{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T20:07:26Z","timestamp":1780344446290,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T00:00:00Z","timestamp":1657065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["TRR 169"],"award-info":[{"award-number":["TRR 169"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,6]]},"DOI":"10.1145\/3477495.3531666","type":"proceedings-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T15:12:13Z","timestamp":1657206733000},"page":"3245-3250","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Golden Retriever"],"prefix":"10.1145","author":[{"given":"Florian","family":"Schneider","sequence":"first","affiliation":[{"name":"Universit\u00e4t Hamburg, Hamburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris","family":"Biemann","sequence":"additional","affiliation":[{"name":"Universit\u00e4t Hamburg, Hamburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,7,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"e_1_3_2_1_3_1","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown , Benjamin Mann , Nick Ryder , Melanie Subbiah , Jared D. Kaplan , Prafulla Dhariwal , Arvind Neelakantan , Pranav Shyam , Girish Sastry , Amanda Askell , Sandhini Agarwal , Ariel Herbert-Voss , Gretchen Krueger , Tom Henighan , Rewon Child , Aditya Ramesh , Daniel Ziegler , Jeffrey Wu , Clemens Winter , Chris Hesse , Mark Chen , Eric Sigler , Mateusz Litwin , Scott Gray , Benjamin Chess , Jack Clark , Christopher Berner , Sam McCandlish , Alec Radford , Ilya Sutskever , and Dario Amodei . 2020 . Language Models are Few-Shot Learners . In Advances in Neural Information Processing Systems , Vol. 33 . Virtual , 1877--1901. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, Vol. 33. Virtual, 1877--1901."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-2001"},{"key":"e_1_3_2_1_5_1","volume-title":"UNITER: UNiversal Image-TExt Representation Learning. In European Conference on Computer Vision (ECCV). Online, 104--120","author":"Chen Yen-Chun","year":"2020","unstructured":"Yen-Chun Chen , Linjie Li , Licheng Yu , Ahmed El Kholy , Faisal Ahmed , Zhe Gan , Yu Cheng , and Jingjing Liu . 2020 . UNITER: UNiversal Image-TExt Representation Learning. In European Conference on Computer Vision (ECCV). Online, 104--120 . Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu. 2020. UNITER: UNiversal Image-TExt Representation Learning. In European Conference on Computer Vision (ECCV). Online, 104--120."},{"key":"e_1_3_2_1_6_1","volume-title":"The CLEF 2004 cross-language image retrieval track. In Proceedings of the 5th conference on Cross-Language Evaluation Forum: multilingual Information Access for Text, Speech and Images. 597--613","author":"Clough Paul","year":"2004","unstructured":"Paul Clough , Henning M\u00fcller , and Mark Sanderson . 2004 . The CLEF 2004 cross-language image retrieval track. In Proceedings of the 5th conference on Cross-Language Evaluation Forum: multilingual Information Access for Text, Speech and Images. 597--613 . Paul Clough, Henning M\u00fcller, and Mark Sanderson. 2004. The CLEF 2004 cross-language image retrieval track. In Proceedings of the 5th conference on Cross-Language Evaluation Forum: multilingual Information Access for Text, Speech and Images. 597--613."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2019 . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding . In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics . Minneapolis, MN, USA, 4171--4186. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics. Minneapolis, MN, USA, 4171--4186."},{"key":"e_1_3_2_1_8_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","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 . In 9th International Conference on Learning Representations, ICLR 2021 , Virtual Event, Austria , May 3-7, 2021. 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. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021."},{"key":"e_1_3_2_1_9_1","volume-title":"Sofie Van Landeghem, and Adriane Boyd","author":"Honnibal Matthew","year":"2020","unstructured":"Matthew Honnibal , Ines Montani , Sofie Van Landeghem, and Adriane Boyd . 2020 . spaCy: Industrial-strength Natural Language Processing in Python . https:\/\/spacy.io\/. Matthew Honnibal, Ines Montani, Sofie Van Landeghem, and Adriane Boyd. 2020. spaCy: Industrial-strength Natural Language Processing in Python. https:\/\/spacy.io\/."},{"key":"e_1_3_2_1_10_1","volume-title":"Billion-scale similarity search with GPUs","author":"Douze Jeff","year":"2019","unstructured":"Johnson, Jeff and Douze , Matthijs and J\u00e9gou , Herv\u00e9. 2019. Billion-scale similarity search with GPUs . IEEE Transactions on Big Data ( 2019 ). Johnson, Jeff and Douze, Matthijs and J\u00e9gou, Herv\u00e9. 2019. Billion-scale similarity search with GPUs. IEEE Transactions on Big Data (2019)."},{"key":"e_1_3_2_1_11_1","volume-title":"A statistical interpretation of term specificity and its application in retrieval. Journal of documentation","author":"Jones Karen Sp\u00e4rck","year":"1972","unstructured":"Karen Sp\u00e4rck Jones . 1972. A statistical interpretation of term specificity and its application in retrieval. Journal of documentation ( 1972 ). Karen Sp\u00e4rck Jones. 