Discriminative Mixture-of-Templates for Viewpoint Classification

Gu, Chunhui; Ren, Xiaofeng

doi:10.1007/978-3-642-15555-0_30

Cited by 132 publications

(138 citation statements)

References 21 publications

Supporting

Mentioning

135

Contrasting

Order By: Relevance

“…While monolithic models are still common in the literature [7,21], there have been several influential approaches modeling multiple components of objects [10,12,5,17]. Nevertheless, each of these methods has it own limitations.…”

Section: Introductionmentioning

confidence: 99%

Multi-component Models for Object Detection

Arbeláez

Lin

et al. 2012

Computer Vision – ECCV 2012

Self Cite

View full text Add to dashboard Cite

Abstract. In this paper, we propose a multi-component approach for object detection. Rather than attempting to represent an object category with a monolithic model, or pre-defining a reduced set of aspects, we form visual clusters from the data that are tight in appearance and configuration spaces. We train individual classifiers for each component, and then learn a second classifier that operates at the category level by aggregating responses from multiple components. In order to reduce computation cost during detection, we adopt the idea of object window selection, and our segmentation-based selection mechanism produces fewer than 500 windows per image while preserving high object recall. When compared to the leading methods in the challenging VOC PASCAL 2010 dataset, our multi-component approach obtains highly competitive results. Furthermore, unlike monolithic detection methods, our approach allows the transfer of finer-grained semantic information from the components, such as keypoint location and segmentation masks.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-component Models for Object Detection

Arbeláez

Lin

et al. 2012

Computer Vision – ECCV 2012

Self Cite

View full text Add to dashboard Cite

show abstract

“…Green boxes indicate correct detections with an intersection over union ratio > 0.5; red boxes indicate false detections. With DPM+a, we capture a wider range of variation that does not only manifest in more detected people (ex 4,7,8,12), but also in more precise bounding boxes (ex 6,10,11,14). Both methods fail in case of highly occluded or truncated people, as in ex 5 and 10.…”

Section: Discussionmentioning

confidence: 99%

“…Appearance based clustering of training data in the context of the deformable part model by Felzenszwalb et al [9] was proposed by Gu et al [12]. The bounding box aspect ratio is supplemented by a distance on the HOG descriptors as a criterion to define the mixture components.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Training Deformable Object Models for Human Detection Based on Alignment and Clustering

Drayer

Brox

2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

Abstract. We propose a clustering method that considers non-rigid alignment of samples. The motivation for such a clustering is training of object detectors that consist of multiple mixture components. In particular, we consider the deformable part model (DPM) of Felzenszwalb et al., where each mixture component includes a learned deformation model. We show that alignment based clustering distributes the data better to the mixture components of the DPM than previous methods. Moreover, the alignment helps the non-convex optimization of the DPM find a consistent placement of its parts and, thus, learn more accurate part filters.

show abstract

“…Image-based viewpoint classification has been addressed in [17,7]. In these works, the number of viewpoints is limited and the task is solved by viewpoint classifier.…”

Section: Introductionmentioning

confidence: 99%

Fast Detection of Multiple Textureless 3-D Objects

Cai

Werner

Matas

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We propose a fast edge-based approach for detection and approximate pose estimation of multiple textureless objects in a single image. The objects are trained from a set of edge maps, each showing one object in one pose. To each scanning window in the input image, the nearest neighbor is found among these training templates by a twolevel cascade. The first cascade level, based on a novel edge-based sparse image descriptor and fast search by index table, prunes the majority of background windows. The second level verifies the surviving detection hypotheses by oriented chamfer matching, improved by selecting discriminative edges and by compensating a bias towards simple objects. The method outperforms the state-of-the-art approach by Damen et al. (2012). The processing is near real-time, ranging from 2 to 4 frames per second for the training set size ∼10 4 .

show abstract

Discriminative Mixture-of-Templates for Viewpoint Classification

Cited by 132 publications

References 21 publications

Multi-component Models for Object Detection

Multi-component Models for Object Detection

Training Deformable Object Models for Human Detection Based on Alignment and Clustering

Fast Detection of Multiple Textureless 3-D Objects

Contact Info

Product

Resources

About