TY - GEN
T1 - Recaspia
T2 - 26th IEEE International Conference on Image Processing, ICIP 2019
AU - Smailis, Christos
AU - Vrigkas, Michalis
AU - Kakadiaris, Ioannis A.
N1 - Funding Information:
Acknowledgments: This material is supported by the U.S. Department of Homeland Security under Grant Award Number 2017-STBTI-0001-0201 with resources provided by the Core facility for Advanced Computing and Data Science at the University of Houston. The authors gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/9
Y1 - 2019/9
N2 - Many approaches for action recognition focus on general actions, such as 'running' or 'walking'. This work presents a method for recognizing carrying actions in single images, by utilizing privileged information, such as annotation, available only during training, following the learning using privileged information paradigm. In addition, we introduce a dataset for carrying actions, formed using images extracted from YouTube videos depicting several scenarios. We accompany the dataset with a variety of different annotation types that include human pose, object and scene attributes. The experimental results demonstrate that our method, boosted sample averaged F1 score performance by 15.4% and 4.15%, respectively, in the validation and testing partitions of our dataset, when compared to an end-to-end CNN model, trained only with the observable information.
AB - Many approaches for action recognition focus on general actions, such as 'running' or 'walking'. This work presents a method for recognizing carrying actions in single images, by utilizing privileged information, such as annotation, available only during training, following the learning using privileged information paradigm. In addition, we introduce a dataset for carrying actions, formed using images extracted from YouTube videos depicting several scenarios. We accompany the dataset with a variety of different annotation types that include human pose, object and scene attributes. The experimental results demonstrate that our method, boosted sample averaged F1 score performance by 15.4% and 4.15%, respectively, in the validation and testing partitions of our dataset, when compared to an end-to-end CNN model, trained only with the observable information.
KW - Action Recognition
KW - Deep Learning
KW - LUPI
KW - Privileged Information
KW - Static Images
UR - http://www.scopus.com/inward/record.url?scp=85076817737&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85076817737&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2019.8802916
DO - 10.1109/ICIP.2019.8802916
M3 - Conference contribution
AN - SCOPUS:85076817737
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 26
EP - 30
BT - 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 22 September 2019 through 25 September 2019
ER -