{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T21:33:42Z","timestamp":1776116022293,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":86,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T00:00:00Z","timestamp":1728604800000},"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":[[2024,10,13]]},"DOI":"10.1145\/3654777.3676336","type":"proceedings-article","created":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T10:50:36Z","timestamp":1728643836000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["Memory Reviver: Supporting Photo-Collection Reminiscence for People with Visual Impairment via a Proactive Chatbot"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7642-9044","authenticated-orcid":false,"given":"Shuchang","family":"Xu","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5876-7219","authenticated-orcid":false,"given":"Chang","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0078-6238","authenticated-orcid":false,"given":"Zichen","family":"Liu","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Hong Kong University of Science and Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7239-3769","authenticated-orcid":false,"given":"Xiaofu","family":"Jin","sequence":"additional","affiliation":[{"name":"IIP(Computational Media and Arts), The Hong Kong University of Science and Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6268-1583","authenticated-orcid":false,"given":"Lin-Ping","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7515-3755","authenticated-orcid":false,"given":"Yukang","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Rochester, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3344-9694","authenticated-orcid":false,"given":"Huamin","family":"Qu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,11]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00129"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3234695.3236344"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1080\/07317110802677005"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517692"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445505"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866080"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00253"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01605"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3432196"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2481291"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308561.3353797"},{"key":"e_1_3_2_2_13_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems 33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared\u00a0D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877\u20131901."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10902-005-3889-4"},{"key":"e_1_3_2_2_15_1","volume-title":"The psychology of human-computer interaction","author":"Card K","unstructured":"Stuart\u00a0K Card. 2018. The psychology of human-computer interaction. Crc Press."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2020.1841438"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581012"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376569"},{"key":"e_1_3_2_2_19_1","volume-title":"Mobilevlm v2: Faster and stronger baseline for vision language model. arXiv preprint arXiv:2402.03766","author":"Chu Xiangxiang","year":"2024","unstructured":"Xiangxiang Chu, Limeng Qiao, Xinyu Zhang, Shuang Xu, Fei Wei, Yang Yang, Xiaofei Sun, Yiming Hu, Xinyang Lin, Bo Zhang, 2024. Mobilevlm v2: Faster and stronger baseline for vision language model. arXiv preprint arXiv:2402.03766 (2024)."},{"key":"e_1_3_2_2_20_1","volume-title":"Organization in autobiographical memory. Memory & cognition 15, 2","author":"Conway A","year":"1987","unstructured":"Martin\u00a0A Conway and Debra\u00a0A Bekerian. 1987. Organization in autobiographical memory. Memory & cognition 15, 2 (1987), 119\u2013132."},{"key":"e_1_3_2_2_21_1","volume-title":"Theories of memory","author":"Conway A","unstructured":"Martin\u00a0A Conway and David\u00a0C Rubin. 2019. The structure of autobiographical memory. In Theories of memory. Psychology Press, 103\u2013137."},{"key":"e_1_3_2_2_22_1","volume-title":"Reconstructing the past: personal memory technologies are not just personal and not just for memory. Human\u2013Computer Interaction 27, 1-2","author":"Crete-Nishihata Masashi","year":"2012","unstructured":"Masashi Crete-Nishihata, Ronald\u00a0M Baecker, Michael Massimi, Deborah Ptak, Rachelle Campigotto, Liam\u00a0D Kaufman, Adam\u00a0M Brickman, Gary\u00a0R Turner, Joshua\u00a0R Steinerman, and Sandra\u00a0E Black. 2012. Reconstructing the past: personal memory technologies are not just personal and not just for memory. Human\u2013Computer Interaction 27, 1-2 (2012), 92\u2013123."},{"key":"e_1_3_2_2_23_1","volume-title":"Factors predicting the use of technology: findings from the Center for Research and Education on Aging and Technology Enhancement (CREATE).Psychology and aging 21, 2","author":"Czaja J","year":"2006","unstructured":"Sara\u00a0J Czaja, Neil Charness, Arthur\u00a0D Fisk, Christopher Hertzog, Sankaran\u00a0N Nair, Wendy\u00a0A Rogers, and Joseph Sharit. 2006. Factors predicting the use of technology: findings from the Center for Research and Education on Aging and Technology Enhancement (CREATE).Psychology and aging 21, 2 (2006), 333."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00332"},{"key":"e_1_3_2_2_25_1","volume-title":"Be My Eyes Integrates Be My AI\u2122 into its First Contact Center with Stunning Results. https:\/\/www.bemyeyes.com\/blog\/introducing-microsofts-ai-powered-disability-answer-desk-on-be-my-eyes. [Online","author":"Eyes Be\u00a0My","year":"2024","unstructured":"Be\u00a0My Eyes. 2023. Be My Eyes Integrates Be My AI\u2122 into its First Contact Center with Stunning Results. https:\/\/www.bemyeyes.com\/blog\/introducing-microsofts-ai-powered-disability-answer-desk-on-be-my-eyes. [Online; accessed 3-March-2024]."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207594.2011.596541"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240624"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00103"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2481292"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.112"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502081"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606735"},{"key":"e_1_3_2_2_34_1","volume-title":"https:\/\/www.apple.com\/apple-intelligence\/. [Online","author":"Apple Inc.","year":"2024","unstructured":"Apple Inc.2024. Apple Intelligence. https:\/\/www.apple.com\/apple-intelligence\/. [Online; accessed 30-June-2024]."