{"type":"ScholarlyArticle","title":"Wearable Sensor-Based Few-Shot Continual Learning on Hand Gestures for Motor-Impaired Individuals via Latent Embedding Exploitation","authors":[{"name":"Riyad Bin Rafiq","slug":"riyad-bin-rafiq","given":"Riyad Bin","family":"Rafiq","affiliation":"Department of Computer Science and Engineering , University of North Texas"},{"name":"Weishi Shi","slug":"weishi-shi","given":"Weishi","family":"Shi","affiliation":"Department of Computer Science and Engineering , University of North Texas"},{"name":"Mark V. Albert","slug":"mark-v-albert","given":"Mark V.","family":"Albert","affiliation":"Department of Computer Science and Engineering , University of North Texas; Department of Biomedical Engineering , University of North Texas"}],"abstract":"Hand gestures can provide a natural means of human-computer interaction and enable people who cannot speak to communicate efficiently. Existing hand gesture recognition methods heavily depend on pre-defined gestures, however, motor-impaired individuals require new gestures tailored to each individual's gesture motion and style. Gesture samples collected from different persons have distribution shifts due to their health conditions, the severity of the disability, motion patterns of the arms, etc. In this paper, we introduce the Latent Embedding Exploitation (LEE) mechanism in our replay-based Few-Shot Continual Learning (FSCL) framework that significantly improves the performance of fine-tuning a model for out-of-distribution data. Our method produces a diversified latent feature space by leveraging a preserved latent embedding known as gesture prior knowledge, along with intra-gesture divergence derived from two additional embeddings. Thus, the model can capture latent statistical structure in highly variable gestures with limited samples. We conduct an experimental evaluation using the SmartWatch Gesture and the Motion Gesture datasets. The proposed method results in an average test accuracy of 57.0%, 64.6%, and 69.3% by using one, three, and five samples for six different gestures. Our method helps motor-impaired persons leverage wearable devices, and their unique styles of movement can be learned and applied in human-computer interaction and social communication. Code is available at: https://github.com/riyadRafiq/wearable-latent-embedding-exploitation.","doi":"10.24963/ijcai.2024/823","url":"https://ijcai.org/proceedings/2024/823","pdf":"https://ijcai.org/proceedings/2024/0823.pdf","markdown":"https://ijcai.org/proceedings/2024/823.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/823","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"AI for Good","track":"AI for Good","number":823,"pages":{"first":7438,"last":7446},"keywords":["Multidisciplinary Topics and Applications: General","Machine Learning: General"],"videos":[],"references":[{"position":1,"raw":"[Bank et al., 2020] Dor Bank, Noam Koenigstein, and Raja Giryes. Autoencoders. arXiv preprint arXiv:2003.05991, 2020.","title":null,"authors":"Dor Bank, Noam Koenigstein, Raja Giryes","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bin Rafiq et al., 2020] Riyad Bin Rafiq, Francois Modave, Shion Guha, and Mark V Albert. Validation methods to promote real-world applicability of machine learning in medicine. In 2020 3rd International Conference on Digital Medicine and Image Processing, pages 13-19, 2020.","title":"Validation methods to promote real-world applicability of machine learning in medicine","authors":"Riyad Bin, Rafiq, Francois Modave, Shion Guha, Mark V Albert","year":"2020","venue":"2020 3rd International Conference on Digital Medicine and Image Processing","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Blakeman and Mareschal, 2020] Sam Blakeman and Denis Mareschal. A complementary learning systems approach to temporal difference learning. Neural Networks, 122:218-230, 2020.","title":"A complementary learning systems approach to temporal difference learning","authors":"Mareschal Blakeman, Sam Blakeman, Denis Mareschal","year":"2020","venue":"Neural Networks","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Caramiaux et al., 2015] Baptiste Caramiaux, Marco Donnarumma, and Atau Tanaka. Understanding gesture expressivity through muscle sensing. ACM Transactions on Computer-Human Interaction (TOCHI), 21(6):1-26, 2015.","title":"Understanding gesture expressivity through muscle sensing","authors":"Baptiste Caramiaux, Marco Donnarumma, Atau Tanaka","year":"2015","venue":"ACM Transactions on Computer-Human Interaction (TOCHI)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[CDC, 2023] CDC. Disability impacts all of us, 2023. Accessed: May 13, 2024.","title":"CDC. Disability impacts all of us","authors":null,"year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Costante et al., 2014] Gabriele Costante, Lorenzo Porzi, Oswald Lanz, Paolo Valigi, and Elisa Ricci. Personalizing a smartwatch-based gesture interface with transfer learning. In 2014 22nd European Signal Processing Conference (EUSIPCO), pages 2530-2534. IEEE, 2014.","title":"Personalizing a smartwatch-based gesture interface with transfer learning","authors":"Gabriele Costante, Lorenzo Porzi, Oswald Lanz, Paolo Valigi, Elisa Ricci","year":"2014","venue":"2014 22nd European Signal Processing Conference (EUSIPCO)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ding and Fu, 2017] Zhengming Ding and Yun Fu. Deep domain generalization with structured low-rank constraint. IEEE Transactions on Image Processing, 27(1):304-313, 2017.","title":"Deep domain generalization with structured low-rank constraint","authors":"Zhengming Ding, Yun Fu","year":"2017","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Finn et al., 2017] Chelsea Finn, Pieter Abbeel, and Sergey Levine. Model-agnostic meta-learning for fast adaptation of deep networks. In International conference on machine learning, pages 1126-1135. PMLR, 2017.","title":"Model-agnostic meta-learning for fast adaptation of deep networks","authors":"Finn","year":"2017","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[French, 1999] Robert M French. Catastrophic forgetting in connectionist networks. Trends in cognitive sciences, 3(4):128-135, 1999.","title":"Catastrophic forgetting in connectionist networks","authors":"M Robert, French","year":"1999","venue":"Trends in cognitive sciences","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gidaris and Komodakis, 2018] Spyros Gidaris and Nikos Komodakis. Dynamic few-shot visual learning without forgetting. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4367- 4375, 2018.","title":"Dynamic few-shot visual learning without forgetting","authors":"Spyros Gidaris, Nikos Komodakis","year":"2018","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Guo et al., 2021] Lin Guo, Zongxing Lu, and Ligang Yao. Human-machine interaction sensing technology based on hand gesture recognition: A review. IEEE Transactions on Human-Machine Systems, 51(4):300-309, 2021.","title":"Human-machine interaction sensing technology based on hand gesture recognition: A review","authors":"Lin Guo, Zongxing Lu, Ligang Yao","year":"2021","venue":"IEEE Transactions on Human-Machine Systems","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hu et al., 2018] Ting-Kuei Hu, Yen-Yu Lin, and Pi-Cheng Hsiu. Learning adaptive hidden layers for mobile gesture recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, 2018.","title":"Learning adaptive hidden layers for mobile gesture recognition","authors":"Ting-Kuei Hu, Yen-Yu Lin, Pi-Cheng Hsiu","year":"2018","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kaya and Bilge, 2019] Mahmut Kaya and Hasan S ¸akir Bilge. Deep metric learning: A survey. Symmetry, 11(9):1066, 2019.","title":"Deep metric learning: A survey","authors":"Bilge Kaya, Mahmut Kaya, Hasan S ¸akir Bilge","year":"2019","venue":"Symmetry","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kim et al., 2019] Jee-Eun Kim, Masahiro Bessho, and Ken Sakamura. Towards a smartwatch application to assist students with disabilities in an iot-enabled campus. In 2019 IEEE 1st Global Conference on Life Sciences and Technologies (LifeTech), pages 243-246. IEEE, 2019.","title":"Towards a smartwatch application to assist students with disabilities in an iot-enabled campus","authors":"Jee-Eun Kim, Masahiro Bessho, Ken Sakamura","year":"2019","venue":"IEEE 1st Global Conference on Life Sciences and Technologies (LifeTech)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kimura, 2022] Naoki Kimura. Self-supervised approach for few-shot hand gesture recognition. In Adjunct Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology, pages 1-4, 2022.","title":"Self-supervised approach for few-shot hand gesture recognition","authors":"Naoki Kimura","year":"2022","venue":"Adjunct Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kumar et al., 2022] Ananya Kumar, Aditi Raghunathan, Robbie Jones, Tengyu Ma, and Percy Liang. Fine-tuning can distort pretrained features and underperform out-of- distribution. arXiv preprint arXiv:2202.10054, 2022.","title":"Fine-tuning can distort pretrained