{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T17:45:16Z","timestamp":1772300716398,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":107,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF","award":["SCH-2123521"],"award-info":[{"award-number":["SCH-2123521"]}]},{"name":"NSF","award":["SCH-2123749"],"award-info":[{"award-number":["SCH-2123749"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548238","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:35Z","timestamp":1665416555000},"page":"5903-5912","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["Progressive Cross-modal Knowledge Distillation for Human Action Recognition"],"prefix":"10.1145","author":[{"given":"Jianyuan","family":"Ni","sequence":"first","affiliation":[{"name":"Texas State University, San Marcos, TX, USA"}]},{"given":"Anne H.H.","family":"Ngu","sequence":"additional","affiliation":[{"name":"Texas State University, San Marcos, TX, USA"}]},{"given":"Yan","family":"Yan","sequence":"additional","affiliation":[{"name":"Texas State University, San Marcos, IL, USA"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3028561"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Zeeshan Ahmad and Naimul Mefraz Khan. 2019. Multidomain multimodal fusion for human action recognition using inertial sensors. In BigMM. 429--434.  Zeeshan Ahmad and Naimul Mefraz Khan. 2019. Multidomain multimodal fusion for human action recognition using inertial sensors. In BigMM. 429--434.","DOI":"10.1109\/BigMM.2019.00026"},{"key":"e_1_3_2_2_3_1","volume-title":"Do deep nets really need to be deep? Advances in neural information processing systems","author":"Ba Jimmy","year":"2014","unstructured":"Jimmy Ba and Rich Caruana . 2014. Do deep nets really need to be deep? Advances in neural information processing systems , Vol. 27 ( 2014 ). Jimmy Ba and Rich Caruana. 2014. Do deep nets really need to be deep? Advances in neural information processing systems, Vol. 27 (2014)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Zhe Cao Tomas Simon Shih-En Wei and Yaser Sheikh. 2017. Realtime multi-person 2d pose estimation using part affinity fields. In CVPR. 7291--7299.  Zhe Cao Tomas Simon Shih-En Wei and Yaser Sheikh. 2017. Realtime multi-person 2d pose estimation using part affinity fields. In CVPR. 7291--7299.","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Chen Chen Roozbeh Jafari and Nasser Kehtarnavaz. 2015. UTD-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor. In ICIP. 168--172.  Chen Chen Roozbeh Jafari and Nasser Kehtarnavaz. 2015. UTD-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor. In ICIP. 168--172.","DOI":"10.1109\/ICIP.2015.7350781"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2015.263"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Ke Cheng Yifan Zhang Xiangyu He Weihan Chen Jian Cheng and Hanqing Lu. 2020. Skeleton-based action recognition with shift graph convolutional network. In CVPR. 183--192.  Ke Cheng Yifan Zhang Xiangyu He Weihan Chen Jian Cheng and Hanqing Lu. 2020. Skeleton-based action recognition with shift graph convolutional network. In CVPR. 183--192.","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3034614"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"Neha Dawar and Nasser Kehtarnavaz. 2018. A convolutional neural network-based sensor fusion system for monitoring transition movements in healthcare applications. In ICCA. 482--485.  Neha Dawar and Nasser Kehtarnavaz. 2018. A convolutional neural network-based sensor fusion system for monitoring transition movements in healthcare applications. In ICCA. 482--485.","DOI":"10.1109\/ICCA.2018.8444326"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSENS.2018.2878572"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3037715"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"Yong Du Wei Wang and Liang Wang. 2015. Hierarchical recurrent neural network for skeleton based action recognition. In CVPR. 1110--1118.  