Andere Kunden interessierten sich auch für
![Le Complex Events Processing du cas métier à la technique]( "Le Complex Events Processing du cas métier à la technique")
Le Complex Events Processing du cas métier à la technique24,99 €![A Supervised Learning Model for Detecting Alzheimer's Disease]( "A Supervised Learning Model for Detecting Alzheimer's Disease")
A Supervised Learning Model for Detecting Alzheimer's Disease32,99 €![Detecting Anti-Pattern in Event-B]( "Detecting Anti-Pattern in Event-B")
Detecting Anti-Pattern in Event-B36,99 €![Real-time face detection in HD videos]( "Real-time face detection in HD videos")
Real-time face detection in HD videos24,99 €![Advanced Techniques for Detecting and Preventing 51% Attacks on Proof-of-Work Blockchains]( "Advanced Techniques for Detecting and Preventing 51% Attacks on Proof-of-Work Blockchains")
Advanced Techniques for Detecting and Preventing 51% Attacks on Proof-of-Work Blockchains11,99 €![Video Traffic Analysis for Abnormal Events Detection and Classification]( "Video Traffic Analysis for Abnormal Events Detection and Classification")
Video Traffic Analysis for Abnormal Events Detection and Classification35,99 €![Communicating in Risk, Crisis, and High Stress Situations: Evidence-Based Strategies and Practice]( "Communicating in Risk, Crisis, and High Stress Situations: Evidence-Based Strategies and Practice")
Communicating in Risk, Crisis, and High Stress Situations: Evidence-Based Strategies and Practice58,99 €
Video event detection is one of the most important research topics in computer science. The recognition of complex events, e.g. ¿birthday party¿, ¿wedding ceremony¿ or ¿attempting a bike trick¿, is even more difficult since complex events consist of various human interactions with different objects in diverse environments with variable time intervals. In this book, we propose two learning methods. The first proposed method, named maximal evidence learning (MEL), is based on a large-margin formulation that treats instance labels as hidden latent variables, and infers the instance labels and the instance-level classification model simultaneously. MEL can infer optimal solutions by learning as many positive instances as possible from positive videos, and negative instances from negative videos. The second proposed method is called evidence selective ranking (ESR). ESR is based on static-dynamic instance embedding, and employs infinite push ranking to select the most distinctive evidence. Extensive analysis on large-scale video event datasets shows significant performance gains by both methods.In addition, we also demonstrate key selected evidence is meaningful to humans and can be used to locate video segments that signify an event.