Sciweavers


0
posts
with
0
views
468profile views
vestrela@id.uff.brProfessor
Universidade Federal Fluminense
vestrela@id.uff.br
B.Sc. degree from Federal University of Rio de Janeiro (UFRJ) in Electrical and Computer Engineering (ECE); M.Sc. from the Instituto Tecnológico de Aeronáutica (ITA), Sao Jose ...

Publication
335views
11 years 6 months ago
Person Re-Identification: What Features are Important?
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...
Chunxiao Liu, Shaogang Gong, Chen Change Loy, Xing...

Publication
218views
11 years 9 months ago
Comparing Visual Feature Coding for Learning Disjoint Camera Dependencies
This paper systematically investigates the effectiveness of different visual feature coding schemes for facilitating the learning of time-delayed dependencies among disjoint multi-...
Xiatian Zhu, Shaogang Gong, and Chen Change Loy

Publication
363views
12 years 3 months ago
Detecting and Discriminating Behavioural Anomalies
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...
Chen Change Loy, Tao Xiang, Shaogang Gong

Publication
226views
12 years 3 months ago
Modelling Multi-object Activity by Gaussian Processes
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...
Chen Change Loy, Tao Xiang, Shaogang Gong

Publication
283views
12 years 3 months ago
Security and Surveillance
Human eyes are highly efficient devices for scanning through a large quantity of low-level visual sensory data and delivering selective information to one’s brain for high-level...
Shaogang Gong, Chen Change Loy, Tao Xiang

Dataset
1353views
12 years 3 months ago
QMUL Junction 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...

Publication
279views
12 years 10 months ago
Colour Invariant Head Pose Classification in Low Resolution Video
This paper presents an algorithm for the classification of head pose in low resolution video. Invariance to skin, hair and background colours is achieved by classifying using an en...
Ben Benfold and Ian Reid

Publication
285views
12 years 10 months ago
Guiding Visual Surveillance by Tracking Human Attention
We describe a novel method for directing the attention of an automated surveillance system. Our starting premise is that the attention of people in a scene can be used as an indica...
Ben Benfold and Ian Reid
CVPR
2011
IEEE
13 years 18 days ago
Relative pose problem for non-overlapping surveillance cameras with known gravity vector
We present a method for estimating the relative pose of two calibrated or uncalibrated non-overlapping surveillance cameras from observing a moving object. We show how to tackle t...
Branislav Micusik