{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:40:08Z","timestamp":1755870008036,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,18]]},"DOI":"10.1145\/3731120.3744617","type":"proceedings-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T13:34:06Z","timestamp":1752845646000},"page":"470-477","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Answering Multimodal Exclusion Queries with Lightweight Sparse Disentangled Representations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6663-5226","authenticated-orcid":false,"given":"Prachi","family":"J","sequence":"first","affiliation":[{"name":"Indian Institute of Technology, Delhi, New Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8146-4100","authenticated-orcid":false,"given":"Sumit","family":"Bhatia","sequence":"additional","affiliation":[{"name":"Media and Data Science Research Lab, Adobe Systems, Noida, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3949-2175","authenticated-orcid":false,"given":"Srikanta","family":"Bedathur","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology, Delhi, New Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Yang Bai Xiaoguang Li Gang Wang Chaoliang Zhang Lifeng Shang Jun Xu Zhaowei Wang Fangshan Wang and Qun Liu. 2020. SparTerm: Learning Termbased Sparse Representation for Fast Text Retrieval. arXiv:2010.00768 [cs.IR] https:\/\/arxiv.org\/abs\/2010.00768"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"e_1_3_2_1_3_1","volume-title":"Fl\u00e1vio du Pin Calmon, and Himabindu Lakkaraju","author":"Bhalla Usha","year":"2024","unstructured":"Usha Bhalla, Alexander X. Oesterling, Suraj Srinivas, Fl\u00e1vio du Pin Calmon, and Himabindu Lakkaraju. 2024. Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE). ArXiv abs\/2402.10376 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267740469"},{"key":"e_1_3_2_1_4_1","unstructured":"Nhat-Tan Bui Dinh-Hieu Hoang Quoc-Huy Trinh Minh-Triet Tran Truong Nguyen and Susan Gauch. 2024. NeIn: Telling What You Don't Want. arXiv:2409.06481 [cs.CV] https:\/\/arxiv.org\/abs\/2409.06481"},{"key":"e_1_3_2_1_5_1","unstructured":"Chris Burgess and Hyunjik Kim. 2018. 3D Shapes Dataset. https:\/\/github.com\/deepmind\/3dshapes-dataset\/."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327144.3327186"},{"key":"e_1_3_2_1_7_1","unstructured":"Thibault Formal Carlos Lassance Benjamin Piwowarski and St\u00e9phane Clinchant. 2021. SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval. arXiv:2109.10086 [cs.IR] https:\/\/arxiv.org\/abs\/2109.10086"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463098"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.531"},{"key":"e_1_3_2_1_10_1","volume-title":"On the Binding Problem in Artificial Neural Networks. ArXiv abs\/2012.05208","author":"Greff Klaus","year":"2020","unstructured":"Klaus Greff, Sjoerd van Steenkiste, and J\u00fcrgen Schmidhuber. 2020. On the Binding Problem in Artificial Neural Networks. ArXiv abs\/2012.05208 (2020). https:\/\/api.semanticscholar.org\/CorpusID:228063925"},{"key":"e_1_3_2_1_11_1","unstructured":"Irina Higgins David Amos David Pfau Sebastien Racaniere Loic Matthey Danilo Rezende and Alexander Lerchner. 2018. Towards a Definition of Disentangled Representations. arXiv:1812.02230 [cs.LG] https:\/\/arxiv.org\/abs\/1812.02230"},{"key":"e_1_3_2_1_12_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Sy2fzU9gl","author":"Higgins Irina","year":"2017","unstructured":"Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, and Alexander Lerchner. 2017. beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Sy2fzU9gl"},{"key":"e_1_3_2_1_13_1","volume-title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=F76bwRSLeK","author":"Huben Robert","year":"2024","unstructured":"Robert Huben, Hoagy Cunningham, Logan Riggs Smith, Aidan Ewart, and Lee Sharkey. 2024. Sparse Autoencoders Find Highly Interpretable Features in Language Models. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=F76bwRSLeK"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141267"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"2658","author":"Kim Hyunjik","year":"2018","unstructured":"Hyunjik Kim and Andriy Mnih. 2018. Disentangling by Factorising. In Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 80), Jennifer Dy and Andreas Krause (Eds.). PMLR, 2649-2658. https:\/\/proceedings.mlr.press\/v80\/kim18b.html"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475448"},{"key":"e_1_3_2_1_17_1","unstructured":"Minyoung Kim Yuting Wang Pritish Sahu and Vladimir Pavlovic. 2019. Relevance Factor VAE: Learning and Identifying Disentangled Factors. arXiv:1902.01568 [cs.LG] https:\/\/arxiv.org\/abs\/1902.01568"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","unstructured":"Mihee Lee and Vladimir Pavlovic. 2021. Private-Shared Disentangled Multimodal VAE for Learning of Latent Representations. 1692-1700. doi:10.1109\/CVPRW53098.2021.00185","DOI":"10.1109\/CVPRW53098.2021.00185"},{"key":"e_1_3_2_1_19_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. arXiv:2201.12086 [cs.CV] https:\/\/arxiv.org\/abs\/2201.12086","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. arXiv:2201.12086 [cs.CV] https:\/\/arxiv.org\/abs\/2201.12086"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.389"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01029"},{"key":"e_1_3_2_1_23_1","volume-title":"andWenwu Zhu","author":"Ma Jianxin","year":"2019","unstructured":"Jianxin Ma, Chang Zhou, Peng Cui, Hongxia Yang, andWenwu Zhu. 2019. Learning Disentangled Representations for Recommendation. arXiv:1910.14238 [cs.LG] https:\/\/arxiv.org\/abs\/1910.14238"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","unstructured":"Chaitanya Malaviya Peter Shaw Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2023. QUEST: A Retrieval Dataset of Entity-Seeking Queries with Implicit Set Operations. