Sciweavers

52 search results - page 4 / 11
» Metadata Challenges for Situational Properties of Learning O...
Sort
View
ECCV
2008
Springer
15 years 11 months ago
VideoCut: Removing Irrelevant Frames by Discovering the Object of Interest
We propose a novel method for removing irrelevant frames from a video given user-provided frame-level labeling for a very small number of frames. We first hypothesize a number of c...
David Liu, Gang Hua, Tsuhan Chen
ICCV
2005
IEEE
15 years 11 months ago
Combining Generative Models and Fisher Kernels for Object Recognition
Learning models for detecting and classifying object categories is a challenging problem in machine vision. While discriminative approaches to learning and classification have, in...
Alex Holub, Max Welling, Pietro Perona
CVPR
2008
IEEE
15 years 11 months ago
Unsupervised modeling of object categories using link analysis techniques
We propose an approach for learning visual models of object categories in an unsupervised manner in which we first build a large-scale complex network which captures the interacti...
Gunhee Kim, Christos Faloutsos, Martial Hebert
PAMI
2012
13 years 17 hour ago
CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts
—We present a novel framework to generate and rank plausible hypotheses for the spatial extent of objects in images using bottom-up computational processes and mid-level selectio...
João Carreira, Cristian Sminchisescu
CVPR
2012
IEEE
13 years 9 hour ago
Meta-class features for large-scale object categorization on a budget
In this paper we introduce a novel image descriptor enabling accurate object categorization even with linear models. Akin to the popular attribute descriptors, our feature vector ...
Alessandro Bergamo, Lorenzo Torresani