Sciweavers

27 search results - page 3 / 6
» Discriminative Figure-Centric Models for Joint Action Locali...
Sort
View
ECCV
2010
Springer
13 years 10 months ago
Tracklet Descriptors  for Action Modeling and Video Analysis
We present spatio-temporal feature descriptors that can be inferred from video and used as building blocks in action recognition systems. They capture the evolution of ``elementar...
Michalis Raptis , Stefano Soatto
CVPR
2012
IEEE
11 years 7 months ago
Discovering discriminative action parts from mid-level video representations
We describe a mid-level approach for action recognition. From an input video, we extract salient spatio-temporal structures by forming clusters of trajectories that serve as candi...
Michalis Raptis, Iasonas Kokkinos, Stefano Soatto
ICPR
2008
IEEE
13 years 11 months ago
Full body tracking-based human action recognition
In this paper, we present a novel method for human action recognition with the combined global movement feature and local configuration feature. The human action is represented as...
Junxia Gu, Xiaoqing Ding, Shengjin Wang, Youshou W...
WACV
2012
IEEE
12 years 9 days ago
Simultaneous inference of activity, pose and object
Human movements are important cues for recognizing human actions, which can be captured by explicit modeling and tracking of actor or through space-time low-level features. Howeve...
Furqan M. Khan, Vivek Kumar Singh, Ram Nevatia
ICCV
2007
IEEE
14 years 6 months ago
Retrieving actions in movies
We address recognition and localization of human actions in realistic scenarios. In contrast to the previous work studying human actions in controlled settings, here we train and ...
Ivan Laptev, Patrick Pérez