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Anna Rogers Jordan Boyd-Graber and Naoaki Okazaki (Eds.). Association for Computational Linguistics Toronto Canada 14032-14047. doi:10.18653\/v1\/2023.acl-long.784","DOI":"10.18653\/v1\/2023.acl-long.784"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03936-z"},{"key":"e_1_3_2_1_26_1","unstructured":"Andrew Ng et al. [n. d.]. Sparse autoencoder ([n.d.])."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Thong Nguyen Mariya Hendriksen Andrew Yates and Maarten de Rijke. 2024. Multimodal Learned Sparse Retrieval with Probabilistic Expansion Control. arXiv:2402.17535 [cs.IR] https:\/\/arxiv.org\/abs\/2402.17535","DOI":"10.1007\/978-3-031-56060-6_29"},{"key":"e_1_3_2_1_28_1","unstructured":"Charles O'Neill Christine Ye Kartheik G. Iyer and John F Wu. 2024. Towards Interpretable Scientific Foundation Models: Sparse Autoencoders for Disentangling Dense Embeddings of Scientific Concepts. In Neurips 2024 Workshop Foundation Models for Science: Progress Opportunities and Challenges. https:\/\/openreview.net\/forum?id=mPq3R6jdtD"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Fabio Pizzati Pietro Cerri and Raoul de Charette. 2020. Model-based occlusion disentanglement for image-to-image translation. arXiv:2004.01071 [cs.CV] https:\/\/arxiv.org\/abs\/2004.01071","DOI":"10.1007\/978-3-030-58565-5_27"},{"key":"e_1_3_2_1_31_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever.","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. arXiv:2103.00020 [cs.CV] https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"e_1_3_2_1_32_1","volume-title":"CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation. ArXiv abs\/2211.00295","author":"Ravichander Abhilasha","year":"2022","unstructured":"Abhilasha Ravichander, Matt Gardner, and Ana Marasovi?. 2022. CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation. ArXiv abs\/2211.00295 (2022). https:\/\/api.semanticscholar.org\/CorpusID: 253244137"},{"key":"e_1_3_2_1_33_1","volume-title":"Image Alt-text Dataset For Automatic Image Captioning. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:51876975","author":"Sharma Piyush","year":"2018","unstructured":"Piyush Sharma, Nan Ding, Sebastian Goodman, and Radu Soricut. 2018. Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:51876975"},{"key":"e_1_3_2_1_34_1","unstructured":"Jaisidh Singh Ishaan Shrivastava Mayank Vatsa Richa Singh and Aparna Bharati. 2024. Learn ''No'' to Say ''Yes'' Better: Improving Vision-Language Models via Negations. arXiv:2403.20312 [cs.CV] https:\/\/arxiv.org\/abs\/2403.20312"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3722553"},{"key":"e_1_3_2_1_36_1","volume-title":"Hovy","author":"Subramanian Anant","year":"2017","unstructured":"Anant Subramanian, Danish Pruthi, Harsh Jhamtani, Taylor Berg-Kirkpatrick, and Eduard H. Hovy. 2017. SPINE: SParse Interpretable Neural Embeddings. ArXiv abs\/1711.08792 (2017). https:\/\/api.semanticscholar.org\/CorpusID:19143983"},{"key":"e_1_3_2_1_37_1","unstructured":"Xin Wang Hong Chen Si'ao Tang Zihao Wu and Wenwu Zhu. 2024. Disentangled Representation Learning. arXiv:2211.11695 [cs.LG] https:\/\/arxiv.org\/abs\/2211.11695"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Xin Wang Hong Chen Zihao Wu Wenwu Zhu et al. 2024. Disentangled representation learning. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024).","DOI":"10.1109\/TPAMI.2024.3420937"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-long.139"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3657619"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Boqiang Zhang Hongtao Xie Zuan Gao and Yuxin Wang. 2024. Choose What You Need: Disentangled Representation Learning for Scene Text Recognition Removal and Editing. arXiv:2405.04377 [cs.CV] https:\/\/arxiv.org\/abs\/2405.04377","DOI":"10.1109\/CVPR52733.2024.02679"},{"key":"e_1_3_2_1_42_1","unstructured":"Wenhao Zhang Mengqi Zhang Shiguang Wu Jiahuan Pei Zhaochun Ren Maarten de Rijke Zhumin Chen and Pengjie Ren. 2024. ExcluIR: Exclusionary Neural Information Retrieval. arXiv:2404.17288 [cs.IR] https:\/\/arxiv.org\/abs\/2404.17288"},{"key":"e_1_3_2_1_43_1","unstructured":"Jiawei Zhou Xiaoguang Li Lifeng Shang Xin Jiang Qun Liu and Lei Chen. 2024. Retrieval-based Disentangled Representation Learning with Natural Language Supervision. arXiv:2212.07699 [cs.CL] https:\/\/arxiv.org\/abs\/2212.07699"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.175"}],"event":{"name":"ICTIR '25: International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Padua Italy","acronym":"ICTIR '25"},"container-title":["Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731120.3744617","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:20:25Z","timestamp":1755868825000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731120.3744617"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,18]]},"references-count":44,"alternative-id":["10.1145\/3731120.3744617","10.1145\/3731120"],"URL":"https:\/\/doi.org\/10.1145\/3731120.3744617","relation":{},"subject":[],"published":{"date-parts":[[2025,7,18]]},"assertion":[{"value":"2025-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}