Looking beyond the image: Unsupervised learning for object saliency and detection
We propose a principled probabilistic formulation of object saliency as a sampling problem.
This novel formulation allows us to learn, from a large corpus of unlabelled images, which …
This novel formulation allows us to learn, from a large corpus of unlabelled images, which …
Multi-scale and real-time non-parametric approach for anomaly detection and localization
In this paper we propose an approach for anomaly detection and localization, in video
surveillance applications, based on spatio-temporal features that capture scene dynamic …
surveillance applications, based on spatio-temporal features that capture scene dynamic …
Event detection in video sequences: Challenges and perspectives
The growing need for information and high-quality video cameras has led to the proliferation
of video based systems that perform tasks such as traffic monitoring, surveillance, etc. A …
of video based systems that perform tasks such as traffic monitoring, surveillance, etc. A …
Identifying rare and subtle behaviors: A weakly supervised joint topic model
One of the most interesting and desired capabilities for automated video behavior analysis is
the identification of rarely occurring and subtle behaviors. This is of practical value because …
the identification of rarely occurring and subtle behaviors. This is of practical value because …
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 …
visual sensory data and delivering selective information to one's brain for high-level …
Unsupervised abnormal crowd activity detection using semiparametric scan statistic
We propose a fully unsupervised method for abnormal activity detection in crowded scenes.
Neither normal nor abnormal training examples are needed before detection. By observing …
Neither normal nor abnormal training examples are needed before detection. By observing …
Visual interestingness in image sequences
Interestingness is said to be the power of attracting or holding one's attention (because
something is unusual or exciting, etc.). We, as humans, have the great capacity to direct our …
something is unusual or exciting, etc.). We, as humans, have the great capacity to direct our …
Exploiting simple hierarchies for unsupervised human behavior analysis
We propose a data-driven, hierarchical approach for the analysis of human actions in visual
scenes. In particular, we focus on the task of in-house assisted living. In such scenarios the …
scenes. In particular, we focus on the task of in-house assisted living. In such scenarios the …
A prototype learning framework using emd: Application to complex scenes analysis
In the last decades, many efforts have been devoted to develop methods for automatic
scene understanding in the context of video surveillance applications. This paper presents a …
scene understanding in the context of video surveillance applications. This paper presents a …
Local abnormal behavior detection based on optical flow and spatio-temporal gradient
S Zhu, J Hu, Z Shi - Multimedia Tools and Applications, 2016 - Springer
To improve the accuracy of the detection of local abnormal behavior, a novel method is here
proposed. The main idea of the proposed method is described as follows: firstly, a video …
proposed. The main idea of the proposed method is described as follows: firstly, a video …