151
click to vote
Publication
State-of-the-art person re-identi cation methods seek robust person matching through combining various feature types. Often, these features are implicitly assigned with a single ve...
CVPR
2012
IEEE
11 years 10 months ago
2012
IEEE
Foreground detection is at the core of many video processing tasks. In this paper, we propose a novel video foreground detection method that exploits the statistics of 3D space-tim...
Publication
This paper aims to address the problem of anomaly detection and discrimination in complex behaviours, where anomalies are subtle and difficult to detect owing to the complex tempor...
Publication
We present a new approach for activity modelling and anomaly detection based on non-parametric Gaussian Process (GP) models. Specifically, GP regression models are formulated to l...
226
click to vote
Dataset
QMUL junction dataset is for research on activity analysis and crowded scenes.
Video length: 1 hour (90000 frames)
Frame size: 360x288
Frame rate: 25 Hz
Compression codec: ff...
ACCV
2010
Springer
12 years 11 months ago
2010
Springer
Spatiotemporal segmentation is an essential task for video analysis. The strong interconnection between finding an object's spatial support and finding its motion characterist...
Publication
Computer scientists have made ceaseless efforts to replicate cognitive video understanding abilities
of human brains onto autonomous vision systems. As video surveillance cameras ...
COMPSYSTECH
2010
13 years 3 months ago
2010
: The interest of the scientific community for anthropocentric (human-centered) video analysis stems from the fact that the extracted information (e.g. human presence, identity, bo...
CHI
2009
ACM
13 years 5 months ago
2009
ACM
In this paper, we discuss the potential for effective representations of video data to aid analysis of large datasets of video clips and describe a prototype developed to explore ...