Yong Du Wei Wang and Liang Wang. 2015. Hierarchical recurrent neural network for skeleton based action recognition. In CVPR. 1110--1118.","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"e_1_3_2_2_13_1","volume-title":"Multimodal Action Recognition using Graph Convolutional Neural Networks. Master's thesis","author":"Duhme Michael","unstructured":"Michael Duhme . 2021. Multimodal Action Recognition using Graph Convolutional Neural Networks. Master's thesis . University of Koblenz-Landau, Active Vision Group . Michael Duhme. 2021. Multimodal Action Recognition using Graph Convolutional Neural Networks. Master's thesis. University of Koblenz-Landau, Active Vision Group."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92659-5_17"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Takashi Fukuda Masayuki Suzuki Gakuto Kurata Samuel Thomas Jia Cui and Bhuvana Ramabhadran. 2017. Efficient Knowledge Distillation from an Ensemble of Teachers.. In Interspeech. 3697--3701.  Takashi Fukuda Masayuki Suzuki Gakuto Kurata Samuel Thomas Jia Cui and Bhuvana Ramabhadran. 2017. Efficient Knowledge Distillation from an Ensemble of Teachers.. In Interspeech. 3697--3701.","DOI":"10.21437\/Interspeech.2017-614"},{"key":"e_1_3_2_2_16_1","unstructured":"Ruohan Gao Tae-Hyun Oh Kristen Grauman and Lorenzo Torresani. 2020. Listen to look: Action recognition by previewing audio. In CVPR. 10457--10467.  Ruohan Gao Tae-Hyun Oh Kristen Grauman and Lorenzo Torresani. 2020. Listen to look: Action recognition by previewing audio. In CVPR. 10457--10467."},{"key":"e_1_3_2_2_17_1","volume-title":"Vitaly Ablavsky, Pietro Morerio, Vittorio Murino, and Stan Sclaroff.","author":"Garcia Nuno C","year":"2019","unstructured":"Nuno C Garcia , Sarah Adel Bargal , Vitaly Ablavsky, Pietro Morerio, Vittorio Murino, and Stan Sclaroff. 2019 . Dmcl : Distillation multiple choice learning for multimodal action recognition. arXiv preprint arXiv:1912.10982 (2019). Nuno C Garcia, Sarah Adel Bargal, Vitaly Ablavsky, Pietro Morerio, Vittorio Murino, and Stan Sclaroff. 2019. Dmcl: Distillation multiple choice learning for multimodal action recognition. arXiv preprint arXiv:1912.10982 (2019)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.06.004"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_2_2_20_1","unstructured":"Haodong Guo Ling Chen Liangying Peng and Gencai Chen. 2016. Wearable sensor based multimodal human activity recognition exploiting the diversity of classifier ensemble. In UbiComp. 1112--1123.  Haodong Guo Ling Chen Liangying Peng and Gencai Chen. 2016. Wearable sensor based multimodal human activity recognition exploiting the diversity of classifier ensemble. In UbiComp. 1112--1123."},{"key":"e_1_3_2_2_21_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton , Oriol Vinyals , and Jeff Dean . 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 ( 2015 ). Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Judy Hoffman Saurabh Gupta and Trevor Darrell. 2016. Learning with side information through modality hallucination. In CVPR. 826--834.  Judy Hoffman Saurabh Gupta and Trevor Darrell. 2016. Learning with side information through modality hallucination. In CVPR. 826--834.","DOI":"10.1109\/CVPR.2016.96"},{"key":"e_1_3_2_2_23_1","unstructured":"Mohamed E Hussein Marwan Torki Mohammad A Gowayyed and Motaz El-Saban. 2013. Human action recognition using a temporal hierarchy of covariance descriptors on 3d joint locations. In IJCAI.  Mohamed E Hussein Marwan Torki Mohammad A Gowayyed and Motaz El-Saban. 2013. Human action recognition using a temporal hierarchy of covariance descriptors on 3d joint locations. In IJCAI."},{"key":"e_1_3_2_2_24_1","volume-title":"Hamlet: A hierarchical multimodal attention-based human activity recognition algorithm. In IROS. 10285--10292.","author":"Islam Md Mofijul","year":"2020","unstructured":"Md Mofijul Islam and Tariq Iqbal . 2020 . Hamlet: A hierarchical multimodal attention-based human activity recognition algorithm. In IROS. 10285--10292. Md Mofijul Islam and Tariq Iqbal. 