{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:30:24Z","timestamp":1771468224616,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","funder":[{"DOI":"10.13039\/100009002","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","award":["T2EP20123-0006"],"award-info":[{"award-number":["T2EP20123-0006"]}],"id":[{"id":"10.13039\/100009002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755814","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:56:43Z","timestamp":1761371803000},"page":"5198-5207","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["DT-UFC: Universal Large Model Feature Coding via Peaky-to-Balanced Distribution Transformation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8787-8014","authenticated-orcid":false,"given":"Changsheng","family":"Gao","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2287-4217","authenticated-orcid":false,"given":"Zijie","family":"Liu","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7163-6263","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9100-2906","authenticated-orcid":false,"given":"Dong","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3638-5566","authenticated-orcid":false,"given":"Xiaoyan","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9866-1947","authenticated-orcid":false,"given":"Weisi","family":"Lin","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803110"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054770"},{"key":"e_1_3_2_1_4_1","first-page":"233","article-title":"A closer look at memorization in deep networks (ICML'17)","author":"Arpit Devansh","year":"2017","unstructured":"Devansh Arpit, Stanis\u0142aw Jastrzundefinedbski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S. Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, and Simon Lacoste-Julien. 2017. A closer look at memorization in deep networks (ICML'17). JMLR, 233-242.","journal-title":"JMLR"},{"key":"e_1_3_2_1_5_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"Sung Jin Hwang, and Nick Johnston","author":"Ball\u00e9 Johannes","year":"2018","unstructured":"Johannes Ball\u00e9, David C. Minnen, Saurabh Singh, Sung Jin Hwang, and Nick Johnston. 2018. Variational image compression with a scale hyperprior. ArXiv, Vol. abs\/1802.01436 (2018)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3200698"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647798"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02129"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350849"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451100"},{"key":"e_1_3_2_1_12_1","unstructured":"Patrick Esser Sumith Kulal Andreas Blattmann Rahim Entezari Jonas M\u00fcller Harry Saini Yam Levi Dominik Lorenz Axel Sauer Frederic Boesel et al. 2024. Scaling rectified flow transformers for high-resolution image synthesis. In ICML."},{"key":"e_1_3_2_1_13_1","volume-title":"Image coding for machines with omnipotent feature learning","author":"Feng Ruoyu","unstructured":"Ruoyu Feng, Xin Jin, Zongyu Guo, Runsen Feng, Yixin Gao, Tianyu He, Zhizheng Zhang, Simeng Sun, and Zhibo Chen. 2022. Image coding for machines with omnipotent feature learning. In ECCV. Springer, 510-528."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/PCS60826.2024.10566361"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3467124"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3144424"},{"key":"e_1_3_2_1_17_1","first-page":"556","article-title":"Rethinking the Joint Optimization in Video Coding for Machines: A Case Study","author":"Gao Changsheng","year":"2024","unstructured":"Changsheng Gao, Zhuoyuan Li, Li Li, Dong Liu, and Feng Wu. 2024b. Rethinking the Joint Optimization in Video Coding for Machines: A Case Study. In DCC. 556-556.","journal-title":"DCC."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3130754"},{"key":"e_1_3_2_1_19_1","volume-title":"Test Conditions, and Benchmark. arXiv preprint arXiv:2412.04307","author":"Gao Changsheng","year":"2024","unstructured":"Changsheng Gao, Yifan Ma, Qiaoxi Chen, Yenan Xu, Dong Liu, and Weisi Lin. 2024c. Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark. arXiv preprint arXiv:2412.04307 (2024)."},{"key":"e_1_3_2_1_20_1","first-page":"5185","article-title":"Structured multi-modal feature embedding and alignment for image-sentence retrieval","author":"Ge Xuri","year":"2021","unstructured":"Xuri Ge, Fuhai Chen, Joemon M Jose, Zhilong Ji, Zhongqin Wu, and Xiao Liu. 2021. Structured multi-modal feature embedding and alignment for image-sentence retrieval. In ACM MM. 5185-5193.","journal-title":"ACM MM."},{"key":"e_1_3_2_1_21_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611851"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897802"},{"key":"e_1_3_2_1_24_1","volume-title":"Bridging compressed image latents and multimodal large language models. arXiv preprint arXiv:2407.19651","author":"Kao Chia-Hao","year":"2024","unstructured":"Chia-Hao Kao, Cheng Chien, Yu-Jen Tseng, Yi-Hsin Chen, Alessandro Gnutti, Shao-Yuan Lo, Wen-Hsiao Peng, and Riccardo Leonardi. 2024. Bridging compressed image latents and multimodal large language models. arXiv preprint arXiv:2407.19651 (2024)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3302858"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.02.009"},{"key":"e_1_3_2_1_27_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_28_1","volume-title":"International conference on machine learning. PMLR, 12888-12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022b. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_29_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems, Vol. 34 (2021), 9694-9705."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP56404.2022.10008901"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP63160.2024.10849824"},{"key":"e_1_3_2_1_32_1","volume-title":"Uniformly Accelerated Motion Model for Inter Prediction. In 2024 IEEE International Conference on Visual Communications and Image Processing (VCIP). 1-5.","author":"Li Zhuoyuan","year":"2024","unstructured":"Zhuoyuan Li, Yao Li, Chuanbo Tang, Li Li, Dong Liu, and Feng Wu. 2024b. Uniformly Accelerated Motion Model for Inter Prediction. In 2024 IEEE International Conference on Visual Communications and Image Processing (VCIP). 