{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:04:27Z","timestamp":1765357467329,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3613435","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"9360-9364","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Zero-Shot Learning for Computer Vision Applications"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4619-3058","authenticated-orcid":false,"given":"Sandipan","family":"Sarma","sequence":"first","affiliation":[{"name":"Indian Institute of Technology, Guwahati, Guwahati, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Label-embedding for image classification","author":"Akata Zeynep","year":"2015","unstructured":"Zeynep Akata, Florent Perronnin, Zaid Harchaoui, and Cordelia Schmid. 2015. Label-embedding for image classification. IEEE transactions on pattern analysis and machine intelligence, Vol. 38, 7 (2015), 1425--1438."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533149"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6616"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"e_1_3_2_2_5_1","volume-title":"Cisco visual networking index (vni) complete forecast update","author":"Barnett Thomas","year":"2017","unstructured":"Thomas Barnett, Shruti Jain, Usha Andra, and Taru Khurana. 2018. Cisco visual networking index (vni) complete forecast update, 2017--2022. Americas\/EMEAR Cisco Knowledge Network (CKN) Presentation (2018), 1--30."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.575"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19909"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00746"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01338"},{"key":"e_1_3_2_2_10_1","volume-title":"Ramazan Gokberk Cinbis, and Nazli Ikizler-Cinbis","author":"Demirel Berkan","year":"2018","unstructured":"Berkan Demirel, Ramazan Gokberk Cinbis, and Nazli Ikizler-Cinbis. 2018. Zero-Shot Object Detection by Hybrid Region Embedding. In BMVC."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018303"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"e_1_3_2_2_13_1","volume-title":"Generative adversarial networks. arXiv preprint arXiv:1406.2661","author":"Goodfellow Ian J","year":"2014","unstructured":"Ian J Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial networks. arXiv preprint arXiv:1406.2661 (2014)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506179"},{"key":"e_1_3_2_2_15_1","volume-title":"Proceedings of the Asian Conference on Computer Vision.","author":"Hayat Nasir","year":"2020","unstructured":"Nasir Hayat, Munawar Hayat, Shafin Rahman, Salman Khan, Syed Waqas Zamir, and Fahad Shahbaz Khan. 2020. Synthesizing the Unseen for Zero-shot Object Detection. In Proceedings of the Asian Conference on Computer Vision."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413517"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01441"},{"key":"e_1_3_2_2_18_1","volume-title":"Prompting Visual-Language Models for Efficient Video Understanding. In European Conference on Computer Vision (ECCV).","author":"Ju Chen","year":"2022","unstructured":"Chen Ju, Tengda Han, Kunhao Zheng, Ya Zhang, and Weidi Xie. 2022. Prompting Visual-Language Models for Efficient Video Understanding. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"e_1_3_2_2_20_1","volume-title":"Attribute-based classification for zero-shot visual object categorization","author":"Lampert Christoph H","year":"2013","unstructured":"Christoph H Lampert, Hannes Nickisch, and Stefan Harmeling. 2013. Attribute-based classification for zero-shot visual object categorization. IEEE transactions on pattern analysis and machine intelligence, Vol. 36, 3 (2013), 453--465."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413600"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00152"},{"key":"e_1_3_2_2_25_1","volume-title":"Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"e_1_3_2_2_27_1","volume-title":"Cees G. M. Snoek, and Ling Shao.","author":"Narayan Sanath","year":"2020","unstructured":"Sanath Narayan, Akshita Gupta, Fahad Shahbaz Khan, Cees G. M. Snoek, and Ling Shao. 2020. Latent embedding feedback and discriminative features for zero-shot classification. In ECCV. 479--495."},{"key":"e_1_3_2_2_28_1","volume-title":"Proceedings, Part IV. Springer, 1--18","author":"Ni Bolin","year":"2022","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. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part IV. Springer, 1--18."