2020. Hamlet: A hierarchical multimodal attention-based human activity recognition algorithm. In IROS. 10285--10292."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Xiao Jin Baoyun Peng Yichao Wu Yu Liu Jiaheng Liu Ding Liang Junjie Yan and Xiaolin Hu. 2019. Knowledge distillation via route constrained optimization. In ICCV. 1345--1354.  Xiao Jin Baoyun Peng Yichao Wu Yu Liu Jiaheng Liu Ding Liang Junjie Yan and Xiaolin Hu. 2019. Knowledge distillation via route constrained optimization. In ICCV. 1345--1354.","DOI":"10.1109\/ICCV.2019.00143"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2014.04.007"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/FUTURETECH.2010.5482729"},{"key":"e_1_3_2_2_28_1","volume-title":"Paraphrasing complex network: Network compression via factor transfer. Advances in neural information processing systems","author":"Kim Jangho","year":"2018","unstructured":"Jangho Kim , SeongUk Park , and Nojun Kwak . 2018. Paraphrasing complex network: Network compression via factor transfer. Advances in neural information processing systems , Vol. 31 ( 2018 ). Jangho Kim, SeongUk Park, and Nojun Kwak. 2018. Paraphrasing complex network: Network compression via factor transfer. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_2_29_1","volume-title":"Cycle-contrast for self-supervised video representation learning. arXiv preprint arXiv:2010.14810","author":"Kong Quan","year":"2020","unstructured":"Quan Kong , Wenpeng Wei , Ziwei Deng , Tomoaki Yoshinaga , and Tomokazu Murakami . 2020. Cycle-contrast for self-supervised video representation learning. arXiv preprint arXiv:2010.14810 ( 2020 ). Quan Kong, Wenpeng Wei, Ziwei Deng, Tomoaki Yoshinaga, and Tomokazu Murakami. 2020. Cycle-contrast for self-supervised video representation learning. arXiv preprint arXiv:2010.14810 (2020)."},{"key":"e_1_3_2_2_30_1","volume-title":"Mmact: A large-scale dataset for cross modal human action understanding. In ICCV. 8658--8667.","author":"Kong Quan","year":"2019","unstructured":"Quan Kong , Ziming Wu , Ziwei Deng , Martin Klinkigt , Bin Tong , and Tomokazu Murakami . 2019 . Mmact: A large-scale dataset for cross modal human action understanding. In ICCV. 8658--8667. Quan Kong, Ziming Wu, Ziwei Deng, Martin Klinkigt, Bin Tong, and Tomokazu Murakami. 2019. Mmact: A large-scale dataset for cross modal human action understanding. In ICCV. 8658--8667."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Kisoo Kwon Hwidong Na Hoshik Lee and Nam Soo Kim. 2020. Adaptive knowledge distillation based on entropy. In ICASSP. 7409--7413.  Kisoo Kwon Hwidong Na Hoshik Lee and Nam Soo Kim. 2020. Adaptive knowledge distillation based on entropy. In ICASSP. 7409--7413.","DOI":"10.1109\/ICASSP40776.2020.9054698"},{"key":"e_1_3_2_2_32_1","volume-title":"Sang Min Yoon, and Heeryon Cho","author":"Lee Song-Mi","year":"2017","unstructured":"Song-Mi Lee , Sang Min Yoon, and Heeryon Cho . 2017 . Human activity recognition from accelerometer data using Convolutional Neural Network. In BigComp . 131--134. Song-Mi Lee, Sang Min Yoon, and Heeryon Cho. 2017. Human activity recognition from accelerometer data using Convolutional Neural Network. In BigComp. 131--134."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018561"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107356"},{"key":"e_1_3_2_2_35_1","volume-title":"Symbiotic graph neural networks for 3d skeleton-based human action recognition and motion prediction. TPAMI","author":"Li Maosen","year":"2021","unstructured":"Maosen Li , Siheng Chen , Xu Chen , Ya Zhang , Yanfeng Wang , and Qi Tian . 2021. Symbiotic graph neural networks for 3d skeleton-based human action recognition and motion prediction. TPAMI ( 2021 ). Maosen Li, Siheng Chen, Xu Chen, Ya Zhang, Yanfeng Wang, and Qi Tian. 2021. Symbiotic graph neural networks for 3d skeleton-based human action recognition and motion prediction. TPAMI (2021)."