Much of recent action recognition research is based on
space-time interest points extracted from video using a Bag
of Words (BOW) representation. It mainly relies on the discrimi...
Matteo Bregonzio (Queen Mary, University of London...
Videos of multi-player team sports provide a challenging domain for dynamic scene analysis. Player actions and interactions are complex as they are driven by many factors, such as...
Kihwan Kim, Matthias Grundmann, Ariel Shamir, Iain...
Real-time unusual event detection in video stream has been a difficult challenge due to the lack of sufficient training information, volatility of the definitions for both norm...
Although more efficient in computation compared to other tracking approaches such as particle filtering, the kernel-based tracking suffers from the "singularity" problem...
Semantic concept detectors are often individually and independently developed. Using peripherally related concepts for leveraging the power of joint detection, which is referred t...