{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T10:15:14Z","timestamp":1776420914617,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":102,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3772318.3791528","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:12:33Z","timestamp":1776053553000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["EchoScriptor: Automatic Lifelogging Narratives via Activity-Based Audio\u2013Language Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0729-8471","authenticated-orcid":false,"given":"Kaylee Yaxuan","family":"Li","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4629-029X","authenticated-orcid":false,"given":"Xinghao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0478-4028","authenticated-orcid":false,"given":"Haizhong","family":"Zheng","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0086-8777","authenticated-orcid":false,"given":"Kang G.","family":"Shin","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8046-0538","authenticated-orcid":false,"given":"Alanson","family":"P. Sample","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Sharath Adavanne Archontis Politis Joonas Nikunen and Tuomas Virtanen. 2018. Sound event localization and detection of overlapping sources using convolutional recurrent neural networks. IEEE Journal of Selected Topics in Signal Processing 13 1 (2018) 34\u201348.","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"e_1_3_3_2_3_2","unstructured":"Andrea Agostinelli Timo\u00a0I Denk Zal\u00e1n Borsos Jesse Engel Mauro Verzetti Antoine Caillon Qingqing Huang Aren Jansen Adam Roberts Marco Tagliasacchi et\u00a0al. 2023. Musiclm: Generating music from text. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2301.11325 (2023)."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Mehmet\u00a0Ali Arabac\u0131 Fatih \u00d6zkan Elif Surer Peter Jan\u010dovi\u010d and Alptekin Temizel. 2021. Multi-modal egocentric activity recognition using multi-kernel learning. Multimedia Tools and Applications 80 11 (2021) 16299\u201316328.","DOI":"10.1007\/s11042-020-08789-7"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/1614320.1614350"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511759185"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Esma\u00a0Mansouri Benssassi Juan-Carlos Gomez LouAnne\u00a0E Boyd Gillian\u00a0R Hayes and Juan Ye. 2018. Wearable assistive technologies for autism: opportunities and challenges. IEEE Pervasive Computing 17 2 (2018) 11\u201321.","DOI":"10.1109\/MPRV.2018.022511239"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Sejal Bhalla Mayank Goel and Rushil Khurana. 2021. Imu2doppler: Cross-modal domain adaptation for doppler-based activity recognition using imu data. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 5 4 (2021) 1\u201320.","DOI":"10.1145\/3494994"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Marc Bolanos Mariella Dimiccoli and Petia Radeva. 2016. Toward storytelling from visual lifelogging: An overview. IEEE Transactions on Human-Machine Systems 47 1 (2016) 77\u201390.","DOI":"10.1109\/THMS.2016.2616296"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Marc Brysbaert and Micha\u00ebl Stevens. 2018. Power analysis and effect size in mixed effects models: A tutorial. Journal of cognition 1 1 (2018) 9.","DOI":"10.5334\/joc.10"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858498"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","unstructured":"Wenqiang Chen Jiaxuan Cheng Leyao Wang Wei Zhao and Wojciech Matusik. 2024. Sensor2Text: Enabling Natural Language Interactions for Daily Activity Tracking Using Wearable Sensors. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 8 4 Article 192 (Nov. 2024) 26\u00a0pages. 10.1145\/3699747","DOI":"10.1145\/3699747"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Zhe Chen Chao Cai Tianyue Zheng Jun Luo Jie Xiong and Xin Wang. 2021. RF-based human activity recognition using signal adapted convolutional neural network. IEEE Transactions on Mobile Computing 22 1 (2021) 487\u2013499.","DOI":"10.1109\/TMC.2021.3073969"},{"key":"e_1_3_3_2_15_2","unstructured":"Bhawana Chhaglani Sarmistha\u00a0Sarna Gomasta Yuvraj Agarwal Jeremy Gummeson and Prashant Shenoy. 2025. FeatureSense: Protecting Speaker Attributes in Always-On Audio Sensing System. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.24115 (2025)."