Z Zheng, L Yang, Y Wang, M Zhang… - … on Circuits and …, 2023 - ieeexplore.ieee.org
Recent years have witnessed a growing interest in compressed video action recognition due to the rapid growth of online videos. It remarkably reduces the storage by replacing raw …
Z Fan, J Liu, Y Wang - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Human pose estimation from videos has many real-world applications. Existing methods focus on applying models with a uniform computation profile on fully de-coded frames …
Compressed video action recognition has recently drawn growing attention, since it remarkably reduces the storage and computational cost via replacing raw videos by …
Y Hu, Y He, Y Li, J Li, Y Han… - Proceedings of the …, 2023 - openaccess.thecvf.com
Video semantic segmentation (VSS) is a computationally expensive task due to the per- frame prediction for videos of high frame rates. In recent work, compact models or adaptive …
Y Mou, X Jiang, K Xu, T Sun… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Compressed video action recognition offers the advantage of reducing decoding and inference time compared to the RGB domain. However, the compressed domain poses …
Modeling and recognizing video activities from videos are key parts of many promising applications such as visual surveillance, human–computer interaction, and video …
B Li, J Chen, X Bao, D Huang - Advances in Neural …, 2023 - proceedings.neurips.cc
Compressed videos offer a compelling alternative to raw videos, showing the possibility to significantly reduce the on-line computational and storage cost. However, current …
H Li, X Jiang, B Guan, RRM Tan… - … on Image Processing, 2021 - ieeexplore.ieee.org
Recent methods including CoViAR and DMC-Net provide a new paradigm for action recognition since they are directly targeted at compressed videos (eg, MPEG4 files). It …
D Zhuang, M Jiang, J Kong, T Liu - International Journal of Machine …, 2021 - Springer
In recent years, action recognition has become a popular and challenging task in computer vision. Nowadays, two-stream networks with appearance stream and motion stream can …