},{"key":"e_1_3_2_2_36_1","volume-title":"Tsm: Temporal shift module for efficient video understanding. In ICCV. 7083--7093.","author":"Lin Ji","year":"2019","unstructured":"Ji Lin , Chuang Gan , and Song Han . 2019 . Tsm: Temporal shift module for efficient video understanding. In ICCV. 7083--7093. Ji Lin, Chuang Gan, and Song Han. 2019. Tsm: Temporal shift module for efficient video understanding. In ICCV. 7083--7093."},{"key":"e_1_3_2_2_37_1","volume-title":"Spatio-temporal lstm with trust gates for 3d human action recognition","author":"Liu Jun","unstructured":"Jun Liu , Amir Shahroudy , Dong Xu , and Gang Wang . 2016. Spatio-temporal lstm with trust gates for 3d human action recognition . In ECCV. Springer , 816--833. Jun Liu, Amir Shahroudy, Dong Xu, and Gang Wang. 2016. Spatio-temporal lstm with trust gates for 3d human action recognition. In ECCV. Springer, 816--833."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2785279"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"Jun Liu Gang Wang Ping Hu Ling-Yu Duan and Alex C Kot. 2017b. Global context-aware attention lstm networks for 3d action recognition. In CVPR. 1647--1656.  Jun Liu Gang Wang Ping Hu Ling-Yu Duan and Alex C Kot. 2017b. Global context-aware attention lstm networks for 3d action recognition. In CVPR. 1647--1656.","DOI":"10.1109\/CVPR.2017.391"},{"key":"e_1_3_2_2_40_1","unstructured":"Linqing Liu Huan Wang Jimmy Lin Richard Socher and Caiming Xiong. 2019. Attentive student meets multi-task teacher: Improved knowledge distillation for pretrained models. (2019).  Linqing Liu Huan Wang Jimmy Lin Richard Socher and Caiming Xiong. 2019. Attentive student meets multi-task teacher: Improved knowledge distillation for pretrained models. (2019)."},{"key":"e_1_3_2_2_41_1","unstructured":"Mengyuan Liu and Junsong Yuan. 2018. Recognizing human actions as the evolution of pose estimation maps. In CVPR. 1159--1168.  Mengyuan Liu and Junsong Yuan. 2018. Recognizing human actions as the evolution of pose estimation maps. In CVPR. 1159--1168."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3086590"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2911204"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3428666"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.3390\/s18103363"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/BSN.2006.6"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"crossref","unstructured":"Sakorn Mekruksavanich and Anuchit Jitpattanakul. 2020. Smartwatch-based human activity recognition using hybrid lstm network. In 2020 IEEE SENSORS. 1--4.  Sakorn Mekruksavanich and Anuchit Jitpattanakul. 2020. Smartwatch-based human activity recognition using hybrid lstm network. In 2020 IEEE SENSORS. 1--4.","DOI":"10.1109\/SENSORS47125.2020.9278630"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ECTIDAMTNCON51128.2021.9425769"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.3390\/sym12091570"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"Federico Monti Karl Otness and Michael M Bronstein. 2018. Motifnet: a motif-based graph convolutional network for directed graphs. In DSW. 225--228.  Federico Monti Karl Otness and Michael M Bronstein. 2018. Motifnet: a motif-based graph convolutional network for directed graphs. In DSW. 225--228.","DOI":"10.1109\/DSW.2018.8439897"},{"key":"e_1_3_2_2_52_1","volume-title":"Anne HH Ngu, and Yan Yan","author":"Ni Jianyuan","year":"2021","unstructured":"Jianyuan Ni , Raunak Sarbajna , Yang Liu , Anne HH Ngu, and Yan Yan . 2021 . Cross-modal Knowledge Distillation for Vision-to-Sensor Action Recognition . arXiv preprint arXiv:2112.01849 (2021). Jianyuan Ni, Raunak Sarbajna, Yang Liu, Anne HH Ngu, and Yan Yan. 2021. Cross-modal Knowledge Distillation for Vision-to-Sensor Action Recognition. arXiv preprint arXiv:2112.01849 (2021)."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"crossref","unstructured":"Ferda Ofli Rizwan Chaudhry Gregorij Kurillo Ren\u00e9 Vidal and Ruzena Bajcsy. 2013. Berkeley mhad: A comprehensive multimodal human action database. In WACV. 53--60.  