Abstract. This paper presents an exemplar-based approach to detecting and localizing human actions, such as running, cycling, and swinging, in realistic videos with dynamic backgro...
We present a novel approach for detecting global behaviour
anomalies in multiple disjoint cameras by learning
time delayed dependencies between activities cross camera
views. Sp...
Multi-class classification schemes typically require human input in the form of precise category names or numbers for each example to be annotated – providing this can be impra...
Ajay Joshi, Fatih Porikli, Nikolaos Papanikolopoul...
Relevance feedback, which traditionally uses the terms in the relevant documents to enrich the user's initial query, is an effective method for improving retrieval performanc...
Feature selection, as a preprocessing step to machine learning, has been very effective in reducing dimensionality, removing irrelevant data, increasing learning accuracy, and imp...