We investigate video classification via a two-stream convolutional neural network (CNN)
design that directly ingests information extracted from compressed video bitstreams. Our …

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 …

Advanced video classification systems decode video frames to derive texture and motion
representations for ingestion and analysis by spatio-temporal deep convolutional neural …

Convolutional neural networks (CNNs) have been exten-sively applied for image
recognition problems giving state-of-the-art results on recognition, detection, segmentation …

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 …

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 …