Ferda Ofli Rizwan Chaudhry Gregorij Kurillo Ren\u00e9 Vidal and Ruzena Bajcsy. 2013. Berkeley mhad: A comprehensive multimodal human action database. In WACV. 53--60.","DOI":"10.1109\/WACV.2013.6474999"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.3390\/s16010115"},{"key":"e_1_3_2_2_55_1","volume-title":"Security and privacy for artificial intelligence: Opportunities and challenges. arXiv preprint arXiv:2102.04661","author":"Oseni Ayodeji","year":"2021","unstructured":"Ayodeji Oseni , Nour Moustafa , Helge Janicke , Peng Liu , Zahir Tari , and Athanasios Vasilakos . 2021. Security and privacy for artificial intelligence: Opportunities and challenges. arXiv preprint arXiv:2102.04661 ( 2021 ). Ayodeji Oseni, Nour Moustafa, Helge Janicke, Peng Liu, Zahir Tari, and Athanasios Vasilakos. 2021. Security and privacy for artificial intelligence: Opportunities and challenges. arXiv preprint arXiv:2102.04661 (2021)."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"crossref","unstructured":"Madhuri Panwar S Ram Dyuthi K Chandra Prakash Dwaipayan Biswas Amit Acharyya Koushik Maharatna Arvind Gautam and Ganesh R Naik. 2017. CNN based approach for activity recognition using a wrist-worn accelerometer. In EMBC. 2438--2441.  Madhuri Panwar S Ram Dyuthi K Chandra Prakash Dwaipayan Biswas Amit Acharyya Koushik Maharatna Arvind Gautam and Ganesh R Naik. 2017. CNN based approach for activity recognition using a wrist-worn accelerometer. In EMBC. 2438--2441.","DOI":"10.1109\/EMBC.2017.8037349"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"crossref","unstructured":"Wonpyo Park Dongju Kim Yan Lu and Minsu Cho. 2019. Relational knowledge distillation. In CVPR. 3967--3976.  Wonpyo Park Dongju Kim Yan Lu and Minsu Cho. 2019. Relational knowledge distillation. In CVPR. 3967--3976.","DOI":"10.1109\/CVPR.2019.00409"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"crossref","unstructured":"Baoyun Peng Xiao Jin Jiaheng Liu Dongsheng Li Yichao Wu Yu Liu Shunfeng Zhou and Zhaoning Zhang. 2019. Correlation congruence for knowledge distillation. In ICCV. 5007--5016.  Baoyun Peng Xiao Jin Jiaheng Liu Dongsheng Li Yichao Wu Yu Liu Shunfeng Zhou and Zhaoning Zhang. 2019. Correlation congruence for knowledge distillation. In ICCV. 5007--5016.","DOI":"10.1109\/ICCV.2019.00511"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11058-w"},{"key":"e_1_3_2_2_60_1","volume-title":"Ali Saheb Pasand, and Ali Ghodsi","author":"Rezagholizadeh Mehdi","year":"2021","unstructured":"Mehdi Rezagholizadeh , Aref Jafari , Puneeth Salad , Pranav Sharma , Ali Saheb Pasand, and Ali Ghodsi . 2021 . Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher . arXiv preprint arXiv:2110.08532 (2021). Mehdi Rezagholizadeh, Aref Jafari, Puneeth Salad, Pranav Sharma, Ali Saheb Pasand, and Ali Ghodsi. 2021. Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher. arXiv preprint arXiv:2110.08532 (2021)."},{"key":"e_1_3_2_2_61_1","volume-title":"Antoine Chassang, Carlo Gatta, and Yoshua Bengio.","author":"Romero Adriana","year":"2014","unstructured":"Adriana Romero , Nicolas Ballas , Samira Ebrahimi Kahou , Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2014 . Fitnets : Hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014). Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2014. Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)."},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19071644"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"crossref","unstructured":"Lei Shi Yifan Zhang Jian Cheng and Hanqing Lu. 2019. Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In CVPR. 12026--12035.  Lei Shi Yifan Zhang Jian Cheng and Hanqing Lu. 2019. Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In CVPR. 12026--12035.","DOI":"10.1109\/CVPR.2019.01230"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86523-8_36"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107511"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3045135"},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"e_1_3_2_2_68_1","volume-title":"Constructing stronger and faster baselines for skeleton-based action recognition. arXiv preprint arXiv:2106.15125","author":"Song Yi-Fan","year":"2021","unstructured":"Yi-Fan Song , Zhang Zhang , Caifeng Shan , and Liang Wang . 