Multiclass Object Recognition with Sparse, Localized Features

Mutch, Jim; Lowe, David

doi:10.1109/cvpr.2006.200

Cited by 346 publications

(316 citation statements)

References 22 publications

Supporting

Mentioning

303

Contrasting

Unclassified

Order By: Relevance

“…At various points in time, these models have matched or surpassed state-of-the-art systems on datasets such as CalTech101 [24,32] and Labeled-Faces-in-the-Wild (LFW) [26,27]. These results reinforce the belief that ultimately, the quest to understand the key properties of biological intelligence will be essential in producing truly intelligent artificial systems.…”

Section: From Neuroscience Models To Engineering Applicationssupporting

confidence: 69%

Throwing Down the Visual Intelligence Gauntlet

Tan

Leibo

Poggio

2013

Machine Learning for Computer Vision

View full text Add to dashboard Cite

Section: From Neuroscience Models To Engineering Applicationssupporting

confidence: 69%

Throwing Down the Visual Intelligence Gauntlet

Tan

Leibo

Poggio

2013

Machine Learning for Computer Vision

View full text Add to dashboard Cite

“…Fergus et al [7] adopted a similar approach, but included a greater array of invariants and so produced a system that might be expected to be more robust to changes in scale, orientation and so on (but we are not aware of any authoritative comparison). Similar work continues to date, see [19,11,18,1] for example.…”

Section: Introductionmentioning

confidence: 69%

Learning object classes from structure

Xiao¹,

Song²,

Hall³

2007

Procedings of the British Machine Vision Conference 2007

View full text Add to dashboard Cite

The problem of identifying the class of an object from its visual appearance has received significant attention recently. Most of the work to date is premised on photometric measures, often building codebooks made from interest regions. All of it has been tested only on photographs, so far as we know. Our approach differs in two significant ways. First, we do not build a codebook of interest regions but instead make use of a hierarchical description of an image based on a watershed transform. Root nodes in the hierarchy are putative objects to be classified. Second, we classify these putative objects using a vector of fixed length that represents the structure of the hierarchy below the node. This allows us to classify not just photographs, but also paintings and drawings of visual objects.

show abstract

“…Other approaches include filtering techniques [29] and sampling of video patches [1]. Hierarchical techniques for activity recognition have been used as well, but these typically focus on neurologically-inspired visual cortex-type models [9,32,23,28]. Often, these authors adhere faithfully to the models of the visual cortex, using motion-direction sensitive "cells" such as Gabor filters in the first layer [11,26].…”

Section: Introductionmentioning

confidence: 99%

Unstructured human activity detection from RGBD images

Sung

Ponce

Selman

et al. 2012

2012 IEEE International Conference on Robotics and Automation

201

View full text Add to dashboard Cite

Abstract-Being able to detect and recognize human activities is essential for several applications, including personal assistive robotics. In this paper, we perform detection and recognition of unstructured human activity in unstructured environments. We use a RGBD sensor (Microsoft Kinect) as the input sensor, and compute a set of features based on human pose and motion, as well as based on image and pointcloud information. Our algorithm is based on a hierarchical maximum entropy Markov model (MEMM), which considers a person's activity as composed of a set of sub-activities. We infer the two-layered graph structure using a dynamic programming approach. We test our algorithm on detecting and recognizing twelve different activities performed by four people in different environments, such as a kitchen, a living room, an office, etc., and achieve good performance even when the person was not seen before in the training set. 1

show abstract

Multiclass Object Recognition with Sparse, Localized Features

Abstract: We apply a biologically inspired model of visual object recognition to the multiclass object categorization problem.

Cited by 346 publications

References 22 publications

Throwing Down the Visual Intelligence Gauntlet

Throwing Down the Visual Intelligence Gauntlet

Learning object classes from structure

Unstructured human activity detection from RGBD images

Contact Info

Product

Resources

About