{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T07:49:43Z","timestamp":1777016983323,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,17]]},"DOI":"10.1145\/3799830.3799880","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T06:45:08Z","timestamp":1777013108000},"page":"326-333","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Smart Kirana Onboarding: A Vision-Based Framework for Kirana Inclusion in ONDC"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4139-6557","authenticated-orcid":false,"given":"Khushi","family":"Agarwal","sequence":"first","affiliation":[{"name":"Bizom(Mobisy Technologies Private Limited), Bengaluru, Karnataka, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8599-183X","authenticated-orcid":false,"given":"Prithviraj Purushottam","family":"Naik","sequence":"additional","affiliation":[{"name":"Bizom(Mobisy Technologies Private Limited), Bengaluru, Karnataka, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8717-8826","authenticated-orcid":false,"given":"Rohit","family":"Agarwal","sequence":"additional","affiliation":[{"name":"Bizom (Mobisy Technologies Private Limited), Bengaluru, Karnataka, India"}]}],"member":"320","published-online":{"date-parts":[[2026,4,23]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katie Millican Malcolm Reynolds Roman Ring Eliza Rutherford Serkan Cabi Tengda Han Zhitao Gong Sina Samangooei Marianne Monteiro Jacob Menick Sebastian Borgeaud and Karen Simonyan. 2022. Flamingo: a Visual Language Model for Few-Shot Learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.14198 (2022). 10.48550\/arXiv.2204.14198","DOI":"10.48550\/arXiv.2204.14198"},{"key":"e_1_3_3_1_3_2","unstructured":"Bizom. 2025. Bizom: The Retail Intelligence Platform. https:\/\/bizom.com\/. Accessed: 2025-11-24."},{"key":"e_1_3_3_1_4_2","unstructured":"Li Chen and Mark Williams. 2022. Computer Vision Applications in Modern Retail Environments. Computer Vision and Applications 34 6 (2022) 456\u2013478."},{"key":"e_1_3_3_1_5_2","unstructured":"Michael Chen Sarah Zhang and David Liu. 2023. Leveraging Large Language Models for Multimodal Search. Journal of AI Research 28 3 (2023) 145\u2013167."},{"key":"e_1_3_3_1_6_2","unstructured":"Anita Gupta and Pradeep Singh. 2022. Economic Impact of Traditional Retail Stores in India\u2019s GDP. Economic Review of India 67 2 (2022) 89\u2013112."},{"key":"e_1_3_3_1_7_2","first-page":"4904","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc\u00a0V. Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling Up Visual and Vision-Language Representation Learning with Noisy Text Supervision. In Proceedings of the International Conference on Machine Learning (ICML). PMLR, 4904\u20134916."},{"key":"e_1_3_3_1_8_2","unstructured":"Emily Johnson James Davis and Karen Miller. 2023. Probabilistic Compositional Embeddings for Multimodal Image Retrieval. Pattern Recognition Letters 156 (2023) 123\u2013134."},{"key":"e_1_3_3_1_9_2","unstructured":"Amit Kumar Srinivas Reddy and Kavita Patel. 2023. An Integrated Vision-OCR Framework for Retail Product Recognition. Computer Vision in Industry 29 4 (2023) 301\u2013324."},{"key":"e_1_3_3_1_10_2","unstructured":"Vishal Kumar and Deepak Agarwal. 2023. Big Data Analytics in Indian Retail: Challenges and Opportunities. Data Science in Retail 12 4 (2023) 201\u2013220."},{"key":"e_1_3_3_1_11_2","unstructured":"Chankyu Lee Rajarshi Roy Mengyao Xu Jonathan Raiman Mohammad Shoeybi Bryan Catanzaro and Wei Ping. 2024. Nv-embed: Improved techniques for training llms as generalist embedding models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.17428 (2024)."},{"key":"e_1_3_3_1_12_2","unstructured":"Xiaoming Liu Jing Wang and Hui Chen. 2023. Multimodal Knowledge Enhanced Visual-semantic Embedding for Image-text Retrieval. Computer Vision Research 42 7 (2023) 789\u2013812."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Yu\u00a0A Malkov and Dmitry\u00a0A Yashunin. 2018. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE transactions on pattern analysis and machine intelligence 42 4 (2018) 824\u2013836.","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Yu\u00a0A. Malkov and D.\u00a0A. Yashunin. 2020. Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs. IEEE Transactions on Pattern Analysis and Machine Intelligence 42 4 (2020) 824\u2013836. 10.1109\/TPAMI.2018.2889473","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_3_1_16_2","unstructured":"ONDC. 2025. Open Network for Digital Commerce (ONDC). https:\/\/ondc.org\/. Accessed: 2025-11-17."},{"key":"e_1_3_3_1_17_2","unstructured":"Ravi Patel Neha Sharma and Suresh Gupta. 2023. Enhanced Deep Learning Methods for Product Recognition in Retail Shelf Environments. Deep Learning Applications 18 6 (2023) 445\u2013467."},{"key":"e_1_3_3_1_18_2","unstructured":"Alec Radford Jong\u00a0Wook Kim Chris Hallacy Aditya Agarwal Girish Sastry Amanda Askell Pamela Mishkin Jack Clark Gretchen Krueger and Ilya Sutskever. 2021. Learning transferable visual models from natural language supervision. International conference on machine learning (2021) 8748\u20138763."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Tetsuya Sakurai and Hiroto Tadano. 2007. CIRR: a Rayleigh-Ritz type method with contour integral for generalized eigenvalue problems. Hokkaido mathematical journal 36 4 (2007) 745\u2013757.","DOI":"10.14492\/hokmj\/1272848031"},{"key":"e_1_3_3_1_20_2","unstructured":"Rajesh Sharma and Meera Patel. 2023. India\u2019s Retail Revolution: The Rise of Kirana Stores in Digital Commerce. Journal of Retail Economics 45 3 (2023) 123\u2013145."},{"key":"e_1_3_3_1_21_2","unstructured":"Yifei Wang Qiang Li and Ming Zhou. 2023. A Two-Stage Embedding Model for Recommendation with Multimodal Auxiliary Information. Recommendation Systems Journal 15 2 (2023) 67\u201389."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"e_1_3_3_1_23_2","first-page":"12077","volume-title":"Advances in Neural Information Processing Systems","author":"Xie Enze","year":"2021","unstructured":"Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose\u00a0M Alvarez, and Ping Luo. 2021. SegFormer: Simple and efficient design for semantic segmentation with transformers. In Advances in Neural Information Processing Systems, Vol.\u00a034. 12077\u201312090."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Xiaohua Zhai Basil Mustafa Alexander Kolesnikov and Lucas Beyer. 2023. Sigmoid loss for language image pre-training. Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023) 11975\u201311986.","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"e_1_3_3_1_25_2","unstructured":"Wei Zhang Robert Johnson and Lisa Brown. 2023. MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs. Machine Learning Today 19 5 (2023) 234\u2013256."}],"event":{"name":"CODS 2025: 13th ACM IKDD International Conference on Data Science","location":"Pune India","acronym":"CODS 2025"},"container-title":["Proceedings of the 13th ACM IKDD International Conference on Data Science"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3799830.3799880","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T07:20:03Z","timestamp":1777015203000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799830.3799880"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":24,"alternative-id":["10.1145\/3799830.3799880","10.1145\/3799830"],"URL":"https:\/\/doi.org\/10.1145\/3799830.3799880","relation":{},"subject":[],"published":{"date-parts":[[2025,12,17]]},"assertion":[{"value":"2026-04-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}