{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:30:34Z","timestamp":1784399434362,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":30,"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":[{"name":"National Natural Science Foundation of China","award":["62206123, 62176170"],"award-info":[{"award-number":["62206123, 62176170"]}]},{"name":"Guangxi Natural Science Foundation","award":["2024GXNSFAA010484"],"award-info":[{"award-number":["2024GXNSFAA010484"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681073","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"2545-2553","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards Labeling-free Fine-grained Animal Pose Estimation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9036-7791","authenticated-orcid":false,"given":"Dan","family":"Zeng","sequence":"first","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0469-8293","authenticated-orcid":false,"given":"Yu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4587-513X","authenticated-orcid":false,"given":"Shuiwang","family":"Li","sequence":"additional","affiliation":[{"name":"Guilin University of Technology, Guilin, Guangxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4651-7163","authenticated-orcid":false,"given":"Qijun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Sichuan University, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6510-0964","authenticated-orcid":false,"given":"Qiaomu","family":"Shen","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Zhuhai, Zhuhai, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8424-0092","authenticated-orcid":false,"given":"Bo","family":"Tang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"e_1_3_2_2_2_1","volume-title":"DeepBehavior: A deep learning toolbox for automated analysis of animal and human behavior imaging data. Frontiers in systems neuroscience","author":"Arac Ahmet","year":"2019","unstructured":"Ahmet Arac, Pingping Zhao, Bruce H Dobkin, S Thomas Carmichael, and Peyman Golshani. 2019. DeepBehavior: A deep learning toolbox for automated analysis of animal and human behavior imaging data. Frontiers in systems neuroscience, Vol. 13 (2019), 20."},{"key":"e_1_3_2_2_3_1","volume-title":"Proceedings, Part XI 16","author":"Biggs Benjamin","year":"2020","unstructured":"Benjamin Biggs, Oliver Boyne, James Charles, Andrew Fitzgibbon, and Roberto Cipolla. 2020. Who left the dogs out? 3d animal reconstruction with expectation maximization in the loop. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XI 16. Springer, 195--211."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00959"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 2151--2160","author":"Pero Luca Del","year":"2015","unstructured":"Luca Del Pero, Susanna Ricco, Rahul Sukthankar, and Vittorio Ferrari. 2015. Articulated motion discovery using pairs of trajectories. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2151--2160."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.47994"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478325"},{"key":"e_1_3_2_2_9_1","volume-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels. Advances in neural information processing systems","author":"Han Bo","year":"2018","unstructured":"Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, and Masashi Sugiyama. 2018. Co-teaching: Robust training of deep neural networks with extremely noisy labels. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_2_10_1","volume-title":"Animal pose estimation: A closer look at the state-of-the-art, existing gaps and opportunities. Computer Vision and Image Understanding","author":"Jiang Le","year":"2022","unstructured":"Le Jiang, Caleb Lee, Divyang Teotia, and Sarah Ostadabbas. 2022. Animal pose estimation: A closer look at the state-of-the-art, existing gaps and opportunities. Computer Vision and Image Understanding (2022), 103483."},{"key":"e_1_3_2_2_11_1","volume-title":"Workshop on challenges in representation learning, ICML","volume":"3","author":"Dong-Hyun","unstructured":"Dong-Hyun Lee et al. 2013. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Workshop on challenges in representation learning, ICML, Vol. 3. Atlanta, 896."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00153"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01647"},{"key":"e_1_3_2_2_14_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Li Guangrui","year":"2022","unstructured":"Guangrui Li, Yifan Sun, Zongxin Yang, and Yi Yang. 2022. Decompose to Generalize: Species-Generalized Animal Pose Estimation. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_2_15_1","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part V 13. Springer, 740--755."},{"key":"e_1_3_2_2_16_1","volume-title":"Catflw: Cat facial landmarks in the wild dataset. arXiv preprint arXiv:2305.04232","author":"Martvel George","year":"2023","unstructured":"George Martvel, Nareed Farhat, Ilan Shimshoni, and Anna Zamansky. 2023. Catflw: Cat facial landmarks in the wild dataset. arXiv preprint arXiv:2305.04232 (2023)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00190"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/jwmg.120"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01240"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01844"},{"key":"e_1_3_2_2_21_1","volume-title":"Learning semantic-aligned action representation","author":"Ni Bingbing","year":"2017","unstructured":"Bingbing Ni, Teng Li, and Xiaokang Yang. 2017. Learning semantic-aligned action representation. IEEE transactions on neural networks and learning systems, Vol. 29, 8 (2017), 3715--3725."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01139"},{"key":"e_1_3_2_2_23_1","volume-title":"SyDog: A synthetic dog dataset for improved 2D pose estimation. arXiv preprint arXiv:2108.00249","author":"Shooter Moira","year":"2021","unstructured":"Moira Shooter, Charles Malleson, and Adrian Hilton. 2021. SyDog: A synthetic dog dataset for improved 2D pose estimation. arXiv preprint arXiv:2108.00249 (2021)."},{"key":"e_1_3_2_2_24_1","volume-title":"Alexey Kurakin, and Chun-Liang Li.","author":"Sohn Kihyuk","year":"2020","unstructured":"Kihyuk Sohn, David Berthelot, Nicholas Carlini, Zizhao Zhang, Han Zhang, Colin A Raffel, Ekin Dogus Cubuk, Alexey Kurakin, and Chun-Liang Li. 2020. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in neural information processing systems, Vol. 33 (2020), 596--608."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350609"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"e_1_3_2_2_28_1","volume-title":"Coarse-to-fine pseudo-labeling guided meta-learning for few-shot classification. arXiv preprint arXiv:2007.05675","author":"Yang Jinhai","year":"2020","unstructured":"Jinhai Yang, Hua Yang, and Lin Chen. 2020. Coarse-to-fine pseudo-labeling guided meta-learning for few-shot classification. arXiv preprint arXiv:2007.05675 (2020)."},{"key":"e_1_3_2_2_29_1","first-page":"17301","article-title":"Apt-36k: A large-scale benchmark for animal pose estimation and tracking","volume":"35","author":"Yang Yuxiang","year":"2022","unstructured":"Yuxiang Yang, Junjie Yang, Yufei Xu, Jing Zhang, Long Lan, and Dacheng Tao. 2022. Apt-36k: A large-scale benchmark for animal pose estimation and tracking. Advances in Neural Information Processing Systems, Vol. 35 (2022), 17301--17313.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_30_1","volume-title":"Ap-10k: A benchmark for animal pose estimation in the wild. arXiv preprint arXiv:2108.12617","author":"Yu Hang","year":"2021","unstructured":"Hang Yu, Yufei Xu, Jing Zhang, Wei Zhao, Ziyu Guan, and Dacheng Tao. 2021. Ap-10k: A benchmark for animal pose estimation in the wild. arXiv preprint arXiv:2108.12617 (2021)."}],"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\/3664647.3681073","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:52Z","timestamp":1750294672000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681073"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":30,"alternative-id":["10.1145\/3664647.3681073","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681073","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"}}]}}