We investigate video classification via a two-stream convolutional neural network (CNN) design that directly ingests information extracted from compressed video bitstreams. Our approach begins with the observation that all modern video codecs divide the input frames into macroblocks (MBs). We demonstrate that selective access to MB motion vector (MV) information within compressed video bitstrea...

The recognition of objects that appear in a video sequence is an essential aspect of any video content analysis system. We present an approach which classifies a segmented video object based on its appearance (object views) in successive video frames. The classification is performed by matching curvature features of the contours of these object views to a database containing preprocessed views ...

The recognition of objects that appear in a video sequence is an essential aspect of any video content analysis system. We present an approach which classifies a segmented video object based on its appearance (object views) in successive video frames. The classification is performed by matching curvature features of the contours of these object views to a database containing preprocessed views ...

A nonparametric video retrieval and frame classification systm that uses affinity propagation algorithm is proposed. The main goal of the proposed system is to develop "tiny video" that achieves high video compression rates while retaining the overall visual appearance of video. The proposed video retrieval system utilizes the strengths of affinity propagation algorithm that uses exem...

Computer vision applications often need to process only a representative part of the visual input rather than the whole image/sequence. Considerable research has been carried out into salient region detection methods based either on models emulating human visual attention (VA) mechanisms or on computational approximations. Most of the proposed methods are bottom-up and their major goal is to fi...

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 classification community and the use of deep convolutional networks (CNNs) which produce competitive results with handcrafted motion features. These networks were adapted to use video frames in various ways and have yielded stat...

In this paper we address the problem of sports video classification Using Hidden Markov Models (HMMs). For each sports genre, we construct two HMMs representing motion and color features respectively. The observation sequences generated from the principal motion direction and the principal color of each frame are fed to a motion and a color HMM respectively. The outputs are integrated to make a...

In this paper we propose an innovative combination strategy for a system using video and audio stream of a news video to automatically segment it into stories. In our approach, the segmentation is performed in two steps: first, shots are classified by combining three different anchor shot detection algorithms using video information only. Then, the shot classification is improved by using a nov...

A video shot is defined as a continuously imaged temporal segment of a video. Since the semantic content of a video is largely based on its production (imaging) process, the complete segmentation of a video into shots is a fundamental first step for most kinds of semantic video processing tasks. Here we present a classification of shot boundary detection algorithms, including those that deal wi...

The recognition of objects that appear in a video sequence is an essential aspect of any video content analysis system. We present an approach which classifies a segmented video object based on its appearance (object views) in successive video frames. The classification is performed by matching curvature features of the contours of these object views to a database containing preprocessed views ...