Learning Semantic Scene Models by Trajectory Analysis

By Xiaogang Wang, Kinh H. Tieu, W. Grimson. European Conference on Computer Vision, 2006

322 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/40d90a85c9e4561025213aeeeae9d9571c1d337f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Ocean Engineering

Citations in the corpus

Understanding collective crowd behaviors: Learning a Mixture model of Dynamic pedestrian-Agents (2012, methodology): “Representative clusters of trajectories by A)MDA model, B)Spectral Clustering [24] and C)HDP [21].”
A Data-Driven Approach for Event Prediction (2010, methodology): “In this case, the algorithm is given a large corpus of training video captured at a particular location as input, and the objective is to identify abnormal events taking place in the future in that same scene [7, 8 ,9,10].”
Unsupervised Activity Perception in Crowded and Complicated Scenes Using Hierarchical Bayesian Models (2008, unknown): “Then, object tracks are used to model activities [7], [8], [9], [10], [11], [12], [13], [14], [15], [16], [17], [18].”
Detecting anomalous events in videos by learning deep representations of appearance and motion (2017, background): “Early works in the literature are based on the analysis of individual moving objects in the scene [5, 6, 7, 8].”
Unsupervised Activity Perception by Hierarchical Bayesian Models (2007, methodology): “The object tracks are used to model activities [8] [11] [13].”
Automatic Tractography Segmentation Using a High-Dimensional White Matter Atlas (2007, methodology): “The mean closest point measure has also been applied to trajectory clustering in outdoor video [32].”
Trajectory-Based Anomalous Event Detection (2008, methodology): “[27] define an ad hoc trajectory similarity measure and an associated clustering technique; and Dee and Hogg [28] detect anomalies using inexplicability scores, a measure of how much”
Object Segmentation by Long Term Analysis of Point Trajectories (2010, methodology): “For instance, it has been used for learning traffic models in [24].”
Intelligent multi-camera video surveillance: A review (2013, background): “Therefore, people prefer unsupervised approaches (Brand and Kettnaker , 2000; Song et al., 2003; Wang et al., 2006, 2009) which can automatically learn the models of activities without labeling training samples.”
Topic models for scene analysis and abnormality detection (2009, background): “In cases where the scene model is learnt by clustering trajectories [9, 2] abnormality is defined as an outlier trajectory i.”
Learning Deep Representations of Appearance and Motion for Anomalous Event Detection (2015, methodology): “In [33], trajectories which are spatially close and have similar motion patterns are identiﬁed and used for detecting unusual events.”
Learning object motion patterns for anomaly detection and improved object detection (2008, background): “Wang et al. [18] have presented another approach in which the tracks are clustered into vehicle and pedestrian paths.”
Multi-camera activity correlation analysis (2009, methodology): “[21] stitch trajectories of the same objects observed in different views to form so called “global trajectories”, which is then followed by the same trajectory clustering method developed for single view activity analysis [17].”