Sciweavers

659 search results - page 35 / 132
» Object Labelling from Human Action Recognition
Sort
View

Publication
922views
16 years 9 months ago
Multi-Class Active Learning for Image Classification
One of the principal bottlenecks in applying learning techniques to classification problems is the large amount of labeled training data required. Especially for images and video, ...
Ajay J. Joshi, Fatih Porikli, Nikolaos Papanikolop...
120
Voted
ICRA
2008
IEEE
288views Robotics» more  ICRA 2008»
15 years 8 months ago
Human tracking and segmentation supported by silhouette-based gait recognition
— Gait recognition has recently gained attention as an effective approach to identify individuals at a distance from a camera. Most existing gait recognition algorithms assume th...
Junqiu Wang, Yasushi Makihara, Yasushi Yagi
ICCV
2011
IEEE
14 years 2 months ago
Actively Selecting Annotations Among Objects and Attributes
We present an active learning approach to choose image annotation requests among both object category labels and the objects’ attribute labels. The goal is to solicit those labe...
Adriana Kovashka, Sudheendra Vijayanarasimhan, Kri...
ICASSP
2011
IEEE
14 years 5 months ago
Hierarchical Latent Dirichlet Allocation models for realistic action recognition
It has always been very difficult to recognize realistic actions from unconstrained videos because there are tremendous variations from camera motion, background clutter, object a...
Heping Li, Jie Liu, Shuwu Zhang
ICCV
2011
IEEE
14 years 2 months ago
Discriminative Figure-Centric Models for Joint Action Localization and Recognition
In this paper we develop an algorithm for action recognition and localization in videos. The algorithm uses a figurecentric visual word representation. Different from previous ap...
Tian Lan, Yang Wang, Greg Mori