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Junho Choi Chang Choi Hoon Ko and Pankoo Kim. 2016. Intelligent healthcare service using health lifelog analysis. Journal of medical systems 40 8 (2016) 188.","DOI":"10.1007\/s10916-016-0534-1"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Caterina Cinel Cathleen Cortis\u00a0Mack and Geoff Ward. 2018. Towards augmented human memory: Retrieval-induced forgetting and retrieval practice in an interactive end-of-day review.Journal of Experimental Psychology: General 147 5 (2018) 632.","DOI":"10.1037\/xge0000441"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Vladimir Despotovic Peter Pocta and Andrej Zgank. 2022. Audio-based Active and Assisted Living: A review of selected applications and future trends. Computers in Biology and Medicine 149 (2022) 106027.","DOI":"10.1016\/j.compbiomed.2022.106027"},{"key":"e_1_3_3_2_20_2","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers)","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171\u20134186."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"e_1_3_3_2_23_2","first-page":"1068","volume-title":"International conference on machine learning","author":"Engel Jesse","year":"2017","unstructured":"Jesse Engel, Cinjon Resnick, Adam Roberts, Sander Dieleman, Mohammad Norouzi, Douglas Eck, and Karen Simonyan. 2017. Neural audio synthesis of musical notes with wavenet autoencoders. In International conference on machine learning. PMLR, 1068\u20131077."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/2800835.2801643"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Irfan\u00a0A Essa. 2002. Ubiquitous sensing for smart and aware environments. IEEE personal communications 7 5 (2002) 47\u201349.","DOI":"10.1109\/98.878538"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Alexander\u00a0R Fabbri Wojciech Kry\u015bci\u0144ski Bryan McCann Caiming Xiong Richard Socher and Dragomir Radev. 2021. Summeval: Re-evaluating summarization evaluation. Transactions of the Association for Computational Linguistics 9 (2021) 391\u2013409.","DOI":"10.1162\/tacl_a_00373"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Emilio Ferrara. 2024. Large language models for wearable sensor-based human activity recognition health monitoring and behavioral modeling: A survey of early trends datasets and challenges. Sensors 24 15 (2024) 5045.","DOI":"10.3390\/s24155045"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.gem-1.3"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1085"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Biying Fu Naser Damer Florian Kirchbuchner and Arjan Kuijper. 2020. Sensing technology for human activity recognition: A comprehensive survey. Ieee Access 8 (2020) 83791\u201383820.","DOI":"10.1109\/ACCESS.2020.2991891"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/2505821.2505830"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"e_1_3_3_2_33_2","unstructured":"Shayan Gharib Konstantinos Drossos Emre Cakir Dmitriy Serdyuk and Tuomas Virtanen. 2018. Unsupervised adversarial domain adaptation for acoustic scene classification. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1808.05777 (2018)."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"crossref","unstructured":"Sreyan Ghosh Sonal Kumar Ashish Seth Chandra Kiran\u00a0Reddy Evuru Utkarsh Tyagi S Sakshi Oriol Nieto Ramani Duraiswami and Dinesh Manocha. 2024. Gama: A large audio-language model with advanced audio understanding and complex reasoning abilities. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.11768 (2024).","DOI":"10.18653\/v1\/2024.emnlp-main.361"},{"key":"e_1_3_3_2_35_2","unstructured":"Arushi Goel Sreyan Ghosh Jaehyeon Kim Sonal Kumar Zhifeng Kong Sang-gil Lee Chao-Han\u00a0Huck Yang Ramani Duraiswami Dinesh Manocha Rafael Valle et\u00a0al. 2025. Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.08128 (2025)."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Yuan Gong Yu-An Chung and James Glass. 2021. Ast: Audio spectrogram transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2104.01778 (2021).","DOI":"10.21437\/Interspeech.2021-698"},{"key":"e_1_3_3_2_37_2","unstructured":"Yuan Gong Hongyin Luo Alexander\u00a0H Liu Leonid Karlinsky and James Glass. 2023. Listen think and understand. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.10790 (2023)."},{"key":"e_1_3_3_2_38_2","unstructured":"Yuan Gong Andrew Rouditchenko Alexander\u00a0H Liu David Harwath Leonid Karlinsky Hilde Kuehne and James Glass. 2022. Contrastive audio-visual masked autoencoder. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.07839 (2022)."