Progressive Cross-modal Knowledge Distillation for Human Action Recognition
Author:
Affiliation:
1. Texas State University, San Marcos, TX, USA
2. Texas State University, San Marcos, IL, USA
Funder
NSF
Publisher
ACM
Link
https://dl.acm.org/doi/pdf/10.1145/3503161.3548238
Reference107 articles.
1. CNN-Based Multistage Gated Average Fusion (MGAF) for Human Action Recognition Using Depth and Inertial Sensors
2. 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.
3. 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).
4. 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.
5. 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.
Cited by 7 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Privilege-guided knowledge distillation for edge deployment in excavator activity recognition;Automation in Construction;2024-10
2. QMKD: A Two-Stage Approach to Enhance Multi-Teacher Knowledge Distillation;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30
3. Multiscale knowledge distillation with attention based fusion for robust human activity recognition;Scientific Reports;2024-05-30
4. Data-Efficient Masked Video Modeling for Self-supervised Action Recognition;Proceedings of the 31st ACM International Conference on Multimedia;2023-10-26
5. DANet: Multi-scale UAV Target Detection with Dynamic Feature Perception and Scale-aware Knowledge Distillation;Proceedings of the 31st ACM International Conference on Multimedia;2023-10-26
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3