A Chadha, A Abbas… - 2017 IEEE International …, 2017 - ieeexplore.ieee.org
We investigate video classification via a 3D deep convolutional neural network (CNN) that directly ingests compressed bitstream information. This idea is based on the observation that …
Group convolution has been shown to offer great computational savings in various 2D convolutional architectures for image classification. It is natural to ask: 1) if group convolution …
M Jubran, A Abbas, A Chadha… - IEEE Transactions on …, 2018 - ieeexplore.ieee.org
Advanced video classification systems decode video frames to derive texture and motion representations for ingestion and analysis by spatio-temporal deep convolutional neural …
J Yue-Hei Ng, M Hausknecht… - Proceedings of the …, 2015 - cv-foundation.org
Convolutional neural networks (CNNs) have been exten-sively applied for image recognition problems giving state-of-the-art results on recognition, detection, segmentation …
H Ye, Z Wu, RW Zhao, X Wang, YG Jiang… - Proceedings of the 5th …, 2015 - dl.acm.org
Videos contain very rich semantic information. Traditional hand-crafted features are known to be inadequate in analyzing complex video semantics. Inspired by the huge success of the …
Motion plays a crucial role in understanding videos and most state-of-the-art neural models for video classification incorporate motion information typically using optical flows extracted …
Video classification has advanced tremendously over the recent years. A large part of the improvements in video classification had to do with the work done by the image …
J Zheng, X Cao, B Zhang, X Zhen… - IEEE transactions on …, 2018 - ieeexplore.ieee.org
Video classification has been extensively researched in computer vision due to its wide spread applications. However, it remains an outstanding task because of the great …
Abstract Convolutional Neural Networks (CNNs) have been established as a powerful class of models for image recognition problems. Encouraged by these results, we provide an …