/CVPR.2017.787"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3241651"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3404663"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Christoph Feichtenhofer Haoqi Fan Jitendra Malik and Kaiming He. 2019. Slowfast networks for video recognition.","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_14_1","volume-title":"How Far Are We From AGI. arXiv preprint arXiv:2405.10313","author":"Feng Tao","year":"2024","unstructured":"Tao Feng, Chuanyang Jin, Jingyu Liu, Kunlun Zhu, Haoqin Tu, Zirui Cheng, Guanyu Lin, and Jiaxuan You. 2024. How Far Are We From AGI. arXiv preprint arXiv:2405.10313 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"Making pre-trained language models better few-shot learners. arXiv preprint arXiv:2012.15723","author":"Gao Tianyu","year":"2020","unstructured":"Tianyu Gao, Adam Fisch, and Danqi Chen. 2020. Making pre-trained language models better few-shot learners. arXiv preprint arXiv:2012.15723 (2020)."},{"key":"e_1_3_2_1_16_1","volume-title":"All about knowledge graphs for actions. arXiv preprint arXiv:2008.12432","author":"Ghosh Pallabi","year":"2020","unstructured":"Pallabi Ghosh, Nirat Saini, Larry S Davis, and Abhinav Shrivastava. 2020. All about knowledge graphs for actions. arXiv preprint arXiv:2008.12432 (2020)."},{"key":"e_1_3_2_1_17_1","volume-title":"Vincent Michalski, Joanna Materzynska, Susanne Westphal, Heuna Kim, Valentin Haenel, Ingo Fruend, Peter Yianilos, Moritz Mueller-Freitag, et al.","author":"Goyal Raghav","year":"2017","unstructured":"Raghav Goyal, Samira Ebrahimi Kahou, Vincent Michalski, Joanna Materzynska, Susanne Westphal, Heuna Kim, Valentin Haenel, Ingo Fruend, Peter Yianilos, Moritz Mueller-Freitag, et al. 2017. The\" something something\" video database for learning and evaluating visual common sense."},{"key":"e_1_3_2_1_18_1","unstructured":"Chen Ju Tengda Han Kunhao Zheng Ya Zhang and Weidi Xie. 2022. Prompting visual-language models for efficient video understanding."},{"key":"e_1_3_2_1_19_1","volume-title":"VicTR: Video-conditioned Text Representations for Activity Recognition. arXiv preprint arXiv:2304.02560","author":"Kahatapitiya Kumara","year":"2023","unstructured":"Kumara Kahatapitiya, Anurag Arnab, Arsha Nagrani, and Michael S Ryoo. 2023. VicTR: Video-conditioned Text Representations for Activity Recognition. arXiv preprint arXiv:2304.02560 (2023)."},{"key":"e_1_3_2_1_20_1","unstructured":"Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev et al. 2017. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Hildegard Kuehne Hueihan Jhuang Est\u00edbaliz Garrote Tomaso Poggio and Thomas Serre. 2011. HMDB: a large video database for human motion recognition.","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_2_1_24_1","unstructured":"Kunchang Li Yali Wang Yinan He Yizhuo Li Yi Wang Limin Wang and Yu Qiao. 2022. UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer. arxiv: 2211.09552 [cs.CV]"},{"key":"e_1_3_2_1_25_1","unstructured":"Kunchang Li Yali Wang Junhao Zhang Peng Gao Guanglu Song Yu Liu Hongsheng Li and Yu Qiao. 2022. UniFormer: Unifying Convolution and Self-attention for Visual Recognition. In ICLR."},{"key":"e_1_3_2_1_26_1","volume-title":"Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190","author":"Li Xiang Lisa","year":"2021","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00634"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Ze Liu Jia Ning Yue Cao Yixuan Wei Zheng Zhang Stephen Lin and Han Hu. 2022. Video swin transformer.","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Ze Liu Jia Ning Yue Cao Yixuan Wei Zheng Zhang Stephen Lin and Han Hu. 2022. Video swin transformer.","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00034"},{"key":"e_1_3_2_1_32_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Menon Sachit","year":"2022","unstructured":"Sachit Menon and Carl Vondrick. 2022. Visual Classification via Description from Large Language Models. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_33_1","unstructured":"Bolin Ni Houwen Peng Minghao Chen Songyang Zhang Gaofeng Meng Jianlong Fu Shiming Xiang and Haibin Ling. 2022. Expanding language-image pretrained models for general video recognition."},{"key":"e_1_3_2_1_34_1","first-page":"26462","article-title":"St-adapter: Parameter-efficient image-to-video transfer learning","volume":"35","author":"Pan Junting","year":"2022","unstructured":"Junting Pan, Ziyi Lin, Xiatian Zhu, Jing Shao, and Hongsheng Li. 2022. St-adapter: Parameter-efficient image-to-video transfer learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 26462--26477.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00219"},{"key":"e_1_3_2_1_36_1","unstructured":"Mandela Patrick Dylan Campbell Yuki Asano Ishan Misra Florian Metze Christoph Feichtenhofer Andrea Vedaldi and Jo ao F Henriques. 2021. Keeping your eye on the ball: Trajectory attention in video transformers."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Jie Qin Li Liu Ling Shao Fumin Shen Bingbing Ni Jiaxin Chen and Yunhong Wang. 2017. Zero-shot action recognition with error-correcting output codes. In CVPR.","DOI":"10.1109\/CVPR.2017.117"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01281"},{"key":"e_1_3_2_1_40_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning Transferable Visual Models From Natural Language Supervision."