features and underperform out-ofdistribution","authors":"Ananya Kumar, Aditi Raghunathan, Robbie Jones, Tengyu Ma, Percy Liang","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Kunwar et al., 2022] Utkarsh Kunwar, Sheetal Borar, Moritz Berghofer, Julia Kylmälä, Ilhan Aslan, Luis A Leiva, and Antti Oulasvirta. Robust and deployable gesture recognition for smartwatches. In 27th International Conference on Intelligent User Interfaces, pages 277-291, 2022.","title":"Robust and deployable gesture recognition for smartwatches","authors":"Utkarsh Kunwar, Sheetal Borar, Moritz Berghofer, Julia Kylmälä, Ilhan Aslan, Luis A Leiva, Antti Oulasvirta","year":"2022","venue":"27th International Conference on Intelligent User Interfaces","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Laput and Harrison, 2019] Gierad Laput and Chris Harrison. Sensing fine-grained hand activity with smartwatches. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, pages 1-13, 2019.","title":"Gierad Laput and Chris Harrison. Sensing fine-grained hand activity with smartwatches","authors":"Harrison Laput","year":"2019","venue":"Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Li et al., 2019] Chenyang Li, Xin Zhang, Lufan Liao, Lianwen Jin, and Weixin Yang. Skeleton-based gesture recognition using several fully connected layers with path signature features and temporal transformer module. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 8585-8593, 2019.","title":"Skeleton-based gesture recognition using several fully connected layers with path signature features and temporal transformer module","authors":"Chenyang Li, Xin Zhang, Lufan Liao, Lianwen Jin, Weixin Yang","year":"2019","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Malu et al., 2018] Meethu Malu, Pramod Chundury, and Leah Findlater. Exploring accessible smartwatch interactions for people with upper body motor impairments. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, pages 1-12, 2018.","title":"Exploring accessible smartwatch interactions for people with upper body motor impairments","authors":"Malu","year":"2018","venue":"Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Mohamed et al., 2021] Noraini Mohamed, Mumtaz Begum Mustafa, and Nazean Jomhari. A review of the hand gesture recognition system: Current progress and future directions. IEEE Access, 9:157422-157436, 2021.","title":"A review of the hand gesture recognition system: Current progress and future directions","authors":"Noraini Mohamed, Mumtaz Begum Mustafa, Nazean Jomhari","year":"2021","venue":"IEEE Access","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Nguyen-Trong et al., 2021] Khanh Nguyen-Trong, Hoai Nam Vu, Ngon Nguyen Trung, and Cuong Pham. Gesture recognition using wearable sensors with bi-long short-term memory convolutional neural networks. IEEE Sensors Journal, 21(13):15065-15079, 2021.","title":"Gesture recognition using wearable sensors with bi-long short-term memory convolutional neural networks","authors":"Khanh Nguyen-Trong, Nam Hoai, Ngon Vu, Cuong Nguyen Trung, Pham","year":"2021","venue":"IEEE Sensors Journal","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[NIDCD, 2024] NIDCD. Quick statistics about voice, speech, and language, 2024. Accessed: May 13, 2024.","title":"NIDCD. Quick statistics about voice, speech, and language","authors":null,"year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Parisi et al., 2019] German I Parisi, Ronald Kemker, Jose L Part, Christopher Kanan, and Stefan Wermter. Continual lifelong learning with neural networks: A review. Neural networks, 113:54-71, 2019.","title":"Continual lifelong learning with neural networks: A review","authors":"Parisi","year":"2019","venue":"Neural networks","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Perrusquía, 2022] Adolfo Perrusquía. Human-behavior learning: A new complementary learning perspective for optimal decision making controllers. Neurocomputing, 489:157-166, 2022.","title":"Human-behavior learning: A new complementary learning perspective for optimal decision making controllers","authors":"Adolfo Perrusquía","year":"2022","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Pisharady and Saerbeck, 2015] Pramod Kumar Pisharady and Martin Saerbeck. Recent methods and databases in vision-based hand gesture recognition: A review. Computer Vision and Image Understanding, 141:152-165, 2015.","title":"Recent methods and databases in vision-based hand gesture recognition: A review","authors":"Pramod Kumar, Pisharady, Martin Saerbeck","year":"2015","venue":"Computer