NDLI: Randomized Max-Margin Compositions for Visual Recognition

Content Provider	IEEE Xplore Digital Library
Author	Eigenstetter, A. Takami, M. Ommer, B.
Copyright Year	2014
Description	Author affiliation: Heidelberg Collaboratory for Image Process. & IWR, Univ. of Heidelberg, Heidelberg, Germany (Eigenstetter, A.; Takami, M.; Ommer, B.)
Abstract	A main theme in object detection are currently discriminative part-based models. The powerful model that combines all parts is then typically only feasible for few constituents, which are in turn iteratively trained to make them as strong as possible. We follow the opposite strategy by randomly sampling a large number of instance specific part classifiers. Due to their number, we cannot directly train a powerful classifier to combine all parts. Therefore, we randomly group them into fewer, overlapping compositions that are trained using a maximum-margin approach. In contrast to the common rationale of compositional approaches, we do not aim for semantically meaningful ensembles. Rather we seek randomized compositions that are discriminative and generalize over all instances of a category. Our approach not only localizes objects in cluttered scenes, but also explains them by parsing with compositions and their constituent parts. We conducted experiments on PASCAL VOC'07, on the VOC'10 evaluation server, and on the MITIndoor scene dataset. To the best of our knowledge, our randomized max-margin compositions (RM2C) are the currently best performing single class object detector using only HOG features. Moreover, the individual contributions of compositions and their parts are evaluated in separate experiments that demonstrate their potential.
Starting Page	3590
Ending Page	3597
File Size	1170050
Page Count	8
File Format	PDF
ISBN	9781479951185
ISSN	10636919
DOI	10.1109/CVPR.2014.459
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2014-06-23
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Training Visualization Object detection Object recognition Support vector machines Deformable models Pattern recognition randomized models object detection visual recognition scene classification compositionality mid-level representation part-based models visual parsing
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Hierarchical Joint Max-Margin Learning of Mid and Top Level Representations for Visual Recognition

Max-margin additive classifiers for detection

Max Margin Learning of Hierarchical Configural Deformable Templates (HCDTs) for Efficient Object Parsing and Pose Estimation

Discriminatively Trained And-Or Tree Models for Object Detection

A discriminatively trained, multiscale, deformable part model

Cascade object detection with deformable part models

Part-Based Visual Tracking with Online Latent Structural Learning

Max-margin analysis based patch sampling for discovery of mid-level parts

From Subcategories to Visual Composites: A Multi-level Framework for Object Detection

Randomized Max-Margin Compositions for Visual Recognition

Similar Documents

Hierarchical Joint Max-Margin Learning of Mid and Top Level Representations for Visual Recognition

Max-margin additive classifiers for detection

Max Margin Learning of Hierarchical Configural Deformable Templates (HCDTs) for Efficient Object Parsing and Pose Estimation

Discriminatively Trained And-Or Tree Models for Object Detection

A discriminatively trained, multiscale, deformable part model

Cascade object detection with deformable part models

Part-Based Visual Tracking with Online Latent Structural Learning

Max-margin analysis based patch sampling for discovery of mid-level parts

From Subcategories to Visual Composites: A Multi-level Framework for Object Detection

Randomized Max-Margin Compositions for Visual Recognition