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2466137"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173998"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3532106.3533522"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6780"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501966"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3441852.3476548"},{"key":"e_1_3_2_2_41_1","volume-title":"Chatting makes perfect: Chat-based image retrieval. Advances in Neural Information Processing Systems 36","author":"Levy Matan","year":"2024","unstructured":"Matan Levy, Rami Ben-Ari, Nir Darshan, and Dani Lischinski. 2024. Chatting makes perfect: Chat-based image retrieval. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_2_42_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730\u201319742."},{"key":"e_1_3_2_2_43_1","volume-title":"International conference on machine learning. PMLR, 12888\u201312900","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. In International conference on machine learning. PMLR, 12888\u201312900."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3569476"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3371300.3383343"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445644"},{"key":"e_1_3_2_2_47_1","volume-title":"Pursuing happiness: The architecture of sustainable change. Review of general psychology 9, 2","author":"Lyubomirsky Sonja","year":"2005","unstructured":"Sonja Lyubomirsky, Kennon\u00a0M Sheldon, and David Schkade. 2005. Pursuing happiness: The architecture of sustainable change. Review of general psychology 9, 2 (2005), 111\u2013131."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300665"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173633"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3527450"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581302"},{"key":"e_1_3_2_2_52_1","volume-title":"Mobile design pattern gallery: UI patterns for smartphone apps. \" O\u2019Reilly Media","author":"Neil Theresa","unstructured":"Theresa Neil. 2014. Mobile design pattern gallery: UI patterns for smartphone apps. \" O\u2019Reilly Media, Inc.\"."},{"key":"e_1_3_2_2_53_1","unstructured":"Jakob Nielsen. 2005. Ten usability heuristics. (2005)."},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/1753326.1753635"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","unstructured":"Abhirama\u00a0Subramanyam Penamakuri Manish Gupta Mithun\u00a0Das Gupta and Anand Mishra. 2023. Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering. In IJCAI. ijcai.org. https:\/\/doi.org\/10.24963\/ijcai.2023\/146","DOI":"10.24963\/ijcai.2023\/146"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580921"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174033"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581145"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642152"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376404"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3441852.3471233"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-1781-2_80"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174178"},{"key":"e_1_3_2_2_65_1","volume-title":"Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805","author":"Team Gemini","year":"2023","unstructured":"Gemini Team, Rohan Anil, Sebastian Borgeaud, Yonghui Wu, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew\u00a0M Dai, Anja Hauth, 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642839"},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1"},{"key":"e_1_3_2_2_69_1","volume-title":"Augmenting language models with long-term memory. Advances in Neural Information Processing Systems 36","author":"Wang Weizhi","year":"2024","unstructured":"Weizhi Wang, Li Dong, Hao Cheng, Xiaodong Liu, Xifeng Yan, Jianfeng Gao, and Furu Wei. 2024. Augmenting language models with long-term memory. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642235"},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.1177\/0164027510364122"},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637364"},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581426"},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/637069.637096"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998364"},{"key":"e_1_3_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517582"},{"key":"e_1_3_2_2_77_1","volume-title":"International conference on machine learning. PMLR","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In International conference on machine learning. PMLR, 2048\u20132057."},{"key":"e_1_3_2_2_78_1","first-page":"1","article-title":"Virtual Paving: Rendering a smooth path for people with visual impairment through vibrotactile and audio feedback","volume":"4","author":"Xu Shuchang","year":"2020","unstructured":"Shuchang Xu, Ciyuan Yang, Wenhao Ge, Chun Yu, and Yuanchun Shi. 2020. Virtual Paving: Rendering a smooth path for people with visual impairment through vibrotactile and audio feedback. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 4, 3 (2020), 1\u201325.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_3_2_2_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3495003"},{"key":"e_1_3_2_2_80_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/744"},{"key":"e_1_3_2_2_81_1","volume-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision). arXiv preprint arXiv:2309.17421 9, 1","author":"Yang Zhengyuan","year":"2023","unstructured":"Zhengyuan Yang, Linjie Li, Kevin Lin, Jianfeng Wang, Chung-Ching Lin, Zicheng Liu, and Lijuan Wang. 2023. The dawn of lmms: Preliminary explorations with gpt-4v (ision). arXiv preprint arXiv:2309.17421 9, 1 (2023), 1."},{"key":"e_1_3_2_2_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445212"},{"key":"e_1_3_2_2_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01247"},{"key":"e_1_3_2_2_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3134756"},{"key":"e_1_3_2_2_85_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29946"},{"key":"e_1_3_2_2_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702437"}],"event":{"name":"UIST '24: The 37th Annual ACM Symposium on User Interface Software and Technology","location":"Pittsburgh PA USA","acronym":"UIST '24"},"container-title":["Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654777.3676336","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3654777.3676336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T21:12:03Z","timestamp":1754341923000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654777.3676336"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,11]]},"references-count":86,"alternative-id":["10.1145\/3654777.3676336","10.1145\/3654777"],"URL":"https:\/\/doi.org\/10.1145\/3654777.3676336","relation":{},"subject":[],"published":{"date-parts":[[2024,10,11]]},"assertion":[{"value":"2024-10-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}