{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:10:25Z","timestamp":1755825025610,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733361","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:31:04Z","timestamp":1750876264000},"page":"1018-1026","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["HyHE:Enhancing Image-Text Retrieval through Hyperbolic Hierarchical Embeddings"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8695-6581","authenticated-orcid":false,"given":"Aohui","family":"Miao","sequence":"first","affiliation":[{"name":"CCIIP Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4488-0102","authenticated-orcid":false,"given":"Wei","family":"Wei","sequence":"additional","affiliation":[{"name":"CCIIP Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_33"},{"key":"e_1_3_2_1_5_1","first-page":"7694","volume-title":"International Conference on Machine Learning","author":"Desai Karan","year":"2023","unstructured":"Karan Desai, Maximilian Nickel, Tanmay Rajpurohit, Justin Johnson, and Shanmukha Ramakrishna Vedantam. Hyperbolic image-text representations. In International Conference on Machine Learning, pages 7694--7731. PMLR, 2023."},{"key":"e_1_3_2_1_6_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2017.8053243"},{"key":"e_1_3_2_1_8_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020."},{"key":"e_1_3_2_1_9_1","volume-title":"Jamie Ryan Kiros, and Sanja Fidler. Vse: Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612","author":"Faghri Fartash","year":"2017","unstructured":"Fartash Faghri, David J Fleet, Jamie Ryan Kiros, and Sanja Fidler. Vse: Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612, 2017."},{"key":"e_1_3_2_1_10_1","volume-title":"Hyperbolic neural networks. Advances in neural information processing systems, 31","author":"Ganea Octavian","year":"2018","unstructured":"Octavian Ganea, Gary B\u00e9cigneul, and Thomas Hofmann. Hyperbolic neural networks. Advances in neural information processing systems, 31, 2018."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00661"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00108"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00010"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_15_1","volume-title":"Deep fragment embeddings for bidirectional image sentence mapping. Advances in neural information processing systems, 27","author":"Karpathy Andrej","year":"2014","unstructured":"Andrej Karpathy, Armand Joulin, and Li F Fei-Fei. Deep fragment embeddings for bidirectional image sentence mapping. Advances in neural information processing systems, 27, 2014."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00645"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658001"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612101"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/158"},{"key":"e_1_3_2_1_22_1","volume-title":"Selectively hard negative mining for alleviating gradient vanishing in image-text matching","author":"Li Zheng","year":"2024","unstructured":"Zheng Li, Caili Guo, Xin Wang, Zerun Feng, and Zhongtian Du. Selectively hard negative mining for alleviating gradient vanishing in image-text matching. IEEE Transactions on Circuits and Systems for Video Technology, 2024."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"e_1_3_2_1_30_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"Ren Shaoqing","year":"2016","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE transactions on pattern analysis and machine intelligence, 39(6):1137--1149, 2016."},{"key":"e_1_3_2_1_31_1","volume-title":"Hyperbolic word embeddings. arXiv preprint arXiv:1810.06546","author":"Tifrea Alexandru","year":"2018","unstructured":"Alexandru Tifrea, Gary B\u00e9cigneul, and Octavian-Eugen Ganea. Poincar\\'e glove: Hyperbolic word embeddings. arXiv preprint arXiv:1810.06546, 2018."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"e_1_3_2_1_36_1","volume-title":"Hyperbolic contrastive learning. arXiv preprint arXiv:2302.01409","author":"Yue Yun","year":"2023","unstructured":"Yun Yue, Fangzhou Lin, Kazunori D Yamada, and Ziming Zhang. Hyperbolic contrastive learning. arXiv preprint arXiv:2302.01409, 2023."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Chicago IL USA","acronym":"ICMR '25"},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733361","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:05:27Z","timestamp":1755749127000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733361"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":38,"alternative-id":["10.1145\/3731715.3733361","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733361","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}