1972. A statistical interpretation of term specificity and its application in retrieval. Journal of documentation (1972)."},{"key":"e_1_3_2_1_12_1","volume-title":"Oscar: Object-Semantics Aligned Pre-training for Vision-and-Language Tasks. In European Conference on Computer Vision (ECCV). Online, 121--137","author":"Li Xiujun","year":"2020","unstructured":"Xiujun Li , Xi Yin , Chunyuan Li , Pengchuan Zhang , Xiaowei Hu , Lei Zhang , Lijuan Wang , Houdong Hu , Li Dong , Furu Wei , 2020 . Oscar: Object-Semantics Aligned Pre-training for Vision-and-Language Tasks. In European Conference on Computer Vision (ECCV). Online, 121--137 . Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, et al. 2020. Oscar: Object-Semantics Aligned Pre-training for Vision-and-Language Tasks. In European Conference on Computer Vision (ECCV). Online, 121--137."},{"key":"e_1_3_2_1_13_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Lin Tsung-Yi","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 European Conference on Computer Vision (ECCV) . Zurich, Switzerland, 740--755. 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 European Conference on Computer Vision (ECCV). Zurich, Switzerland, 740--755."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3451390"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2021"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Machine Learning (ICML). Online, 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 , 2021 . Learning Transferable Visual Models from Natural Language Supervision . In International Conference on Machine Learning (ICML). Online, 8748--8763 . 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 (ICML). Online, 8748--8763."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Gurevych Nils","year":"2019","unstructured":"Reimers, Nils and Gurevych , Iryna. 2019 . Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks . In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) . Hong Kong, China, 3973--3983. Reimers, Nils and Gurevych, Iryna. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Hong Kong, China, 3973--3983."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_1_19_1","volume-title":"Self-Supervised Multi-Modal Text-Image Retrieval Methods to Improve Human Reading. Master's thesis","author":"Schneider Florian","unstructured":"Florian Schneider . 2021. Self-Supervised Multi-Modal Text-Image Retrieval Methods to Improve Human Reading. Master's thesis . University of Hamburg. Florian Schneider. 2021. Self-Supervised Multi-Modal Text-Image Retrieval Methods to Improve Human Reading. Master's thesis. University of Hamburg."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop. Mexico City, Mexico (online).","author":"Schneider Florian","year":"2021","unstructured":"Florian Schneider , \u00d6zge Alacc am, Xintong Wang , and Chris Biemann . 2021 . Towards Multi-Modal Text-Image Retrieval to improve Human Reading . In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop. Mexico City, Mexico (online). Florian Schneider, \u00d6zge Alacc am, Xintong Wang, and Chris Biemann. 2021. Towards Multi-Modal Text-Image Retrieval to improve Human Reading. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop. Mexico City, Mexico (online)."},{"key":"e_1_3_2_1_21_1","volume-title":"International Conference on Machine Learning (ICML). Online, 10096--10106","author":"Tan Mingxing","year":"2021","unstructured":"Mingxing Tan and Quoc Le . 2021 . Efficientnetv2: Smaller models and faster training . In International Conference on Machine Learning (ICML). Online, 10096--10106 . Mingxing Tan and Quoc Le. 2021. Efficientnetv2: Smaller models and faster training. In International Conference on Machine Learning (ICML). Online, 10096--10106."},{"key":"e_1_3_2_1_22_1","volume-title":"Ontology based Visual Information Processing. Ph.,D. Dissertation","author":"Town Christopher Phillip","unstructured":"Christopher Phillip Town . 2004. Ontology based Visual Information Processing. Ph.,D. Dissertation . University of Cambridge . Christopher Phillip Town. 2004. Ontology based Visual Information Processing. Ph.,D. Dissertation. University of Cambridge."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_1_24_1","unstructured":"Zhou Yu Jing Li Tongan Luo and Jun Yu. 2020. A PyTorch Implementation of Bottom-Up-Attention. https:\/\/github.com\/MILVLG\/bottom-up-attention.pytorch.  Zhou Yu Jing Li Tongan Luo and Jun Yu. 2020. A PyTorch Implementation of Bottom-Up-Attention. https:\/\/github.com\/MILVLG\/bottom-up-attention.pytorch."}],"event":{"name":"SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Madrid Spain","acronym":"SIGIR '22","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531666","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477495.3531666","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:33Z","timestamp":1750188633000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531666"}},"subtitle":["A Real-Time Multi-Modal Text-Image Retrieval System with the Ability to Focus"],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":24,"alternative-id":["10.1145\/3477495.3531666","10.1145\/3477495"],"URL":"https:\/\/doi.org\/10.1145\/3477495.3531666","relation":{},"subject":[],"published":{"date-parts":[[2022,7,6]]},"assertion":[{"value":"2022-07-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}