{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:47:39Z","timestamp":1783612059106,"version":"3.55.0"},"reference-count":56,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2021,3,19]],"date-time":"2021-03-19T00:00:00Z","timestamp":1616112000000},"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":["Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."],"published-print":{"date-parts":[[2021,3,19]]},"abstract":"<jats:p>Wearables are fundamental to improving our understanding of human activities, especially for an increasing number of healthcare applications from rehabilitation to fine-grained gait analysis. Although our collective know-how to solve Human Activity Recognition (HAR) problems with wearables has progressed immensely with end-to-end deep learning paradigms, several fundamental opportunities remain overlooked. We rigorously explore these new opportunities to learn enriched and highly discriminating activity representations. We propose: i) learning to exploit the latent relationships between multi-channel sensor modalities and specific activities; ii) investigating the effectiveness of data-agnostic augmentation for multi-modal sensor data streams to regularize deep HAR models; and iii) incorporating a classification loss criterion to encourage minimal intra-class representation differences whilst maximising inter-class differences to achieve more discriminative features. Our contributions achieves new state-of-the-art performance on four diverse activity recognition problem benchmarks with large margins---with up to 6% relative margin improvement. We extensively validate the contributions from our design concepts through extensive experiments, including activity misalignment measures, ablation studies and insights shared through both quantitative and qualitative studies. The code base and trained network parameters are open-sourced on GitHub https:\/\/github.com\/AdelaideAuto-IDLab\/Attend-And-Discriminate to support further research.<\/jats:p>","DOI":"10.1145\/3448083","type":"journal-article","created":{"date-parts":[[2021,3,30]],"date-time":"2021-03-30T18:56:41Z","timestamp":1617130601000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":104,"title":["Attend and Discriminate"],"prefix":"10.1145","volume":"5","author":[{"given":"Alireza","family":"Abedin","sequence":"first","affiliation":[{"name":"The University of Adelaide, Adelaide SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahsa","family":"Ehsanpour","sequence":"additional","affiliation":[{"name":"The University of Adelaide, Adelaide SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinfeng","family":"Shi","sequence":"additional","affiliation":[{"name":"The University of Adelaide, Adelaide SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamid","family":"Rezatofighi","sequence":"additional","affiliation":[{"name":"Monash University, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Damith C.","family":"Ranasinghe","sequence":"additional","affiliation":[{"name":"The University of Adelaide, Adelaide SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,3,30]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19","author":"Abedin Alireza","year":"2019","unstructured":"Alireza Abedin , S. Hamid Rezatofighi , Qinfeng Shi , and Damith C. Ranasinghe . 2019. Sparse-Sense: Human Activity Recognition from Highly Sparse Sensor Data-streams Using Set-based Neural Networks . In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19 . International Joint Conferences on Artificial Intelligence Organization, 5780--5786. https:\/\/doi.org\/10.24963\/ijcai. 2019 \/801 Alireza Abedin, S. Hamid Rezatofighi, Qinfeng Shi, and Damith C. Ranasinghe. 2019. Sparse-Sense: Human Activity Recognition from Highly Sparse Sensor Data-streams Using Set-based Neural Networks. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19. International Joint Conferences on Artificial Intelligence Organization, 5780--5786. https:\/\/doi.org\/10.24963\/ijcai.2019\/801"},{"key":"e_1_2_1_2_1","volume-title":"Workshops at the Thirtieth AAAI Conference on Artificial Intelligence.","author":"Alsheikh Mohammad Abu","year":"2016","unstructured":"Mohammad Abu Alsheikh , Ahmed Selim , Dusit Niyato , Linda Doyle , Shaowei Lin , and Hwee-Pink Tan . 2016 . Deep activity recognition models with triaxial accelerometers . In Workshops at the Thirtieth AAAI Conference on Artificial Intelligence. Mohammad Abu Alsheikh, Ahmed Selim, Dusit Niyato, Linda Doyle, Shaowei Lin, and Hwee-Pink Tan. 2016. Deep activity recognition models with triaxial accelerometers. In Workshops at the Thirtieth AAAI Conference on Artificial Intelligence."