{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T22:34:46Z","timestamp":1757630086793,"version":"3.44.0"},"reference-count":23,"publisher":"Association for Computing Machinery (ACM)","issue":"5","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Hum.-Comput. Interact."],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"<jats:p>Input latency significantly deteriorates the users experience during touchscreen interactions, especially when they engage in precision tasks such as writing or drawing with a stylus. We address this issue by first decomposing it into two constituent tasks: stylus nib future trajectory prediction and predicted trajectory length optimization, facilitating a more thorough investigation into balancing latency compensation and side-effects, and then proposing a novel multi-task learning architecture that integrates the consideration of both tasks, enhances overall performance through alternating-joint training. Additional usage of specific features generated with an active stylus and the adoption of a customized distance error metric are also aimed at accuracy improvement. Experiments reveal that the multi-task learning model gives 0.47, 1.30, and 2.24 pixels of average error in cases of prediction in 6, 14, and 20 ms, and offers better trade-offs between latency reduction and side-effects across a wide range of usage scenarios.<\/jats:p>","DOI":"10.1145\/3743742","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T14:28:48Z","timestamp":1757428128000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Self-Distillation Based Multi-task Learning Model For Stylus Input Latency Compensation MHCI027"],"prefix":"10.1145","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6139-2637","authenticated-orcid":false,"given":"Kuangyu","family":"Liu","sequence":"first","affiliation":[{"name":"Xiaomi Technology Co., Ltd","place":["Xian, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2516-8442","authenticated-orcid":false,"given":"Fangjie","family":"Hou","sequence":"additional","affiliation":[{"name":"Xiaomi Technology Co., Ltd","place":["shanghai, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4536-4645","authenticated-orcid":false,"given":"Xinyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xiaomi Technology Co., Ltd","place":["shanghai, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8411-0785","authenticated-orcid":false,"given":"Jianlin","family":"Li","sequence":"additional","affiliation":[{"name":"Xiaomi Technology Co., Ltd","place":["shanghai, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2084-4400","authenticated-orcid":false,"given":"Zuobin","family":"Ning","sequence":"additional","affiliation":[{"name":"Xiaomi Technology Co., Ltd","place":["shanghai, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1528-3013","authenticated-orcid":false,"given":"Xuecheng","family":"Wu","sequence":"additional","affiliation":[{"name":"Xiaomi Technology Co., Ltd","place":["shanghai, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2473-0474","authenticated-orcid":false,"given":"Shunli","family":"Mao","sequence":"additional","affiliation":[{"name":"Xiaomi Technology Co., Ltd","place":["shanghai, China"]}]}],"member":"320","published-online":{"date-parts":[[2025,9,9]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174183"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7799284"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264040"},{"key":"e_1_3_1_5_2","unstructured":"Daniel Berio Memo Akten Frederic\u00a0Fol Leymarie Mick Grierson and R\u00e9jean Plamondon. 2016. Sequence generation with a physiologically plausible model of handwriting and Recurrent Mixture Density Networks. (2016)."},{"key":"e_1_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Yanling Bu Lei Xie Yafeng Yin Chuyu Wang Jingyi Ning Jiannong Cao and Sanglu Lu. 2021. Handwriting-assistant: Reconstructing continuous strokes with millimeter-level accuracy via attachable inertial sensors. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 5 4 (2021) 1\u201325.","DOI":"10.1145\/3494956"},{"key":"e_1_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Daniel Buschek Julia Kinshofer and Florian Alt. 2018. A comparative evaluation of spatial targeting behaviour patterns for finger and stylus tapping on mobile touchscreen devices. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 1 4 (2018) 1\u201321.","DOI":"10.1145\/3161160"},{"key":"e_1_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Rich Caruana. 1997. Multitask learning. Machine learning 28 (1997) 41\u201375.","DOI":"10.1023\/A:1007379606734"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/2817721.2817736"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702300"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2935334.2935381"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3098279.3122150"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50726-8_32"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132272.3134138"},{"key":"e_1_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Chih-Lung Lin Ting-Ching Chu Chia-En Wu Yi-Ming Chang Tsung-Chih Lin Jiann-Fuh Chen Cheng-Yan Chuang and Wen-Ching Chiu. 2017. Tracking touched trajectory on capacitive touch panels using an adjustable weighted prediction covariance matrix. IEEE Transactions on Industrial Electronics 64 6 (2017) 4910\u20134916.","DOI":"10.1109\/TIE.2017.2669887"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242646"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/2984511.2984590"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/2380116.2380174"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00131"},{"key":"e_1_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Qijia Shao Jian Wang Bing Zhou Vu\u00a0An Tran Gurunandan Krishnan and Shree Nayar. 2023. N-euro Predictor: A Neural Network Approach for Smoothing and Predicting Motion Trajectory. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 7 3 (2023) 1\u201325.","DOI":"10.1145\/3610884"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502069"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2015.7403059"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/2642918.2647348"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"}],"container-title":["Proceedings of the ACM on Human-Computer Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T16:07:39Z","timestamp":1757520459000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743742"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,9]]},"references-count":23,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,9,30]]}},"alternative-id":["10.1145\/3743742"],"URL":"https:\/\/doi.org\/10.1145\/3743742","relation":{},"ISSN":["2573-0142"],"issn-type":[{"value":"2573-0142","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,9]]},"assertion":[{"value":"2025-09-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}