{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:21:05Z","timestamp":1765340465771,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754922","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:47:18Z","timestamp":1761374838000},"page":"12006-12015","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["<scp>How2Compress<\/scp>\n                    : Scalable and Efficient Edge Video Analytics via Adaptive Granular Video Compression"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0377-360X","authenticated-orcid":false,"given":"Yuheng","family":"Wu","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science &amp; Technology, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8186-2600","authenticated-orcid":false,"given":"Thanh-Tung","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science &amp; Technology, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9252-4764","authenticated-orcid":false,"given":"Lucas","family":"Liebe","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science &amp; Technology, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6375-8051","authenticated-orcid":false,"given":"Quang","family":"Tau","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science &amp; Technology, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2121-4951","authenticated-orcid":false,"given":"Pablo Espinosa","family":"Campos","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science &amp; Technology, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1850-1782","authenticated-orcid":false,"given":"Jinghan","family":"Cheng","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science &amp; Technology, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5923-6227","authenticated-orcid":false,"given":"Dongman","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science &amp; Technology, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"58","article-title":"Real-Time Video Analytics","volume":"50","author":"Ananthanarayanan Ganesh","year":"2017","unstructured":"Ganesh Ananthanarayanan, Paramvir Bahl, Peter Bod\u00edk, Krishna Chintalapudi, Matthai Philipose, Lenin Ravindranath, and Sudipta Sinha. 2017. Real-Time Video Analytics: The Killer App for Edge Computing. Computer, Vol. 50, 10 (2017), 58-67.","journal-title":"The Killer App for Edge Computing. Computer"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"e_1_3_2_1_3_1","first-page":"967","volume-title":"2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Chaudhary Shubham","year":"2024","unstructured":"Shubham Chaudhary, Aryan Taneja, Anjali Singh, Purbasha Roy, Sohum Sikdar, Mukulika Maity, and Arani Bhattacharya. 2024. TileClipper: Lightweight Selection of Regions of Interest from Videos for Traffic Surveillance. In 2024 USENIX Annual Technical Conference (USENIX ATC 24). USENIX Association, Santa Clara, CA, 967-984. https:\/\/www.usenix.org\/conference\/atc24\/presentation\/chaudhary"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524273.3528178"},{"key":"e_1_3_2_1_5_1","volume-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. 2017a. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence, Vol. 40, 4 (2017), 834-848."},{"key":"e_1_3_2_1_6_1","volume-title":"Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. 2017b. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)."},{"key":"e_1_3_2_1_7_1","volume-title":"NTIRE 2023 benchmark and report. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 1495-1521","author":"Conde Marcos V","year":"2023","unstructured":"Marcos V Conde, Eduard Zamfir, Radu Timofte, Daniel Motilla, Cen Liu, Zexin Zhang, Yunbo Peng, Yue Lin, Jiaming Guo, Xueyi Zou, et al., 2023. Efficient deep models for real-time 4k image super-resolution. NTIRE 2023 benchmark and report. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 1495-1521."},{"key":"e_1_3_2_1_8_1","unstructured":"NVIDIA Corporation. 2021a. NVIDIA Video Codec SDK 11.0.1. https:\/\/developer.nvidia.com\/nvidia-video-codec-sdk."},{"key":"e_1_3_2_1_9_1","unstructured":"NVIDIA Corporation. 2021b. NVIDIA Video Codec SDK 11.0.1 - Adaptive Quantization. https:\/\/docs.nvidia.com\/video-technologies\/video-codec-sdk\/11.0\/nvenc-video-encoder-api-prog-guide\/index.html."},{"key":"e_1_3_2_1_10_1","unstructured":"NVIDIA Corporation. 2024. Nvidia Video SDK - Emphasis Map Feature. https:\/\/docs.nvidia.com\/video-technologies\/video-codec-sdk\/11.1\/nvenc-video-encoder-api-prog-guide\/index.html. Available at https:\/\/docs.nvidia.com\/video-technologies\/video-codec-sdk\/11.1\/nvenc-video-encoder-api-prog-guide\/index.html."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2530146"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3044015"},{"key":"e_1_3_2_1_13_1","first-page":"3858","article-title":"Structural knowledge distillation for object detection","volume":"35","author":"Rijk Philip De","year":"2022","unstructured":"Philip De Rijk, Lukas Schneider, Marius Cordts, and Dariu Gavrila. 2022. Structural knowledge distillation for object detection. Advances in Neural Information Processing Systems, Vol. 35 (2022), 3858-3870.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_14_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR (2021)."