},{"key":"e_1_2_1_3_1","volume-title":"23th International conference on architecture of computing systems","author":"Avci Akin","year":"2010","unstructured":"Akin Avci , Stephan Bosch , Mihai Marin-Perianu , Raluca Marin-Perianu , and Paul Havinga . 2010 . Activity recognition using inertial sensing for healthcare, wellbeing and sports applications: A survey . In 23th International conference on architecture of computing systems 2010. VDE, 1--10. Akin Avci, Stephan Bosch, Mihai Marin-Perianu, Raluca Marin-Perianu, and Paul Havinga. 2010. Activity recognition using inertial sensing for healthcare, wellbeing and sports applications: A survey. In 23th International conference on architecture of computing systems 2010. VDE, 1--10."},{"key":"e_1_2_1_4_1","volume-title":"Proceedings of the 2nd International Conference on Pervasive Computing, Alois Ferscha and Friedemann Mattern (Eds.). 1--17","author":"Bao Ling","unstructured":"Ling Bao and Stephen S. Intille . 2004. Activity recognition from user-annotated acceleration data . In Proceedings of the 2nd International Conference on Pervasive Computing, Alois Ferscha and Friedemann Mattern (Eds.). 1--17 . Ling Bao and Stephen S. Intille. 2004. Activity recognition from user-annotated acceleration data. In Proceedings of the 2nd International Conference on Pervasive Computing, Alois Ferscha and Friedemann Mattern (Eds.). 1--17."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2994551.2994564"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2499621"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2134203.2134205"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2012.12.014"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOMW.2018.8480292"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOMW.2017.7917643"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360774.3360831"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7724"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.3109\/17538157.2010.528648"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3090076"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9484"},{"key":"e_1_2_1_16_1","volume-title":"Proceedings of International Joint Conference on Artificial Intelligence. 1533--1540","author":"Hammerla Nils Y.","year":"2016","unstructured":"Nils Y. Hammerla , Shane Halloran , and Thomas Pl\u00f6tz . 2016 . Deep, Convolutional, and Recurrent Models for Human Activity Recognition Using Wearables . In Proceedings of International Joint Conference on Artificial Intelligence. 1533--1540 . Nils Y. Hammerla, Shane Halloran, and Thomas Pl\u00f6tz. 2016. Deep, Convolutional, and Recurrent Models for Human Activity Recognition Using Wearables. In Proceedings of International Joint Conference on Artificial Intelligence. 1533--1540."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341163.3347727"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3214269"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1107548.1107591"},{"key":"e_1_2_1_20_1","volume-title":"Jessica Sena, and William Robson Schwartz.","author":"Jordao Artur","year":"2018","unstructured":"Artur Jordao , Antonio C Nazare Jr , Jessica Sena, and William Robson Schwartz. 2018 . Human activity recognition based on wearable sensor data: A standardization of the state-of-the-art. arXiv preprint arXiv:1806.05226 (2018). Artur Jordao, Antonio C Nazare Jr, Jessica Sena, and William Robson Schwartz. 2018. Human activity recognition based on wearable sensor data: A standardization of the state-of-the-art. arXiv preprint arXiv:1806.05226 (2018)."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOM.2018.8444585"},{"key":"e_1_2_1_22_1","volume-title":"The International Conference on Learning Representations.","author":"Kingma Diederik P","year":"2015","unstructured":"Diederik P Kingma and Jimmy Ba . 2015 . Adam: A method for stochastic optimization . In The International Conference on Learning Representations. Diederik P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In The International Conference on Learning Representations."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmcj.2012.06.002"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmcj.2011.06.004"},{"key":"e_1_2_1_25_1","volume-title":"Deep learning. Nature 521, 7553","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun , Yoshua Bengio , and Geoffrey Hinton . 2015. Deep learning. Nature 521, 7553 ( 2015 ), 436--444. Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature 521, 7553 (2015), 436--444."},{"key":"e_1_2_1_26_1","volume-title":"Activity recognition in youth using single accelerometer placed at wrist or ankle. Medicine and science in sports and exercise 49, 4","author":"Mannini Andrea","year":"2017","unstructured":"Andrea Mannini , Mary Rosenberger , William L Haskell , Angelo M Sabatini , and Stephen S Intille . 