2021. Constructing stronger and faster baselines for skeleton-based action recognition. arXiv preprint arXiv:2106.15125 ( 2021 ). Yi-Fan Song, Zhang Zhang, Caifeng Shan, and Liang Wang. 2021. Constructing stronger and faster baselines for skeleton-based action recognition. arXiv preprint arXiv:2106.15125 (2021)."},{"key":"e_1_3_2_2_69_1","volume-title":"Sudipta N Sinha, and Marc Pollefeys.","author":"Speciale Pablo","year":"2019","unstructured":"Pablo Speciale , Johannes L Schonberger , Sing Bing Kang , Sudipta N Sinha, and Marc Pollefeys. 2019 . Privacy preserving image-based localization. In CVPR. 5493--5503. Pablo Speciale, Johannes L Schonberger, Sing Bing Kang, Sudipta N Sinha, and Marc Pollefeys. 2019. Privacy preserving image-based localization. In CVPR. 5493--5503."},{"key":"e_1_3_2_2_70_1","volume-title":"Human action recognition from various data modalities: A review. arXiv preprint arXiv:2012.11866","author":"Sun Zehua","year":"2020","unstructured":"Zehua Sun , Qiuhong Ke , Hossein Rahmani , Mohammed Bennamoun , Gang Wang , and Jun Liu . 2020. Human action recognition from various data modalities: A review. arXiv preprint arXiv:2012.11866 ( 2020 ). Zehua Sun, Qiuhong Ke, Hossein Rahmani, Mohammed Bennamoun, Gang Wang, and Jun Liu. 2020. Human action recognition from various data modalities: A review. arXiv preprint arXiv:2012.11866 (2020)."},{"key":"e_1_3_2_2_71_1","volume-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems","author":"Tarvainen Antti","year":"2017","unstructured":"Antti Tarvainen and Harri Valpola . 2017. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems , Vol. 30 ( 2017 ). Antti Tarvainen and Harri Valpola. 2017. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"crossref","unstructured":"Fida Mohammad Thoker and Juergen Gall. 2019. Cross-modal knowledge distillation for action recognition. In ICIP. 6--10.  Fida Mohammad Thoker and Juergen Gall. 2019. Cross-modal knowledge distillation for action recognition. In ICIP. 6--10.","DOI":"10.1109\/ICIP.2019.8802909"},{"key":"e_1_3_2_2_73_1","unstructured":"Frederick Tung and Greg Mori. 2019. Similarity-preserving knowledge distillation. In ICCV. 1365--1374.  Frederick Tung and Greg Mori. 2019. Similarity-preserving knowledge distillation. In ICCV. 1365--1374."},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"crossref","unstructured":"Suraj Vantigodi and R Venkatesh Babu. 2013. Real-time human action recognition from motion capture data. In NCVPRIPG. 1--4.  Suraj Vantigodi and R Venkatesh Babu. 2013. Real-time human action recognition from motion capture data. In NCVPRIPG. 1--4.","DOI":"10.1109\/NCVPRIPG.2013.6776204"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"crossref","unstructured":"Suraj Vantigodi and Venkatesh Babu Radhakrishnan. 2014. Action recognition from motion capture data using meta-cognitive rbf network classifier. In ISSNIP. 1--6.  Suraj Vantigodi and Venkatesh Babu Radhakrishnan. 2014. Action recognition from motion capture data using meta-cognitive rbf network classifier. In ISSNIP. 1--6.","DOI":"10.1109\/ISSNIP.2014.6827664"},{"key":"e_1_3_2_2_76_1","doi-asserted-by":"crossref","unstructured":"Raviteja Vemulapalli Felipe Arrate and Rama Chellappa. 2014. Human action recognition by representing 3d skeletons as points in a lie group. In CVPR. 588--595.  Raviteja Vemulapalli Felipe Arrate and Rama Chellappa. 2014. Human action recognition by representing 3d skeletons as points in a lie group. In CVPR. 588--595.","DOI":"10.1109\/CVPR.2014.82"},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21165589"},{"key":"e_1_3_2_2_78_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2015.00028"},{"key":"e_1_3_2_2_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.198"},{"key":"e_1_3_2_2_80_1","doi-asserted-by":"crossref","unstructured":"Jiahao Wang Qiuling Long Kexuan Liu Yingzi Xie etal 2019. Human action recognition on cellphone using compositional bidir-lstm-cnn networks. In CNCI. Atlantis Press 687--692.  