{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:09:47Z","timestamp":1750219787487,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T00:00:00Z","timestamp":1672790400000},"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":[[2023,1,4]]},"DOI":"10.1145\/3570991.3571010","type":"proceedings-article","created":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T04:13:03Z","timestamp":1672891983000},"page":"208-212","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Designing a Vision Transformer based Enhanced Text Extractor for Product Images"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5125-6311","authenticated-orcid":false,"given":"Saptarshi","family":"Misra","sequence":"first","affiliation":[{"name":"Walmart Global Tech, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5598-7872","authenticated-orcid":false,"given":"Pranay","family":"Dugar","sequence":"additional","affiliation":[{"name":"Walmart Global Tech, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2513-6433","authenticated-orcid":false,"given":"Anirban","family":"Chatterjee","sequence":"additional","affiliation":[{"name":"Walmart Global Tech, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-203X","authenticated-orcid":false,"given":"Lalitdutt","family":"Parsai","sequence":"additional","affiliation":[{"name":"Walmart Global Tech, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0605-630X","authenticated-orcid":false,"given":"Kunal","family":"Banerjee","sequence":"additional","affiliation":[{"name":"Walmart Global Tech, India"}]}],"member":"320","published-online":{"date-parts":[[2023,1,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Jeonghun Baek Geewook Kim Junyeop Lee Sungrae Park Dongyoon Han Sangdoo Yun Seong\u00a0Joon Oh and Hwalsuk Lee. 2019. What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis. In ICCV. 4714\u20134722.","DOI":"10.1109\/ICCV.2019.00481"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Youngmin Baek Bado Lee Dongyoon Han Sangdoo Yun and Hwalsuk Lee. 2019. Character Region Awareness for Text Detection. In CVPR. 9365\u20139374.","DOI":"10.1109\/CVPR.2019.00959"},{"key":"e_1_3_2_1_3_1","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. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR abs\/2010.11929(2020)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Pranay Dugar Rajesh\u00a0Shreedhar Bhat Asit\u00a0Sharad Tarsode Uddipto Dutta Kunal Banerjee Anirban Chatterjee and Vijay\u00a0Srinivas Agneeswaran. 2021. From Pixels to Words: A Scalable Journey of Text Information from Product Images to Retail Catalog. In CIKM. 3787\u20133795.","DOI":"10.1145\/3459637.3481922"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Pranay Dugar Aditya Vikram Anirban Chatterjee Kunal Banerjee and Vijay Agneeswaran. 2022. Don\u2019t Miss the Fine Print! An Enhanced Framework to Extract Text from Low Resolution Images. In VISIGRAPP (5: VISAPP). 664\u2013671.","DOI":"10.5220\/0010971100003124"},{"key":"e_1_3_2_1_6_1","unstructured":"Shancheng Fang Hongtao Xie Yuxin Wang Zhendong Mao and Yongdong Zhang. 2021. Read Like Humans: Autonomous Bidirectional and Iterative Language Modeling for Scene Text Recognition. In CVPR. 7098\u20137107."},{"key":"e_1_3_2_1_7_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR. 770\u2013778."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Wei Liu Chaofeng Chen and Kwan-Yee\u00a0K Wong.2018. A character-aware neural network for distorted scene text recognition.. In AAAI.","DOI":"10.1609\/aaai.v32i1.12246"},{"key":"e_1_3_2_1_10_1","volume-title":"Star-net: A spatial attention residue network for scene text recognition. In BMVC, Vol.\u00a02.","author":"Liu Wei","year":"2016","unstructured":"Wei Liu, Chaofeng Chen, Kwan-Yee\u00a0K Wong, Zhizhong Su, and Junyu Han. 2016. Star-net: A spatial attention residue network for scene text recognition. In BMVC, Vol.\u00a02."},{"key":"e_1_3_2_1_11_1","unstructured":"Maithra Raghu Thomas Unterthiner Simon Kornblith Chiyuan Zhang and Alexey Dosovitskiy. 2021. Do Vision Transformers See Like Convolutional Neural Networks?. In NeurIPS. 12116\u201312128."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Baoguang Shi Xiang Bai and Cong Yao. 2017. An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition.. In TPAMI Vol.\u00a039. 2298\u20132304.","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Baoguang Shi Xinggang Wang Pengyuan Lyu Cong Yao and Xiang Bai. 2016. Robust scene text recognition with automatic rectification. In CVPR. 4168\u20134176.","DOI":"10.1109\/CVPR.2016.452"},{"key":"e_1_3_2_1_14_1","unstructured":"Vibhuti Vasisth and Nishtha Das. 2020. India: Country Of Origin To Be Specified On E-Commerce Websites For Product Listings. https:\/\/www.mondaq.com\/india\/international-trade-investment\/968240\/country-of-origin-to-be-specified-on-e-commerce-websites-for-product-listings. Accessed: 2021-07-08."}],"event":{"name":"CODS-COMAD 2023: 6th Joint International Conference on Data Science & Management of Data (10th ACM IKDD CODS and 28th COMAD)","acronym":"CODS-COMAD 2023","location":"Mumbai India"},"container-title":["Proceedings of the 6th Joint International Conference on Data Science & Management of Data (10th ACM IKDD CODS and 28th COMAD)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3570991.3571010","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3570991.3571010","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:53Z","timestamp":1750178273000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3570991.3571010"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,4]]},"references-count":14,"alternative-id":["10.1145\/3570991.3571010","10.1145\/3570991"],"URL":"https:\/\/doi.org\/10.1145\/3570991.3571010","relation":{},"subject":[],"published":{"date-parts":[[2023,1,4]]},"assertion":[{"value":"2023-01-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}