1-5."},{"key":"e_1_3_2_1_33_1","unstructured":"Zhuoyuan Li Junqi Liao Chuanbo Tang Haotian Zhang Yuqi Li Yifan Bian Xihua Sheng Xinmin Feng Yao Li Changsheng Gao et al. 2024c. USTC-TD: A test dataset and benchmark for image and video coding in 2020s. arXiv preprint arXiv:2409.08481 (2024)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2024.3434520"},{"key":"e_1_3_2_1_35_1","volume-title":"European Conference on Computer Vision. Springer, 329-348","author":"Liu Jinming","year":"2024","unstructured":"Jinming Liu, Ruoyu Feng, Yunpeng Qi, Qiuyu Chen, Zhibo Chen, Wenjun Zeng, and Xin Jin. 2024. Rate-distortion-cognition controllable versatile neural image compression. In European Conference on Computer Vision. Springer, 329-348."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01491-7"},{"key":"e_1_3_2_1_37_1","volume-title":"International conference on machine learning. PMLR, 97-105","author":"Long Mingsheng","year":"2015","unstructured":"Mingsheng Long, Yue Cao, Jianmin Wang, and Michael Jordan. 2015. Learning transferable features with deep adaptation networks. In International conference on machine learning. PMLR, 97-105."},{"key":"e_1_3_2_1_38_1","first-page":"1","article-title":"Feature Compression With 3D Sparse Convolution","author":"Ma Yifan","year":"2024","unstructured":"Yifan Ma, Changsheng Gao, Qiaoxi Chen, Li Li, Dong Liu, and Xiaoyan Sun. 2024. Feature Compression With 3D Sparse Convolution. In VCIP. 1-5.","journal-title":"VCIP."},{"key":"e_1_3_2_1_39_1","first-page":"1","article-title":"Perceptual Image Compression With Conditional Diffusion Transformers","author":"Mao Rui","year":"2024","unstructured":"Rui Mao, Xinmin Feng, Changsheng Gao, Li Li, Dong Liu, and Xiaoyan Sun. 2024. Perceptual Image Compression With Conditional Diffusion Transformers. In VCIP. 1-5.","journal-title":"VCIP."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859894"},{"key":"e_1_3_2_1_41_1","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et al. 2023. DINOv2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)."},{"key":"e_1_3_2_1_42_1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","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. In ICML. PMLR, 8748-8763.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_43_1","volume-title":"Tatsunori B. Hashimoto, and Percy Liang.","author":"Shiori","year":"2020","unstructured":"Shiori Sagawa*, Pang Wei Koh*, Tatsunori B. Hashimoto, and Percy Liang. 2020. Distributionally Robust Neural Networks. In ICLR."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01923"},{"key":"e_1_3_2_1_45_1","volume-title":"Image Coding For Machine Via Analytics-Driven Appearance Redundancy Reduction. In 2024 IEEE International Conference on Image Processing (ICIP). IEEE","author":"Shen Xuelin","year":"2024","unstructured":"Xuelin Shen, Haoqiao Ou, and Wenhan Yang. 2024a. Image Coding For Machine Via Analytics-Driven Appearance Redundancy Reduction. In 2024 IEEE International Conference on Image Processing (ICIP). IEEE, 1883-1889."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447491"},{"key":"e_1_3_2_1_47_1","first-page":"443","volume-title":"proceedings, part III 14","author":"Sun Baochen","year":"2016","unstructured":"Baochen Sun and Kate Saenko. 2016. Deep coral: Correlation alignment for deep domain adaptation. In Computer vision-ECCV 2016 workshops: Amsterdam, the Netherlands, October 8-10 and 15-16, 2016, proceedings, part III 14. Springer, 443-450."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28317"},{"key":"e_1_3_2_1_49_1","volume-title":"Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al.","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al., 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367879"},{"key":"e_1_3_2_1_51_1","volume-title":"European Conference on Computer Vision. Springer, 163-183","author":"Tian Yuan","year":"2024","unstructured":"Yuan Tian, Guo Lu, and Guangtao Zhai. 2024a. Free-VSC: Free semantics from visual foundation models for unsupervised video semantic compression. In European Conference on Computer Vision. Springer, 163-183."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01252"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510033"},{"key":"e_1_3_2_1_54_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3094300"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01920"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.103859"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3222101"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3303716"},{"key":"e_1_3_2_1_60_1","volume-title":"Call for Proposals on Feature Compression for Video Coding for Machines","author":"April","year":"2023","unstructured":"WG2. April 2023. Call for Proposals on Feature Compression for Video Coding for Machines. Vol. ISO\/IEC JTC 1\/SC 29\/WG 2, N282 ( April 2023)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.111115"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3121131"},{"key":"e_1_3_2_1_63_1","first-page":"6137","article-title":"OpenFedLLM: Training large language models on decentralized private data via federated learning","author":"Ye Rui","year":"2024","unstructured":"Rui Ye, Wenhao Wang, Jingyi Chai, Dihan Li, Zexi Li, Yinda Xu, Yaxin Du, Yanfeng Wang, and Siheng Chen. 2024. OpenFedLLM: Training large language models on decentralized private data via federated learning. In ACM SIGKDD. 6137-6147.","journal-title":"ACM SIGKDD."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00052"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33031"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428258"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647464"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296515"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755814","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:07:17Z","timestamp":1765339637000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755814"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":69,"alternative-id":["10.1145\/3746027.3755814","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755814","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"}}]}}