Sciweavers

618 search results - page 74 / 124
» Instant Action Recognition
Sort
View
CVPR
2009
IEEE
15 years 6 months ago
Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos
Analyzing videos of human activities involves not only recognizing actions (typically based on their appearances), but also determining the story/plot of the video. The storyline ...
Abhinav Gupta, Praveen Srinivasan, Jianbo Shi, Lar...
ICRA
2009
IEEE
208views Robotics» more  ICRA 2009»
14 years 9 months ago
Affordance based word-to-meaning association
Abstract-- This paper presents a method to associate meanings to words in manipulation tasks. We base our model on an affordance network, i.e., a mapping between robot actions, rob...
Verica Krunic, Giampiero Salvi, Alexandre Bernardi...
ICCV
2009
IEEE
16 years 4 months ago
Weakly supervised discriminative localization and classification: a joint learning process
Visual categorization problems, such as object classification or action recognition, are increasingly often approached using a detection strategy: a classifier function is first ...
Minh Hoai Nguyen, Lorenzo Torresani, Fernando de l...
INFORMATICASI
2010
14 years 9 months ago
Planning to Discover and Counteract Attacks
Recognizing attack plans is one of the goals of security analysts. Attack plan recognition is critical for predicting future actions of attackers, generating possible actions (i.e...
Tatiana Kichkaylo, Tatyana Ryutov, Michael D. Oros...
CONNECTION
2006
101views more  CONNECTION 2006»
14 years 12 months ago
Learning acceptable windows of contingency
By learning a range of possible times over which the effect of an action can take place, a robot can reason more effectively about causal and contingent relationships in the world...
Kevin Gold, Brian Scassellati