2017. Activity recognition in youth using single accelerometer placed at wrist or ankle. Medicine and science in sports and exercise 49, 4 ( 2017 ), 801. Andrea Mannini, Mary Rosenberger, William L Haskell, Angelo M Sabatini, and Stephen S Intille. 2017. Activity recognition in youth using single accelerometer placed at wrist or ankle. Medicine and science in sports and exercise 49, 4 (2017), 801."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN.2018.00048"},{"key":"e_1_2_1_28_1","volume-title":"Proceedings of International Symposium on Wearable Computers. 100--103","author":"Vishvak","unstructured":"Vishvak S. Murahari and Thomas Pl\u00f6tz. 2018. On Attention Models for Human Activity Recognition . In Proceedings of International Symposium on Wearable Computers. 100--103 . Vishvak S. Murahari and Thomas Pl\u00f6tz. 2018. On Attention Models for Human Activity Recognition. In Proceedings of International Symposium on Wearable Computers. 100--103."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOMW.2017.7917596"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/s16010115"},{"key":"e_1_2_1_31_1","volume-title":"NIPS Autodiff Workshop.","author":"Paszke Adam","year":"2017","unstructured":"Adam Paszke , Sam Gross , Soumith Chintala , Gregory Chanan , Edward Yang , Zachary DeVito , Zeming Lin , Alban Desmaison , Luca Antiga , and Adam Lerer . 2017 . Automatic differentiation in Pytorch . In NIPS Autodiff Workshop. Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic differentiation in Pytorch. In NIPS Autodiff Workshop."},{"key":"e_1_2_1_32_1","unstructured":"Thomas Pl\u00f6tz Nils Y Hammerla and Patrick L Olivier. 2011. Feature learning for activity recognition in ubiquitous computing. In Twenty-second international joint conference on artificial intelligence.  Thomas Pl\u00f6tz Nils Y Hammerla and Patrick L Olivier. 2011. Feature learning for activity recognition in ubiquitous computing. In Twenty-second international joint conference on artificial intelligence."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370216.2370276"},{"key":"e_1_2_1_34_1","volume-title":"Proceedings of the 4th International Symposium on Wearable Computers. 175--176","author":"Randell C.","unstructured":"C. Randell and H. Muller . 2000. Context awareness by analysing accelerometer data . In Proceedings of the 4th International Symposium on Wearable Computers. 175--176 . C. Randell and H. Muller. 2000. Context awareness by analysing accelerometer data. In Proceedings of the 4th International Symposium on Wearable Computers. 175--176."},{"key":"e_1_2_1_35_1","volume-title":"Proceedings of the 17th Conference on Innovative Applications of Artificial Intelligence. 1541--1546","author":"Ravi Nishkam","unstructured":"Nishkam Ravi , Nikhil Dandekar , Preetham Mysore , and Michael L. Littman . 2005. Activity recognition from accelerometer data . In Proceedings of the 17th Conference on Innovative Applications of Artificial Intelligence. 1541--1546 . Nishkam Ravi, Nikhil Dandekar, Preetham Mysore, and Michael L. Littman. 2005. Activity recognition from accelerometer data. In Proceedings of the 17th Conference on Innovative Applications of Artificial Intelligence. 1541--1546."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.2012.13"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26561-2_6"},{"key":"e_1_2_1_38_1","volume-title":"Ranasinghe","author":"Shinmoto Torres Roberto Luis","year":"2017","unstructured":"Roberto Luis Shinmoto Torres , Qinfeng Shi , Anton van den Hengel , and Damith C . Ranasinghe . 2017 . A hierarchical model for recognizing alarming states in a batteryless sensor alarm intervention for preventing falls in older people. Pervasive Mob. Comput. 40, C ( 2017), 1--16. Roberto Luis Shinmoto Torres, Qinfeng Shi, Anton van den Hengel, and Damith C. Ranasinghe. 2017. A hierarchical model for recognizing alarming states in a batteryless sensor alarm intervention for preventing falls in older people. Pervasive Mob. Comput. 40, C (2017), 1--16."},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2008.40"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0185670"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136817"},{"key":"e_1_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Alireza Abedin Varamin Ehsan Abbasnejad Qinfeng Shi Damith C Ranasinghe and Hamid Rezatofighi. 2018. Deep Auto-Set: A Deep Auto-Encoder-Set Network for Activity Recognition Using Wearables. In the 15th EAI International Conference on Mobile and Ubiquitous Systems: Computing Networking and Services. 246--253.  