},{"key":"e_1_3_2_1_15_1","first-page":"450","volume-title":"Proceedings of Machine Learning and Systems, D. Marculescu, Y. Chi, and C. Wu (Eds.)","volume":"4","author":"Du Kuntai","year":"2022","unstructured":"Kuntai Du, Qizheng Zhang, Anton Arapin, Haodong Wang, Zhengxu Xia, and Junchen Jiang. 2022. AccMPEG: Optimizing Video Encoding for Accurate Video Analytics. In Proceedings of Machine Learning and Systems, D. Marculescu, Y. Chi, and C. Wu (Eds.), Vol. 4. 450-466."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461096"},{"key":"e_1_3_2_1_17_1","unstructured":"FFmpeg. 2024. FFmpeg. https:\/\/ffmpeg.org\/. Available at https:\/\/ffmpeg.org\/."},{"key":"e_1_3_2_1_18_1","unstructured":"Alliance for Open Media. 2025. AV1 Codec Library. https:\/\/aomedia.googlesource.com\/aom\/ Accessed: 2025-04-01."},{"key":"e_1_3_2_1_19_1","volume-title":"International conference on learning representations.","author":"Geirhos Robert","year":"2018","unstructured":"Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A Wichmann, and Wieland Brendel. 2018. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In International conference on learning representations."},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Geirhos Robert","year":"2019","unstructured":"Robert Geirhos, Pascal Rubisch, Claudio Michaelis, Matthias Bethge, Felix A Wichmann, and Wieland Brendel. 2019. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Mahshid Ghasemi Sofia Kleisarchaki Thomas Calmant Jiawei Lu Shivam Ojha Zoran Kostic Levent G\u00fcrgen Gil Zussman and Javad Ghaderi. 2023. Real-time Multi-Camera Analytics for Traffic Information Extraction and Visualization. In 2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops). 288-290. doi:10.1109\/PerComWorkshops56833.2023.10150224","DOI":"10.1109\/PerComWorkshops56833.2023.10150224"},{"key":"e_1_3_2_1_22_1","volume-title":"VP9 - An Open Video Codec for Next-Generation Web Video. https:\/\/www.webmproject.org\/vp9\/. Google White Paper","author":"Glover Robert","year":"2013","unstructured":"Robert Glover, Debargha Mukherjee, John Bankoski, Peter Wilkins, Yaowu Xu, Jani Han, Rajat Joshi, Pascal de Rivaz, and Bill Rose. 2013. VP9 - An Open Video Codec for Next-Generation Web Video. https:\/\/www.webmproject.org\/vp9\/. Google White Paper (2013). Accessed: 2025-03-18."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221999"},{"key":"e_1_3_2_1_24_1","first-page":"707","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Hwang Jinwoo","year":"2022","unstructured":"Jinwoo Hwang, Minsu Kim, Daeun Kim, Seungho Nam, Yoonsung Kim, Dohee Kim, Hardik Sharma, and Jongse Park. 2022. {CoVA}: Exploiting {Compressed-Domain} analysis to accelerate video analytics. In 2022 USENIX Annual Technical Conference (USENIX ATC 22). 707-722."},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on Learning Representations.","author":"Islam Md Amirul","year":"2021","unstructured":"Md Amirul Islam, Matthew Kowal, Patrick Esser, Sen Jia, Bjorn Ommer, Konstantinos G Derpanis, and Neil Bruce. 2021. Shape or texture: Understanding discriminative features in CNNs. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01637"},{"key":"e_1_3_2_1_27_1","unstructured":"Glenn Jocher Ayush Chaurasia and Jing Qiu. 2023. Ultralytics YOLO. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","unstructured":"Glenn Jocher Alex Stoken Jirka Borovec NanoCode012 ChristopherSTAN Liu Changyu Laughing tkianai Adam Hogan lorenzomammana yxNONG AlexWang1900 Laurentiu Diaconu Marc wanghaoyang0106 ml5ah Doug Francisco Ingham Frederik Guilhen Hatovix Jake Poznanski Jiacong Fang Lijun Yu changyu98 Mingyu Wang Naman Gupta Osama Akhtar PetrDvoracek and Prashant Rai. 2020. ultralytics\/yolov5: v3.1 - Bug Fixes and Performance Improvements. doi:10.5281\/zenodo.4154370","DOI":"10.5281\/zenodo.4154370"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.23919\/ICACT.2019.8701939"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613785"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612585"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229045"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405874"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_35_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Lu Chris","year":"2024","unstructured":"Chris Lu, Yannick Schroecker, Albert Gu, Emilio Parisotto, Jakob Foerster, Satinder Singh, and Feryal Behbahani. 2024. Structured state space models for in-context reinforcement learning. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_36_1","volume-title":"Separable self-attention for mobile vision transformers. arXiv preprint arXiv:2206.02680","author":"Mehta Sachin","year":"2022","unstructured":"Sachin Mehta and Mohammad Rastegari. 2022. Separable self-attention for mobile vision transformers. arXiv preprint arXiv:2206.02680 (2022)."},{"key":"e_1_3_2_1_37_1","unstructured":"A. Milan L. Leal-Taix\u00e9 I. Reid S. Roth and K. Schindler. 2016. MOT16: A Benchmark for Multi-Object Tracking. (March 2016). http:\/\/arxiv.org\/abs\/1603.00831"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOM56429.2023.10099298"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/PerCom64205.2025.00032"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160530"},{"key":"e_1_3_2_1_41_1","unstructured":"WebM Project. 