{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T18:42:02Z","timestamp":1743100922312},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,25]]},"DOI":"10.1145\/3493612.3520453","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T18:18:27Z","timestamp":1651083507000},"page":"1-8","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["AIDE"],"prefix":"10.1145","author":[{"given":"Rachana","family":"Sreedhar","sequence":"first","affiliation":[{"name":"Wayfair Next"}]},{"given":"Nicole","family":"Tan","sequence":"additional","affiliation":[{"name":"Wayfair Next"}]},{"given":"Jingyue","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Kim","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Spencer","family":"Gregson","sequence":"additional","affiliation":[]},{"given":"Eli","family":"Moreta-Feliz","sequence":"additional","affiliation":[]},{"given":"Niveditha","family":"Samudrala","sequence":"additional","affiliation":[]},{"given":"Shrenik","family":"Sadalgi","sequence":"additional","affiliation":[]}],"member":"320","published-online":{"date-parts":[[2022,4,27]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2021. Amazon.com: Serta Rane Convertible Sofa Bed 66.1\" W x 33.1\" D x 29.5\" H Charcoal : Home & Kitchen. https:\/\/www.amazon.com\/Serta-RNE-3S-CC-SET-Collection-Convertible-Charcoal\/dp\/B07KD6VRK3\/ref=sr_1_3?crid=1L7I1F2I62FOD&keywords=Futon%2BSofa&nav_sdd=aps&qid=1642012348&sprefix=sofas&sr=8-3&th=1 2021. Amazon.com: Serta Rane Convertible Sofa Bed 66.1\" W x 33.1\" D x 29.5\" H Charcoal : Home & Kitchen. https:\/\/www.amazon.com\/Serta-RNE-3S-CC-SET-Collection-Convertible-Charcoal\/dp\/B07KD6VRK3\/ref=sr_1_3?crid=1L7I1F2I62FOD&keywords=Futon%2BSofa&nav_sdd=aps&qid=1642012348&sprefix=sofas&sr=8-3&th=1"},{"key":"e_1_3_2_2_2_1","unstructured":"2021. Azure Cognitive Services. https:\/\/azure.microsoft.com\/en-us\/services\/cognitive-services\/ 2021. Azure Cognitive Services. https:\/\/azure.microsoft.com\/en-us\/services\/cognitive-services\/"},{"key":"e_1_3_2_2_3_1","unstructured":"2021. Be My Eyes. https:\/\/www.bemyeyes.com\/ 2021. Be My Eyes. https:\/\/www.bemyeyes.com\/"},{"key":"e_1_3_2_2_4_1","unstructured":"2021. The Carroll Center for the Blind. https:\/\/carroll.org\/ 2021. The Carroll Center for the Blind. https:\/\/carroll.org\/"},{"key":"e_1_3_2_2_5_1","unstructured":"2021. TapTapSee. https:\/\/taptapseeapp.com\/ 2021. TapTapSee. https:\/\/taptapseeapp.com\/"},{"key":"e_1_3_2_2_6_1","unstructured":"Greg Brockman Mira Murati and Peter Welinder. 2020. OpenAI API. https:\/\/openai.com\/blog\/openai-api\/ Greg Brockman Mira Murati and Peter Welinder. 2020. OpenAI API. https:\/\/openai.com\/blog\/openai-api\/"},{"key":"e_1_3_2_2_7_1","volume-title":"Chiu and Eric Nichols","author":"Jason P.","year":"2016","unstructured":"Jason P. C. Chiu and Eric Nichols . 2016 . Named Entity Recognition with Bidirectional LSTM-CNNs . arXiv:1511.08308 [cs] (July 2016). http:\/\/arxiv.org\/abs\/1511.08308 arXiv: 1511.08308. Jason P. C. Chiu and Eric Nichols. 2016. Named Entity Recognition with Bidirectional LSTM-CNNs. arXiv:1511.08308 [cs] (July 2016). http:\/\/arxiv.org\/abs\/1511.08308 arXiv: 1511.08308."},{"key":"e_1_3_2_2_8_1","unstructured":"Christopher Elamri and Teun de Planque. 2016. Automated Neural Image Caption Generator for Visually Impaired People. Christopher Elamri and Teun de Planque. 2016. Automated Neural Image Caption Generator for Visually Impaired People."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313605"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308561.3353792"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376728"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174092"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"},{"key":"e_1_3_2_2_14_1","volume-title":"Image Scene Graph Generation (SGG) Benchmark. arXiv:2107.12604 [cs] (July","author":"Han Xiaotian","year":"2021","unstructured":"Xiaotian Han , Jianwei Yang , Houdong Hu , Lei Zhang , Jianfeng Gao , and Pengchuan Zhang . 2021. Image Scene Graph Generation (SGG) Benchmark. arXiv:2107.12604 [cs] (July 2021 ). http:\/\/arxiv.org\/abs\/2107.12604 arXiv:2107.12604. Xiaotian Han, Jianwei Yang, Houdong Hu, Lei Zhang, Jianfeng Gao, and Pengchuan Zhang. 2021. Image Scene Graph Generation (SGG) Benchmark. arXiv:2107.12604 [cs] (July 2021). http:\/\/arxiv.org\/abs\/2107.12604 arXiv:2107.12604."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"e_1_3_2_2_16_1","volume-title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks. arXiv:2004.06165 [cs] (July","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 , Yejin Choi , and Jianfeng Gao . 2020 . Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks. arXiv:2004.06165 [cs] (July 2020). http:\/\/arxiv.org\/abs\/2004.06165 arXiv:2004.06165. Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, Yejin Choi, and Jianfeng Gao. 2020. Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks. arXiv:2004.06165 [cs] (July 2020). http:\/\/arxiv.org\/abs\/2004.06165 arXiv:2004.06165."},{"key":"e_1_3_2_2_17_1","volume-title":"End-to-end Sequence Labeling via Bidirectional LSTM-CNNs-CRF. arXiv: 1603.01354 [cs, stat] (May","author":"Ma Xuezhe","year":"2016","unstructured":"Xuezhe Ma and Eduard Hovy . 2016. End-to-end Sequence Labeling via Bidirectional LSTM-CNNs-CRF. arXiv: 1603.01354 [cs, stat] (May 2016 ). http:\/\/arxiv.org\/abs\/1603.01354 arXiv: 1603.01354. Xuezhe Ma and Eduard Hovy. 2016. End-to-end Sequence Labeling via Bidirectional LSTM-CNNs-CRF. arXiv: 1603.01354 [cs, stat] (May 2016). http:\/\/arxiv.org\/abs\/1603.01354 arXiv: 1603.01354."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173633"},{"key":"e_1_3_2_2_19_1","unstructured":"Helen Petrie Chandra Harrison and Sundeep Dev. 2005. Describing images on the Web: a survey of current practice and prospects for the future. Helen Petrie Chandra Harrison and Sundeep Dev. 2005. Describing images on the Web: a survey of current practice and prospects for the future."},{"key":"e_1_3_2_2_20_1","unstructured":"Ashley Pilipiszyn. 2021. GPT-3 Powers the Next Generation of Apps. https:\/\/openai.com\/blog\/gpt-3-apps\/ Ashley Pilipiszyn. 2021. GPT-3 Powers the Next Generation of Apps. https:\/\/openai.com\/blog\/gpt-3-apps\/"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2014.6835988"},{"key":"e_1_3_2_2_22_1","unstructured":"Joe Rohrlich. 2021. BazaarVoice. https:\/\/www.bazaarvoice.com\/blog\/online-shoppers-need-to-see-it-to-believe-it-and-to-buy-it\/ Joe Rohrlich. 2021. BazaarVoice. https:\/\/www.bazaarvoice.com\/blog\/online-shoppers-need-to-see-it-to-believe-it-and-to-buy-it\/"},{"key":"e_1_3_2_2_23_1","volume-title":"Toward Scalable Social Alt Text: Conversational Crowdsourcing as a Tool for Refining Vision-to-Language Technology for the Blind. HCOMP","author":"Salisbury Elliot","year":"2017","unstructured":"Elliot Salisbury , Ece Kamar , and Meredith Ringel Morris . 2017. Toward Scalable Social Alt Text: Conversational Crowdsourcing as a Tool for Refining Vision-to-Language Technology for the Blind. HCOMP ( 2017 ). Elliot Salisbury, Ece Kamar, and Meredith Ringel Morris. 2017. Toward Scalable Social Alt Text: Conversational Crowdsourcing as a Tool for Refining Vision-to-Language Technology for the Blind. HCOMP (2017)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376404"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3441852.3471233"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3234695.3236337"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445547"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998364"},{"key":"e_1_3_2_2_29_1","volume-title":"VinVL: Revisiting Visual Representations in Vision-Language Models. arXiv:2101.00529 [cs] (March","author":"Zhang Pengchuan","year":"2021","unstructured":"Pengchuan Zhang , Xiujun Li , Xiaowei Hu , Jianwei Yang , Lei Zhang , Lijuan Wang , Yejin Choi , and Jianfeng Gao . 2021. VinVL: Revisiting Visual Representations in Vision-Language Models. arXiv:2101.00529 [cs] (March 2021 ). http:\/\/arxiv.org\/abs\/2101.00529 arXiv: 2101.00529. Pengchuan Zhang, Xiujun Li, Xiaowei Hu, Jianwei Yang, Lei Zhang, Lijuan Wang, Yejin Choi, and Jianfeng Gao. 2021. VinVL: Revisiting Visual Representations in Vision-Language Models. arXiv:2101.00529 [cs] (March 2021). http:\/\/arxiv.org\/abs\/2101.00529 arXiv: 2101.00529."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702437"}],"event":{"name":"W4A'22: 19th Web for All Conference","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGACCESS ACM Special Interest Group on Accessible Computing"],"location":"Lyon France","acronym":"W4A'22"},"container-title":["Proceedings of the 19th International Web for All Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3493612.3520453","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T10:41:07Z","timestamp":1684752067000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3493612.3520453"}},"subtitle":["automatic and accessible image descriptions for review imagery in online retail"],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":30,"alternative-id":["10.1145\/3493612.3520453","10.1145\/3493612"],"URL":"https:\/\/doi.org\/10.1145\/3493612.3520453","relation":{},"subject":[],"published":{"date-parts":[[2022,4,25]]},"assertion":[{"value":"2022-04-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}