The vireo group participated in four tasks: instance search, semantic indexing, multimedia event detection and known-item search. In this paper,we will present our approaches and discuss the evaluation results. Instance Search (INS): We experimented four runs to contrast the following for instance search: full matching (vireo b) versus partial matching (vireo m); use of weak geometric informati...

5 We investigate how human action recognition can be improved by considering spatio-temporal layout of 6 actions. From literature, we adopt a pipeline consisting of STIP features, a random forest to quantize the 7 features into histograms, and an SVM classifier. Our goal is to detect 48 human actions, ranging from simple 8 actions such as walk to complex actions such as exchange. Our contributi...

Recent progress in the field of human action recognition points towards the use of Spatio-Temporal Interest Points (STIPs) for local descriptor-based recognition strategies. In this paper, we present a novel approach for robust and selective STIP detection, by applying surround suppression combined with local and temporal constraints. This new method is significantly different from existing STI...