Jiahao Wang Qiuling Long Kexuan Liu Yingzi Xie et al. 2019. Human action recognition on cellphone using compositional bidir-lstm-cnn networks. In CNCI. Atlantis Press 687--692.","DOI":"10.2991\/cnci-19.2019.95"},{"key":"e_1_3_2_2_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449898"},{"key":"e_1_3_2_2_82_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-019-01116-y"},{"key":"e_1_3_2_2_83_1","volume-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"Wang Limin","unstructured":"Limin Wang , Yuanjun Xiong , Zhe Wang , Yu Qiao , Dahua Lin , Xiaoou Tang , and Luc Van Gool . 2016b. Temporal segment networks: Towards good practices for deep action recognition . In ECCV. Springer , 20--36. Limin Wang, Yuanjun Xiong, Zhe Wang, Yu Qiao, Dahua Lin, Xiaoou Tang, and Luc Van Gool. 2016b. Temporal segment networks: Towards good practices for deep action recognition. In ECCV. Springer, 20--36."},{"key":"e_1_3_2_2_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"e_1_3_2_2_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967191"},{"key":"e_1_3_2_2_86_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19173680"},{"key":"e_1_3_2_2_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00216"},{"key":"e_1_3_2_2_88_1","unstructured":"Meng-Chieh Wu Ching-Te Chiu and Kun-Hsuan Wu. 2019a. Multi-teacher knowledge distillation for compressed video action recognition on deep neural networks. In ICASSP. 2202--2206.  Meng-Chieh Wu Ching-Te Chiu and Kun-Hsuan Wu. 2019a. Multi-teacher knowledge distillation for compressed video action recognition on deep neural networks. In ICASSP. 2202--2206."},{"key":"e_1_3_2_2_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2982225"},{"key":"e_1_3_2_2_90_1","volume-title":"Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification","author":"Xiang Liuyu","unstructured":"Liuyu Xiang , Guiguang Ding , and Jungong Han . 2020. Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification . In ECCV. Springer , 247--263. Liuyu Xiang, Guiguang Ding, and Jungong Han. 2020. Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification. In ECCV. Springer, 247--263."},{"key":"e_1_3_2_2_91_1","doi-asserted-by":"crossref","unstructured":"Renyi Xiao Yonghong Hou Zihui Guo Chuankun Li Pichao Wang and Wanqing Li. 2019. Self-attention guided deep features for action recognition. In ICME. 1060--1065.  Renyi Xiao Yonghong Hou Zihui Guo Chuankun Li Pichao Wang and Wanqing Li. 2019. Self-attention guided deep features for action recognition. In ICME. 1060--1065.","DOI":"10.1109\/ICME.2019.00186"},{"key":"e_1_3_2_2_92_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015565"},{"key":"e_1_3_2_2_93_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_3_2_2_94_1","volume-title":"A study of face obfuscation in imagenet. arXiv preprint arXiv:2103.06191","author":"Yang Kaiyu","year":"2021","unstructured":"Kaiyu Yang , Jacqueline Yau , Li Fei-Fei , Jia Deng , and Olga Russakovsky . 2021. A study of face obfuscation in imagenet. arXiv preprint arXiv:2103.06191 ( 2021 ). Kaiyu Yang, Jacqueline Yau, Li Fei-Fei, Jia Deng, and Olga Russakovsky. 2021. A study of face obfuscation in imagenet. arXiv preprint arXiv:2103.06191 (2021)."},{"key":"e_1_3_2_2_95_1","unstructured":"Jingwen Ye Yixin Ji Xinchao Wang Kairi Ou Dapeng Tao and Mingli Song. 2019. Student becoming the master: Knowledge amalgamation for joint scene parsing depth estimation and more. In CVPR. 2829--2838.  Jingwen Ye Yixin Ji Xinchao Wang Kairi Ou Dapeng Tao and Mingli Song. 2019. Student becoming the master: Knowledge amalgamation for joint scene parsing depth estimation and more. In CVPR. 2829--2838."