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"e_1_3_2_1_42_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos."},{"key":"e_1_3_2_1_43_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)."},{"key":"e_1_3_2_1_44_1","unstructured":"Qiushi Sun Zhirui Chen Fangzhi Xu Kanzhi Cheng Chang Ma Zhangyue Yin Jianing Wang Chengcheng Han Renyu Zhu Shuai Yuan et al. 2024. A survey of neural code intelligence: Paradigms advances and beyond. arXiv preprint arXiv:2403.14734 (2024)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Limin Wang Yuanjun Xiong Zhe Wang Yu Qiao Dahua Lin Xiaoou Tang and Luc Van Gool. 2016. Temporal segment networks: Towards good practices for deep action recognition.","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_1_46_1","volume-title":"ActionCLIP: A New Paradigm for Video Action Recognition. arXiv preprint arXiv:2109.08472","author":"Wang Mengmeng","year":"2021","unstructured":"Mengmeng Wang, Jiazheng Xing, and Yong Liu. 2021. ActionCLIP: A New Paradigm for Video Action Recognition. arXiv preprint arXiv:2109.08472 (2021)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Qian Wang and Ke Chen. 2017. Alternative semantic representations for zero-shot human action recognition. In ECML PKDD.","DOI":"10.1007\/978-3-319-71249-9_6"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Yunbo Wang Mingsheng Long Jianmin Wang and Philip S Yu. 2017. Spatiotemporal pyramid network for video action recognition.","DOI":"10.1109\/CVPR.2017.226"},{"key":"e_1_3_2_1_49_1","volume-title":"Generalizing from a few examples: A survey on few-shot learning. ACM computing surveys (csur)","author":"Wang Yaqing","year":"2020","unstructured":"Yaqing Wang, Quanming Yao, James T Kwok, and Lionel M Ni. 2020. Generalizing from a few examples: A survey on few-shot learning. ACM computing surveys (csur), Vol. 53, 3 (2020), 1--34."},{"key":"e_1_3_2_1_50_1","unstructured":"Zejia Weng Xitong Yang Ang Li Zuxuan Wu and Yu-Gang Jiang. 2023. Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization. In ICML."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16401"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01261"},{"key":"e_1_3_2_1_53_1","volume-title":"Transferring textual knowledge for visual recognition. AAAI","author":"Wu Wenhao","year":"2023","unstructured":"Wenhao Wu, Zhun Sun, and Wanli Ouyang. 2023. Transferring textual knowledge for visual recognition. AAAI (2023)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Wenhao Wu Xiaohan Wang Haipeng Luo Jingdong Wang Yi Yang and Wanli Ouyang. 2023. Bidirectional cross-modal knowledge exploration for video recognition with pre-trained vision-language models. In CVPR. 6620--6630.","DOI":"10.1109\/CVPR52729.2023.00640"},{"key":"e_1_3_2_1_55_1","volume-title":"Symbol-LLM: Towards foundational symbol-centric interface for large language models. arXiv preprint arXiv:2311.09278","author":"Xu Fangzhi","year":"2023","unstructured":"Fangzhi Xu, Zhiyong Wu, Qiushi Sun, Siyu Ren, Fei Yuan, Shuai Yuan, Qika Lin, Yu Qiao, and Jun Liu. 2023. Symbol-LLM: Towards foundational symbol-centric interface for large language models. arXiv preprint arXiv:2311.09278 (2023)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"crossref","unstructured":"Shen Yan Xuehan Xiong Anurag Arnab Zhichao Lu Mi Zhang Chen Sun and Cordelia Schmid. 2022. Multiview transformers for video recognition.","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"e_1_3_2_1_58_1","volume-title":"FILIP: Fine-grained Interactive Language-Image Pre-Training. In International Conference on Learning Representations.","author":"Yao Lewei","year":"2021","unstructured":"Lewei Yao, Runhui Huang, Lu Hou, Guansong Lu, Minzhe Niu, Hang Xu, Xiaodan Liang, Zhenguo Li, Xin Jiang, and Chunjing Xu. 2021. FILIP: Fine-grained Interactive Language-Image Pre-Training. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02023"},{"key":"e_1_3_2_1_61_1","volume-title":"Chen Change Loy, and Ziwei Liu","author":"Zhou Kaiyang","year":"2021","unstructured":"Kaiyang Zhou, Jingkang Yang, Chen Change Loy, and Ziwei Liu. 2021. Learning to prompt for vision-language models. arXiv preprint arXiv:2109.01134 (2021)."},{"key":"e_1_3_2_1_62_1","volume-title":"Chen Change Loy, and Ziwei Liu","author":"Zhou Kaiyang","year":"2022","unstructured":"Kaiyang Zhou, Jingkang Yang, Chen Change Loy, and Ziwei Liu. 2022. Conditional prompt learning for vision-language models. In CVPR."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"crossref","unstructured":"Yi Zhu Yang Long Yu Guan Shawn Newsam and Ling Shao. 2018. Towards universal representation for unseen action recognition. In CVPR.","DOI":"10.1109\/CVPR.2018.00983"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680690","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680690","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:57Z","timestamp":1750295877000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680690"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":63,"alternative-id":["10.1145\/3664647.3680690","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680690","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}