2010. VP8 Data Format and Decoding Guide. https:\/\/www.webmproject.org\/vp8\/. Accessed: 2025-03-18."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICGCIoT.2018.8753105"},{"key":"e_1_3_2_1_44_1","volume-title":"Reinforcement learning with sparse rewards using guidance from offline demonstration. arXiv preprint arXiv:2202.04628","author":"Rengarajan Desik","year":"2022","unstructured":"Desik Rengarajan, Gargi Vaidya, Akshay Sarvesh, Dileep Kalathil, and Srinivas Shakkottai. 2022. Reinforcement learning with sparse rewards using guidance from offline demonstration. arXiv preprint arXiv:2202.04628 (2022)."},{"key":"e_1_3_2_1_45_1","volume-title":"Jan Kautz, Scott Linderman, and Wonmin Byeon.","author":"Smith Jimmy","year":"2024","unstructured":"Jimmy Smith, Shalini De Mello, Jan Kautz, Scott Linderman, and Wonmin Byeon. 2024. Convolutional state space models for long-range spatiotemporal modeling. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"e_1_3_2_1_47_1","unstructured":"Shiyu Tang Ting Sun Juncai Peng Guowei Chen Yuying Hao Manhui Lin Zhihong Xiao Jiangbin You and Yi Liu. 2023. PP-MobileSeg: Explore the Fast and Accurate Semantic Segmentation Model on Mobile Devices. arXiv:2304.05152 [cs.CV] https:\/\/arxiv.org\/abs\/2304.05152"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3004696"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_50_1","unstructured":"VideoLAN. 2008. X264. https:\/\/code.videolan.org\/videolan\/x264\/-\/commit\/b59440f09b7eb7e6f30c1131d56843ee92e3751d."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221995"},{"key":"e_1_3_2_1_52_1","volume-title":"The 8th AI City Challenge. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops.","author":"Wang Shuo","year":"2024","unstructured":"Shuo Wang, David C. Anastasiu, Zheng Tang, Ming-Ching Chang, Yue Yao, Liang Zheng, Mohammed Shaiqur Rahman, Meenakshi S. Arya, Anuj Sharma, Pranamesh Chakraborty, Sanjita Prajapati, Quan Kong, Norimasa Kobori, Munkhjargal Gochoo, Munkh-Erdene Otgonbold, Ganzorig Batnasan, Fady Alnajjar, Ping-Yang Chen, Jun-Wei Hsieh, Xunlei Wu, Sameer Satish Pusegaonkar, Yizhou Wang, Sujit Biswas, and Rama Chellappa. 2024. The 8th AI City Challenge. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455944"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3327097"},{"key":"e_1_3_2_1_57_1","volume-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in neural information processing systems","author":"Xie Enze","year":"2021","unstructured":"Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M Alvarez, and Ping Luo. 2021. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in neural information processing systems, Vol. 34 (2021), 12077-12090."},{"key":"e_1_3_2_1_58_1","first-page":"7614","article-title":"CEIP: combining explicit and implicit priors for reinforcement learning with demonstrations","volume":"35","author":"Yan Kai","year":"2022","unstructured":"Kai Yan, Alex Schwing, and Yu-Xiong Wang. 2022. CEIP: combining explicit and implicit priors for reinforcement learning with demonstrations. Advances in Neural Information Processing Systems, Vol. 35 (2022), 7614-7627.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_59_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yang Hanlin","year":"2024","unstructured":"Hanlin Yang, Chao Yu, Siji Chen, et al., 2024. Hybrid policy optimization from Imperfect demonstrations. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796984"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01747"},{"volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 1838-1845","author":"Zhang Lu","key":"e_1_3_2_1_62_1","unstructured":"Lu Zhang and Laurens van der Maaten. 2013. Structure preserving object tracking. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1838-1845."},{"key":"e_1_3_2_1_63_1","volume-title":"CASVA: Configuration-Adaptive Streaming for Live Video Analytics. In IEEE INFOCOM 2022 - IEEE Conference on Computer Communications. 2168-2177","author":"Zhang Miao","year":"2022","unstructured":"Miao Zhang, Fangxin Wang, and Jiangchuan Liu. 2022b. CASVA: Configuration-Adaptive Streaming for Live Video Analytics. In IEEE INFOCOM 2022 - IEEE Conference on Computer Communications. 2168-2177."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3448628"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01177"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.14778\/3636218.3636224"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119563"},{"key":"e_1_3_2_1_68_1","volume-title":"Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159","author":"Zhu Xizhou","year":"2020","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2020. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)."}],"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\/3746027.3754922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:18:29Z","timestamp":1765340309000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754922"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":68,"alternative-id":["10.1145\/3746027.3754922","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754922","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"}}]}}