Alireza Abedin Varamin Ehsan Abbasnejad Qinfeng Shi Damith C Ranasinghe and Hamid Rezatofighi. 2018. Deep Auto-Set: A Deep Auto-Encoder-Set Network for Activity Recognition Using Wearables. In the 15th EAI International Conference on Mobile and Ubiquitous Systems: Computing Networking and Services. 246--253.","DOI":"10.1145\/3286978.3287024"},{"key":"e_1_2_1_43_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez &Lstroke;ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez &Lstroke;ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.02.010"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/1889681.1889687"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2016.2576285"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.5555\/2832747.2832806"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.12.024"},{"key":"e_1_2_1_51_1","volume-title":"6th International Conference on Mobile Computing, Applications and Services. 197--205","author":"Zeng M.","year":"2014","unstructured":"M. Zeng , L. T. Nguyen , B. Yu , O. J. Mengshoel , J. Zhu , P. Wu , and J. Zhang . 2014. Convolutional Neural Networks for human activity recognition using mobile sensors . In 6th International Conference on Mobile Computing, Applications and Services. 197--205 . https:\/\/doi.org\/10.4108\/icst.mobicase. 2014 .257786 M. Zeng, L. T. Nguyen, B. Yu, O. J. Mengshoel, J. Zhu, P. Wu, and J. Zhang. 2014. Convolutional Neural Networks for human activity recognition using mobile sensors. In 6th International Conference on Mobile Computing, Applications and Services. 197--205. https:\/\/doi.org\/10.4108\/icst.mobicase.2014.257786"},{"key":"e_1_2_1_52_1","volume-title":"International Conference on Learning Representations.","author":"Zhang Hongyi","year":"2018","unstructured":"Hongyi Zhang , Moustapha Cisse , Yann N Dauphin , and David Lopez-Paz . 2018 . mixup: Beyond Empirical Risk Minimization . In International Conference on Learning Representations. Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2018. mixup: Beyond Empirical Risk Minimization. In International Conference on Learning Representations."},{"key":"e_1_2_1_53_1","volume-title":"Self-Attention Generative Adversarial Networks. In International Conference on Machine Learning. 7354--7363","author":"Zhang Han","year":"2019","unstructured":"Han Zhang , Ian Goodfellow , Dimitris Metaxas , and Augustus Odena . 2019 . Self-Attention Generative Adversarial Networks. In International Conference on Machine Learning. 7354--7363 . Han Zhang, Ian Goodfellow, Dimitris Metaxas, and Augustus Odena. 2019. Self-Attention Generative Adversarial Networks. In International Conference on Machine Learning. 7354--7363."},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCI-CC.2015.7259385"},{"key":"e_1_2_1_55_1","volume-title":"Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium. 631--640","author":"Zhang Mi","unstructured":"Mi Zhang and Alexander A. Sawchuk . 2012. Motion primitive-based human activity recognition using a bag-of-features approach . In Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium. 631--640 . Mi Zhang and Alexander A. Sawchuk. 2012. Motion primitive-based human activity recognition using a bag-of-features approach. In Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium. 631--640."},{"key":"e_1_2_1_56_1","volume-title":"Thirty-Second AAAI conference on artificial intelligence.","author":"Zheng Nenggan","year":"2018","unstructured":"Nenggan Zheng , Jun Wen , Risheng Liu , Liangqu Long , Jianhua Dai , and Zhefeng Gong . 2018 . Unsupervised representation learning with long-term dynamics for skeleton based action recognition . In Thirty-Second AAAI conference on artificial intelligence. Nenggan Zheng, Jun Wen, Risheng Liu, Liangqu Long, Jianhua Dai, and Zhefeng Gong. 2018. Unsupervised representation learning with long-term dynamics for skeleton based action recognition. In Thirty-Second AAAI conference on artificial intelligence."}],"container-title":["Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3448083","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3448083","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:24:59Z","timestamp":1750195499000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3448083"}},"subtitle":["Beyond the State-of-the-Art for Human Activity Recognition Using Wearable Sensors"],"short-title":[],"issued":{"date-parts":[[2021,3,19]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,3,19]]}},"alternative-id":["10.1145\/3448083"],"URL":"https:\/\/doi.org\/10.1145\/3448083","relation":{},"ISSN":["2474-9567"],"issn-type":[{"value":"2474-9567","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,19]]},"assertion":[{"value":"2021-03-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}