Video data is becoming a much more prevalent medium for transmitting information. While object classification in still images has been a standard task for the computer vision community, the importance of having computers understand video sequences is beginning to be recognized. One task that has emerged from automated video understanding is action classification. In this task, the computer must...

This project aims to assign a gender to the humans detected by a video. The input is a video taken from a moving car on the streets of Philadelphia. As a result, the human objects are full body and the resolution of facial expressions is low. Features used are presence of bags, length of clothes and presence of pink among others to arrive at a hypothesis on gender. This information could be use...

In this paper, we propose a new multi-modal deep learning framework with visual modality and textual for video game genre classification. The proposed consists of three parts: two deeep networks data imaginary data, feature concatenation algorithm, then softmax classifier. Video covers descriptions are usually the very first impression to its consumers they often convey important information ab...

The large amount of videos usage increase the volume of data, more time to access and more man power is required. Video summarization is the solution for this problem. Summarized video can be used to review the important aspect of particular video, indexing and faster browsing. Video summarization techniques are classified into key frame based classification and skim based classification. This ...

In this article, we will discuss the classification of moving objects in videos. An overview of classical steps in video classification will be given and a particular attention will be given to classification in video surveillance since classification in this kind of systems is very important and plays a primary role in several functions such as event classification, speed control, classificati...

In this paper, we present a novel automated indexing and semantic labeling for broadcast soccer video sequences. The proposed method automatically extracts silent events from the video and classifies each event sequence into a concept by sequential association mining. The paper makes three new contributions in multimodal sports video indexing and summarization. First, we propose a novel hierarc...