},{"key":"e_1_3_2_2_29_1","first-page":"1","article-title":"The SUN Attribute Database","volume":"108","author":"Patterson Genevieve","year":"2014","unstructured":"Genevieve Patterson, Chen Xu, Hang Su, and James Hays. 2014. The SUN Attribute Database: Beyond Categories for Deeper Scene Understanding. IJCV, Vol. 108, 1--2 (2014), 59--81.","journal-title":"Beyond Categories for Deeper Scene Understanding. IJCV"},{"key":"e_1_3_2_2_30_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","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 International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_31_1","article-title":"Hubs in space: Popular nearest neighbors in high-dimensional data","volume":"11","author":"Radovanovic Milos","year":"2010","unstructured":"Milos Radovanovic, Alexandros Nanopoulos, and Mirjana Ivanovic. 2010. Hubs in space: Popular nearest neighbors in high-dimensional data. Journal of Machine Learning Research, Vol. 11, sept (2010), 2487--2531.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6868"},{"key":"e_1_3_2_2_33_1","volume-title":"Asian Conference on Computer Vision. Springer, 547--563","author":"Rahman Shafin","year":"2018","unstructured":"Shafin Rahman, Salman Khan, and Fatih Porikli. 2018. Zero-shot object detection: Learning to simultaneously recognize and localize novel concepts. In Asian Conference on Computer Vision. Springer, 547--563."},{"key":"e_1_3_2_2_34_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. 2016. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE transactions on pattern analysis and machine intelligence, Vol. 39, 6 (2016), 1137--1149."},{"key":"e_1_3_2_2_35_1","volume-title":"Resolving Semantic Confusions for Improved Zero-Shot Detection. In 33rd British Machine Vision Conference 2022, BMVC 2022","author":"Sarma Sandipan","year":"2022","unstructured":"Sandipan Sarma, SUSHIL KUMAR, and Arijit Sur. 2022. Resolving Semantic Confusions for Improved Zero-Shot Detection. In 33rd British Machine Vision Conference 2022, BMVC 2022, London, UK, November 21-24, 2022. BMVA Press. https:\/\/bmvc2022.mpi-inf.mpg.de\/0347.pdf"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603147"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00181"},{"key":"e_1_3_2_2_38_1","volume-title":"Technical Report CNS-TR-2011-001. California Institute of Technology.","author":"Wah C.","year":"2011","unstructured":"C. Wah., S. Branson, P. Welinder, P. Perona, and S. Belongie. 2011. The Caltech-UCSD Birds-200--2011 Dataset. Technical Report CNS-TR-2011-001. California Institute of Technology."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71249-9_6"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.12.127"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00101"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01167"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00717"},{"key":"e_1_3_2_2_44_1","volume-title":"End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge Distillation. arXiv preprint arXiv:2204.03541","author":"Wu Mingrui","year":"2022","unstructured":"Mingrui Wu, Jiaxin Gu, Yunhang Shen, Mingbao Lin, Chao Chen, Xiaoshuai Sun, and Rongrong Ji. 2022. End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge Distillation. arXiv preprint arXiv:2204.03541 (2022)."},{"key":"e_1_3_2_2_45_1","volume-title":"Zero-shot learning-A comprehensive evaluation of the good, the bad and the ugly","author":"Xian Yongqin","year":"2018","unstructured":"Yongqin Xian, Christoph H Lampert, Bernt Schiele, and Zeynep Akata. 2018. Zero-shot learning-A comprehensive evaluation of the good, the bad and the ugly. IEEE transactions on pattern analysis and machine intelligence, Vol. 41, 9 (2018), 2251--2265."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00212"},{"key":"e_1_3_2_2_47_1","volume-title":"Tel Aviv","author":"Yi Kai","year":"2022","unstructured":"Kai Yi, Xiaoqian Shen, Yunhao Gou, and Mohamed Elhoseiny. 2022. Exploring hierarchical graph representation for large-scale zero-shot image classification. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XX. Springer, 116--132."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613435","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3613435","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:52Z","timestamp":1755820852000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613435"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":47,"alternative-id":["10.1145\/3581783.3613435","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3613435","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}