},{"key":"e_1_3_2_2_96_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098135"},{"key":"e_1_3_2_2_97_1","unstructured":"Sukmin Yun Jongjin Park Kimin Lee and Jinwoo Shin. 2020. Regularizing class-wise predictions via self-knowledge distillation. In CVPR. 13876--13885.  Sukmin Yun Jongjin Park Kimin Lee and Jinwoo Shin. 2020. Regularizing class-wise predictions via self-knowledge distillation. In CVPR. 13876--13885."},{"key":"e_1_3_2_2_98_1","volume-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928","author":"Zagoruyko Sergey","year":"2016","unstructured":"Sergey Zagoruyko and Nikos Komodakis . 2016. Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928 ( 2016 ). Sergey Zagoruyko and Nikos Komodakis. 2016. Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928 (2016)."},{"key":"e_1_3_2_2_99_1","doi-asserted-by":"publisher","DOI":"10.4108\/icst.mobicase.2014.257786"},{"key":"e_1_3_2_2_100_1","volume-title":"Confidence-Aware Multi-Teacher Knowledge Distillation. arXiv preprint arXiv:2201.00007","author":"Zhang Hailin","year":"2021","unstructured":"Hailin Zhang , Defang Chen , and Can Wang . 2021. Confidence-Aware Multi-Teacher Knowledge Distillation. arXiv preprint arXiv:2201.00007 ( 2021 ). Hailin Zhang, Defang Chen, and Can Wang. 2021. Confidence-Aware Multi-Teacher Knowledge Distillation. arXiv preprint arXiv:2201.00007 (2021)."},{"key":"e_1_3_2_2_101_1","doi-asserted-by":"crossref","unstructured":"Linfeng Zhang Jiebo Song Anni Gao Jingwei Chen Chenglong Bao and Kaisheng Ma. 2019. Be your own teacher: Improve the performance of convolutional neural networks via self distillation. In ICCV. 3713--3722.  Linfeng Zhang Jiebo Song Anni Gao Jingwei Chen Chenglong Bao and Kaisheng Ma. 2019. Be your own teacher: Improve the performance of convolutional neural networks via self distillation. In ICCV. 3713--3722.","DOI":"10.1109\/ICCV.2019.00381"},{"key":"e_1_3_2_2_102_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.24"},{"key":"e_1_3_2_2_103_1","volume-title":"Fusing geometric features for skeleton-based action recognition using multilayer LSTM networks. I?EEE Transactions on Multimedia","author":"Zhang Songyang","year":"2018","unstructured":"Songyang Zhang , Yang Yang , Jun Xiao , Xiaoming Liu , Yi Yang , Di Xie , and Yueting Zhuang . 2018. Fusing geometric features for skeleton-based action recognition using multilayer LSTM networks. I?EEE Transactions on Multimedia , Vol. 20 , 9 ( 2018 ), 2330--2343. Songyang Zhang, Yang Yang, Jun Xiao, Xiaoming Liu, Yi Yang, Di Xie, and Yueting Zhuang. 2018. Fusing geometric features for skeleton-based action recognition using multilayer LSTM networks. I?EEE Transactions on Multimedia, Vol. 20, 9 (2018), 2330--2343."},{"key":"e_1_3_2_2_104_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2935152"},{"key":"e_1_3_2_2_105_1","doi-asserted-by":"crossref","unstructured":"Rui Zhao Kang Wang Hui Su and Qiang Ji. 2019b. Bayesian graph convolution LSTM for skeleton based action recognition. In ICCV. 6882--6892.  Rui Zhao Kang Wang Hui Su and Qiang Ji. 2019b. Bayesian graph convolution LSTM for skeleton based action recognition. In ICCV. 6882--6892.","DOI":"10.1109\/ICCV.2019.00698"},{"key":"e_1_3_2_2_106_1","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/7316954"},{"key":"e_1_3_2_2_107_1","doi-asserted-by":"crossref","unstructured":"Bolei Zhou Alex Andonian Aude Oliva and Antonio Torralba. 2018. Temporal relational reasoning in videos. In ECCV. 803--818.  Bolei Zhou Alex Andonian Aude Oliva and Antonio Torralba. 2018. Temporal relational reasoning in videos. In ECCV. 803--818.","DOI":"10.1007\/978-3-030-01246-5_49"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548238","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548238","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:21Z","timestamp":1750186821000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548238"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":107,"alternative-id":["10.1145\/3503161.3548238","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548238","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}