Vision and Image Understanding","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Porzi et al., 2013] Lorenzo Porzi, Stefano Messelodi, Carla Mara Modena, and Elisa Ricci. A smart watch- based gesture recognition system for assisting people with visual impairments. In Proceedings of the 3rd ACM international workshop on Interactive multimedia on mobile & portable devices, pages 19-24, 2013.","title":"A smart watchbased gesture recognition system for assisting people with visual impairments","authors":"Lorenzo Porzi, Stefano Messelodi, Carla Mara Modena, Elisa Ricci","year":"2013","venue":"Proceedings of the 3rd ACM international workshop on Interactive multimedia on mobile & portable devices","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Qian et al., 2021] Hangwei Qian, Sinno Jialin Pan, and Chunyan Miao. Latent independent excitation for generalizable sensor-based cross-person activity recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 11921-11929, 2021.","title":"Latent independent excitation for generalizable sensor-based cross-person activity recognition","authors":"Qian","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Rafiq et al., 2023] Riyad Bin Rafiq, Syed Araib Karim, and Mark V Albert. An lstm-based gesture-to-speech recognition system. In 2023 IEEE 11th International Conference on Healthcare Informatics (ICHI), pages 430- 438. IEEE, 2023.","title":"An lstm-based gesture-to-speech recognition system","authors":"Riyad Bin, Rafiq Syed, Araib Karim, Mark V Albert","year":"2023","venue":"IEEE 11th International Conference on Healthcare Informatics (ICHI)","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Rahimian et al., 2021] Elahe Rahimian, Soheil Zabihi, Amir Asif, S Farokh Atashzar, and Arash Mohammadi. Few-shot learning for decoding surface electromyography for hand gesture recognition. In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1300-1304. IEEE, 2021.","title":"Few-shot learning for decoding surface electromyography for hand gesture recognition","authors":"Elahe Rahimian, Soheil Zabihi, Amir Asif, S Farokh Atashzar, Arash Mohammadi","year":"2021","venue":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Rebuffi et al., 2017] Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, and Christoph H Lampert. icarl: Incremental classifier and representation learning. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 2001-2010, 2017.","title":"icarl: Incremental classifier and representation learning","authors":"Sylvestre-Alvise, Alexander Rebuffi, Georg Kolesnikov, Christoph H Sperl, Lampert","year":"2017","venue":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Siean and Vatavu, 2021] Alexandru-Ionut Siean and Radu- Daniel Vatavu. Wearable interactions for users with motor impairments: systematic review, inventory, and research implications. In Proceedings of the 23rd International ACM SIGACCESS Conference on Computers and Accessibility, pages 1-15, 2021.","title":"Wearable interactions for users with motor impairments: systematic review, inventory, and research implications","authors":"Alexandru-Ionut Siean, Radu-Daniel Vatavu","year":"2021","venue":"Proceedings of the 23rd International ACM SIGACCESS Conference on Computers and Accessibility","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Snell et al., 2017] Jake Snell, Kevin Swersky, and Richard Zemel. Prototypical networks for few-shot learning. Advances in neural information processing systems, 30, 2017.","title":"Prototypical networks for few-shot learning","authors":"Jake Snell, Kevin Swersky, Richard Zemel","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Stewart et al., 2020] Kenneth Stewart, Garrick Orchard, Sumit Bam Shrestha, and Emre Neftci. Online few- shot gesture learning on a neuromorphic processor. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 10(4):512-521, 2020.","title":"Online fewshot gesture learning on a neuromorphic processor","authors":"Kenneth Stewart, Garrick Orchard, Sumit Bam Shrestha, Emre Neftci","year":"2020","venue":"IEEE Journal on Emerging and Selected Topics in Circuits and Systems","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Van de Ven and Tolias, 2019] Gido M Van de Ven and Andreas S Tolias. Three scenarios for continual learning. arXiv preprint arXiv:1904.07734, 2019. [Vatavu and Ungurean, 2022]","title":"Three scenarios for continual learning","authors":"M Gido, Andreas S Van De Ven, Tolias","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":36,"raw":"Radu-Daniel Vatavu and Ovidiu-Ciprian Ungurean. Understanding gesture input articulation with upper-body wearables for users with upper-body motor impairments. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, pages 1-16, 2022.","title":"Understanding gesture input articulation with upper-body wearables for users with upper-body motor impairments","authors":"Radu-Daniel Vatavu, Ovidiu-Ciprian Ungurean","year":"2022","venue":"Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Wallin et al., 2019] Mitchell T Wallin, William J Culpepper, Jonathan D Campbell, Lorene M Nelson, Annette Langer-Gould, Ruth Ann Marrie, Gary R Cutter, Wendy E Kaye, Laurie Wagner, Helen Tremlett, et al. The prevalence of ms in the united states: a population-based estimate using health claims data. Neurology, 92(10):e1029-e1040, 2019.","title":"The prevalence of ms in the united states: a population-based estimate using health claims data","authors":"William J Mitchell T Wallin, Jonathan D Culpepper, Lorene M Campbell, Annette Nelson, Ruth Langer-Gould, Ann Marrie, Wendy E Gary R Cutter, Laurie Kaye, Helen Wagner, Tremlett","year":"2019","venue":"Neurology","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[White and Black, 2016] Non-Hispanic White and Non- Hispanic Black. Spinal cord injury (sci) facts and figures at a glance. 2016.","title":"Non-Hispanic White and Non-Hispanic Black. Spinal cord injury (sci) facts and figures at a glance","authors":"Black White","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Wu et al., 2012] Di Wu, Fan Zhu, and Ling Shao. One shot learning gesture recognition from rgbd images. In 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pages 7-12. IEEE, 2012.","title":"One shot learning gesture recognition from rgbd images","authors":"Di Wu, Fan Zhu, Ling Shao","year":"2012","venue":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Xie and Cao, 2016] Renqiang Xie and Juncheng Cao. Accelerometer-based hand gesture recognition by neural network and similarity matching. IEEE Sensors Journal, 16(11):4537-4545, 2016.","title":"Renqiang Xie and Juncheng Cao. Accelerometer-based hand gesture recognition by neural network and similarity matching","authors":"Cao Xie","year":"2016","venue":"IEEE Sensors Journal","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Xu et al., 2022] Xuhai Xu, Jun Gong, Carolina Brum, Lilian Liang, Bongsoo Suh, Shivam Kumar Gupta, Yash Agarwal, Laurence Lindsey, Runchang Kang, Behrooz Shahsavari, et al. Enabling hand gesture customization on wrist-worn devices. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, pages 1-19, 2022.","title":"Enabling hand gesture customization on wrist-worn devices","authors":"Xu","year":"2022","venue":"Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Yang et al., 2021] Shuo Yang, Lu Liu, and Min Xu. Free lunch for few-shot learning: Distribution calibration. arXiv preprint arXiv:2101.06395, 2021.","title":"Free lunch for few-shot learning: Distribution calibration","authors":"Shuo Yang, Lu Liu, Min Xu","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Yu et al., 2023] Lu Yu, Malvina Nikandrou, Jiali Jin, and Verena Reiser. Quality-agnostic image captioning to safely assist people with vision impairment. arXiv preprint arXiv:2304.14623, 2023.","title":"Quality-agnostic image captioning to safely assist people with vision impairment","authors":"Lu Yu, Malvina Nikandrou, Jiali Jin, Verena Reiser","year":"2023","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2023/697"},{"position":44,"raw":"[Zhang and Yang, 2021] Yu Zhang and Qiang Yang. A survey on multi-task learning. IEEE Transactions on Knowledge and Data Engineering, 34(12):5586-5609, 2021.","title":"A survey on multi-task learning","authors":"Yu Zhang, Qiang Yang","year":"2021","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Zhou et al., 2021] Benjia Zhou, Yunan Li, and Jun Wan. Regional attention with architecture-rebuilt 3d network for rgb-d gesture recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 3563-3571, 2021.","title":"Regional attention with architecture-rebuilt 3d network for rgb-d gesture recognition","authors":"Zhou","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Zhuang et al., 2020] Fuzhen Zhuang, Zhiyuan Qi, Keyu Duan, Dongbo Xi, Yongchun Zhu, Hengshu Zhu, Hui Xiong, and Qing He. A comprehensive survey on transfer learning. Proceedings of the IEEE, 109(1):43-76, 2020.","title":"A comprehensive survey on transfer learning","authors":"Zhuang","year":"2020","venue":"Proceedings of the IEEE","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}