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Morgan Harvey Marc Langheinrich and Geoff Ward. 2016. Remembering through lifelogging: A survey of human memory augmentation. Pervasive and Mobile Computing 27 (2016) 14\u201326.","DOI":"10.1016\/j.pmcj.2015.12.002"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Steve Hodges Emma Berry and Ken Wood. 2011. SenseCam: A wearable camera that stimulates and rehabilitates autobiographical memory. Memory 19 7 (2011) 685\u2013696.","DOI":"10.1080\/09658211.2011.605591"},{"key":"e_1_3_3_2_41_2","unstructured":"Edward\u00a0J Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang Weizhu Chen et\u00a0al. 2022. Lora: Low-rank adaptation of large language models.ICLR 1 2 (2022) 3."},{"key":"e_1_3_3_2_42_2","unstructured":"Sheikh\u00a0Asif Imran Mohammad Nur\u00a0Hossain Khan Subrata Biswas and Bashima Islam. 2024. Llasa: A multimodal llm for human activity analysis through wearable and smartphone sensors. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.14498 (2024)."},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445169"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/FMSys62467.2024.00011"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Hideo Joho Masaki Matsubara Norihiko Uda Chieko Mizoue and Rahmi Rahmi. 2023. Lifelogging by senior citizens: implications from a light-weight GPS-based study. F1000Research 12 (2023) 1461.","DOI":"10.12688\/f1000research.125012.1"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"crossref","unstructured":"Emil Jovanov and Aleksandar Milenkovic. 2011. Body area networks for ubiquitous healthcare applications: opportunities and challenges. Journal of medical systems 35 5 (2011) 1245\u20131254.","DOI":"10.1007\/s10916-011-9661-x"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/1753326.1753638"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Shian-Ru Ke Hoang Le\u00a0Uyen Thuc Yong-Jin Lee Jenq-Neng Hwang Jang-Hee Yoo and Kyoung-Ho Choi. 2013. A review on video-based human activity recognition. Computers 2 2 (2013) 88\u2013131.","DOI":"10.3390\/computers2020088"},{"key":"e_1_3_3_2_49_2","volume-title":"NAACL-HLT","author":"Kim Chris\u00a0Dongjoo","year":"2019","unstructured":"Chris\u00a0Dongjoo Kim, Byeongchang Kim, Hyunmin Lee, and Gunhee Kim. 2019. AudioCaps: Generating Captions for Audios in The Wild. In NAACL-HLT."},{"key":"e_1_3_3_2_50_2","unstructured":"Zhifeng Kong Arushi Goel Rohan Badlani Wei Ping Rafael Valle and Bryan Catanzaro. 2024. Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.01831 (2024)."},{"key":"e_1_3_3_2_51_2","unstructured":"Khaled Koutini Jan Schl\u00fcter Hamid Eghbal-Zadeh and Gerhard Widmer. 2021. Efficient training of audio transformers with patchout. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.05069 (2021)."},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3722570.3726876"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Amel Ksibi Ala Saleh\u00a0D Alluhaidan Amina Salhi and Sahar\u00a0A El-Rahman. 2021. Overview of lifelogging: current challenges and advances. IEEE Access 9 (2021) 62630\u201362641.","DOI":"10.1109\/ACCESS.2021.3073469"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"crossref","unstructured":"Nicholas\u00a0D Lane Emiliano Miluzzo Hong Lu Daniel Peebles Tanzeem Choudhury and Andrew\u00a0T Campbell. 2010. A survey of mobile phone sensing. IEEE Communications magazine 48 9 (2010) 140\u2013150.","DOI":"10.1109\/MCOM.2010.5560598"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/2030112.2030160"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242609"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/2030112.2030163"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"crossref","unstructured":"Junwoo Lee and Bummo Ahn. 2020. Real-time human action recognition with a low-cost RGB camera and mobile robot platform. Sensors 20 10 (2020) 2886.","DOI":"10.3390\/s20102886"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/1409635.1409643"},{"key":"e_1_3_3_2_60_2","first-page":"19730","volume-title":"International conference on machine learning","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_3_2_61_2","doi-asserted-by":"crossref","unstructured":"Kaylee\u00a0Yaxuan Li Yasha Iravantchi Yichen Zhu Hyunmin Park and Alanson\u00a0P Sample. 2025. HandSAW: Wearable Hand-based Event Recognition via On-Body Surface Acoustic Waves. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 9 1 (2025) 1\u201329.","DOI":"10.1145\/3712276"},{"key":"e_1_3_3_2_62_2","unstructured":"Yixin Liu Pengfei Liu Dragomir Radev and Graham Neubig. 2022. BRIO: Bringing order to abstractive summarization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.16804 (2022)."},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/1555816.1555834"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132990"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"crossref","unstructured":"Saif Mahmud Vineet Parikh Qikang Liang Ke Li Ruidong Zhang Ashwin Ajit Vipin Gunda Devansh Agarwal Fran\u00e7ois Guimbreti\u00e8re and Cheng Zhang. 2024. ActSonic: recognizing everyday activities from inaudible acoustic wave around the body. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 8 4 (2024) 1\u201332.","DOI":"10.1145\/3699752"},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"crossref","unstructured":"Mladen Milo\u0161evi\u0107 Michael\u00a0T Shrove and Emil Jovanov. 2011. Applications of smartphones for ubiquitous health monitoring and wellbeing management. Journal of Information Technology and Applications 1 1 (2011) 7\u201315.","DOI":"10.7251\/JIT1101007M"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3650767"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"crossref","unstructured":"Erik Oudman Isabelle\u00a0F Klukas Tijmen van Teijlingen and Albert Postma. 2025. First-person and third-person lifelogging improves episodic memory. Acta Psychologica 255 (2025) 104929.","DOI":"10.1016\/j.actpsy.2025.104929"},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/SenSys-ML62579.2024.00007"},{"key":"e_1_3_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683064"},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50252-2_26"},{"key":"e_1_3_3_2_72_2","volume-title":"Ubiquitous computing: smart devices, environments and interactions","author":"Poslad Stefan","year":"2011","unstructured":"Stefan Poslad. 2011. Ubiquitous computing: smart devices, environments and interactions. John Wiley & Sons."},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"crossref","unstructured":"Hendrik Purwins Bo Li Tuomas Virtanen Jan Schl\u00fcter Shuo-Yiin Chang and Tara Sainath. 2019. Deep learning for audio signal processing. IEEE Journal of Selected Topics in Signal Processing 13 2 (2019) 206\u2013219.","DOI":"10.1109\/JSTSP.2019.2908700"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"crossref","unstructured":"Amon Rapp and Federica Cena. 2016. Personal informatics for everyday life: How users without prior self-tracking experience engage with personal data. International Journal of Human-Computer Studies 94 (2016) 1\u201317.","DOI":"10.1016\/j.ijhcs.2016.05.006"},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"crossref","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1908.10084 (2019).","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"crossref","unstructured":"Ricardo Ribeiro Alina Trifan and Ant\u00f3nio\u00a0JR Neves. 2022. Lifelog Retrieval From Daily Digital Data: Narrative Review. JMIR Mhealth Uhealth 10 5 (2022) e30517.","DOI":"10.2196\/30517"},{"key":"e_1_3_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.4324\/9780203781036"},{"key":"e_1_3_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/1240624.1240636"},{"key":"e_1_3_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/ESPA.2012.6152455"},{"key":"e_1_3_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCITECHN.2008.4803018"},{"key":"e_1_3_3_2_81_2","doi-asserted-by":"crossref","unstructured":"Ana\u00a0Rita Silva Maria\u00a0Salom\u00e9 Pinho Lu\u00eds Macedo Christopher Moulin Salom\u00e9 Caldeira and Hor\u00e1cio Firmino. 2017. It is not only memory: Effects of sensecam on improving well-being in patients with mild alzheimer disease. International psychogeriatrics 29 5 (2017) 741\u2013754.","DOI":"10.1017\/S104161021600243X"},{"key":"e_1_3_3_2_82_2","first-page":"445","volume-title":"Asian conference on computer vision","author":"Song Sibo","year":"2014","unstructured":"Sibo Song, Vijay Chandrasekhar, Ngai-Man Cheung, Sanath Narayan, Liyuan Li, and Joo-Hwee Lim. 2014. Activity recognition in egocentric life-logging videos. In Asian conference on computer vision. Springer, 445\u2013458."},{"key":"e_1_3_3_2_83_2","doi-asserted-by":"crossref","unstructured":"Ke Sun Chunyu Xia Xinyu Zhang Hao Chen and Charlie\u00a0Jianzhong Zhang. 2024. Multimodal daily-life logging in free-living environment using non-visual egocentric sensors on a smartphone. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 8 1 (2024) 1\u201332.","DOI":"10.1145\/3643553"},{"key":"e_1_3_3_2_84_2","unstructured":"Changli Tang Wenyi Yu Guangzhi Sun Xianzhao Chen Tian Tan Wei Li Lu Lu Zejun Ma and Chao Zhang. 2023. Salmonn: Towards generic hearing abilities for large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.13289 (2023)."},{"key":"e_1_3_3_2_85_2","unstructured":"Nirmalya Thakur and Chia\u00a0Y Han. 2021. A review of assistive technologies for activities of daily living of elderly. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2106.12183 (2021)."},{"key":"e_1_3_3_2_86_2","doi-asserted-by":"crossref","unstructured":"Ye Tian Xiaoyuan Ren Zihao Wang Onat Gungor Xiaofan Yu and Tajana Rosing. 2025. DailyLLM: Context-Aware Activity Log Generation Using Multi-Modal Sensors and LLMs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.13737 (2025).","DOI":"10.1109\/MASS66014.2025.00060"},{"key":"e_1_3_3_2_87_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et\u00a0al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.09288 (2023)."},{"key":"e_1_3_3_2_88_2","doi-asserted-by":"crossref","unstructured":"Endel Tulving and Donald\u00a0M Thomson. 1973. Encoding specificity and retrieval processes in episodic memory.Psychological review 80 5 (1973) 352.","DOI":"10.1037\/h0020071"},{"key":"e_1_3_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.1145\/2970930.2970942"},{"key":"e_1_3_3_2_90_2","doi-asserted-by":"crossref","unstructured":"Tijmen Van\u00a0Teijlingen Erik Oudman and Albert Postma. 2022. Lifelogging as a rehabilitation tool in patients with amnesia: A narrative literature review on the effect of lifelogging on memory loss. Neuropsychological Rehabilitation 32 10 (2022) 2646\u20132672.","DOI":"10.1080\/09602011.2021.1974891"},{"key":"e_1_3_3_2_91_2","doi-asserted-by":"crossref","unstructured":"Jindong Wang Yiqiang Chen Shuji Hao Xiaohui Peng and Lisha Hu. 2019. Deep learning for sensor-based activity recognition: A survey. Pattern recognition letters 119 (2019) 3\u201311.","DOI":"10.1016\/j.patrec.2018.02.010"},{"key":"e_1_3_3_2_92_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054248"},{"key":"e_1_3_3_2_93_2","doi-asserted-by":"crossref","unstructured":"Jacob Westfall David\u00a0A Kenny and Charles\u00a0M Judd. 2014. Statistical power and optimal design in experiments in which samples of participants respond to samples of stimuli.Journal of Experimental Psychology: General 143 5 (2014) 2020.","DOI":"10.1037\/xge0000014"},{"key":"e_1_3_3_2_94_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376875"},{"key":"e_1_3_3_2_95_2","unstructured":"Huatao Xu Panrong Tong Mo Li and Mani Srivastava. 2024. Autolife: Automatic life journaling with smartphones and llms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.15714 (2024)."},{"key":"e_1_3_3_2_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3613299"},{"key":"e_1_3_3_2_97_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485937"},{"key":"e_1_3_3_2_98_2","unstructured":"Yuxuan Ye Edwin Simpson and Raul\u00a0Santos Rodriguez. 2024. Using similarity to evaluate factual consistency in summaries. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.15090 (2024)."},{"key":"e_1_3_3_2_99_2","first-page":"312","volume-title":"European Conference on Computer Vision","author":"Zhang Mingfang","year":"2024","unstructured":"Mingfang Zhang, Yifei Huang, Ruicong Liu, and Yoichi Sato. 2024. Masked video and body-worn imu autoencoder for egocentric action recognition. In European Conference on Computer Vision. Springer, 312\u2013330."},{"key":"e_1_3_3_2_100_2","unstructured":"Tianyi Zhang Varsha Kishore Felix Wu Kilian\u00a0Q Weinberger and Yoav Artzi. 2019. Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1904.09675 (2019)."},{"key":"e_1_3_3_2_101_2","unstructured":"Yuwei Zhang Kumar Ayush Siyuan Qiao A\u00a0Ali Heydari Girish Narayanswamy Maxwell\u00a0A Xu Ahmed\u00a0A Metwally Shawn Xu Jake Garrison Xuhai Xu et\u00a0al. 2025. SensorLM: Learning the Language of Wearable Sensors. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.09108 (2025)."},{"key":"e_1_3_3_2_102_2","unstructured":"Haizhong Zheng Elisa Tsai Yifu Lu Jiachen Sun Brian\u00a0R Bartoldson Bhavya Kailkhura and Atul Prakash. 2024. Elfs: Label-free coreset selection with proxy training dynamics. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.04273 (2024)."},{"key":"e_1_3_3_2_103_2","doi-asserted-by":"crossref","unstructured":"Ya-Li Zheng Xiao-Rong Ding Carmen Chung\u00a0Yan Poon Benny Ping\u00a0Lai Lo Heye Zhang Xiao-Lin Zhou Guang-Zhong Yang Ni Zhao and Yuan-Ting Zhang. 2014. Unobtrusive sensing and wearable devices for health informatics. IEEE transactions on biomedical engineering 61 5 (2014) 1538\u20131554.","DOI":"10.1109\/TBME.2014.2309951"}],"event":{"name":"CHI 2026: CHI Conference on Human Factors in Computing Systems","location":"Barcelona Spain","acronym":"CHI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772318.3791528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T09:35:34Z","timestamp":1776418534000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772318.3791528"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":102,"alternative-id":["10.1145\/3772318.3791528","10.1145\/3772318"],"URL":"https:\/\/doi.org\/10.1145\/3772318.3791528","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}