21,824 Hits in 3.9 sec

Learning Features and Parts for Fine-Grained Recognition

Jonathan Krause, Timnit Gebru, Jia Deng, Li-Jia Li, Li Fei-Fei
2014 2014 22nd International Conference on Pattern Recognition  
The part detectors are learned in a fully unsupervised manner, based on the insight that images with similar poses can be automatically discovered for fine-grained classes in the same domain.  ...  We focus on two major challenges: learning expressive appearance descriptors and localizing discriminative parts.  ...  Suppose we have a collection of n object parts with associated part detectors, which we assume for now have already been trained.  ... 
doi:10.1109/icpr.2014.15 dblp:conf/icpr/KrauseGDLF14 fatcat:mh7b3p4glzgjnkjdlyavbfd4xy

Ensemble of Part Detectors for Simultaneous Classification and Localization [article]

Xiaopeng Zhang, Hongkai Xiong, Weiyao Lin, Qi Tian
2017 arXiv   pre-print
However, automatic discovery of discriminative parts without object/part-level annotations is challenging.  ...  This paper proposes a discriminative mid-level representation paradigm based on the responses of a collection of part detectors, which only requires the image-level labels.  ...  LEARNING PART DETECTORS In this section, we target at learning a collection of discriminative part detectors automatically for image representation.  ... 
arXiv:1705.10034v1 fatcat:qcrjsblvg5bobptvq5px7g3y54

Learning Collections of Part Models for Object Recognition

Ian Endres, Kevin J. Shih, Johnston Jiaa, Derek Hoiem
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
We propose a method to learn a diverse collection of discriminative parts from object bounding box annotations.  ...  We apply the parts to object category detection, pooling part detections within bottom-up proposed regions and using a boosted classifier with proposed sigmoid weak learners for scoring.  ...  Acknowledgements This research is supported in part by ONR MURI grant N000141010934, NSF CAREER award 10-53768, and NSF award IIS 09-04209.  ... 
doi:10.1109/cvpr.2013.126 dblp:conf/cvpr/EndresSJH13 fatcat:icbxdvmmmbct7b5ej76ydhlkk4

Multiple Human Tracking Based on Multi-view Upper-Body Detection and Discriminative Learning

Junliang Xing, Haizhou Ai, Shihong Lao
2010 2010 20th International Conference on Pattern Recognition  
What is more, an online learning process is proposed to learn discriminative human observations, including discriminative interest points and color patches, to effectively track each human when even more  ...  To cope with the difficulties it presents, an offline boosted multiview upper-body detector is used to automatically initialize a new human trajectory and is capable of dealing with partial human occlusions  ...  ACKNOWLEDGMENT This work is supported in part by National Basic Research Program of China (2006CB303102), Beijing Educational Committee Program (YB20081000303), and it is also supported by a grant from  ... 
doi:10.1109/icpr.2010.420 dblp:conf/icpr/XingAL10 fatcat:4rkp4xkimjbtbfnuwz2pr6jffa

Learning Co-occurrence of Local Spatial Strokes for Robust Character Recognition

Song GAO, Chunheng WANG, Baihua XIAO, Cunzhao SHI, Wen ZHOU, Zhong ZHANG
2014 IEICE transactions on information and systems  
High-level semantic information, namely co-occurrence of several strokes is incorporated by learning a sparse dictionary, which can further restrain noise brought by single stroke detectors.  ...  In this paper, we propose a representation method based on local spatial strokes for scene character recognition.  ...  Framework The proposed method consists of four parts: (1) labeling key points for character training images and choosing discriminative strokes for every character; (2) collecting stroke training samples  ... 
doi:10.1587/transinf.e97.d.1937 fatcat:xqg6ihrkifb3fhfts46tifbf44

Picking Deep Filter Responses for Fine-Grained Image Recognition

Xiaopeng Zhang, Hongkai Xiong, Wengang Zhou, Weiyao Lin, Qi Tian
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
This paper proposes an automatic finegrained recognition approach which is free of any object / part annotation at both training and testing stages.  ...  The first picking step is to find distinctive filters which respond to specific patterns significantly and consistently, and learn a set of part detectors via iteratively alternating between new positive  ...  Learning Part Detectors In this section, we target at learning a collection of discriminative detectors that automatically discover discriminative object / parts.  ... 
doi:10.1109/cvpr.2016.128 dblp:conf/cvpr/ZhangXZLT16 fatcat:uaxknyseknfljdm2dnhlzjw6bq

Seeing 3D Chairs: Exemplar Part-Based 2D-3D Alignment Using a Large Dataset of CAD Models

Mathieu Aubry, Daniel Maturana, Alexei A. Efros, Bryan C. Russell, Josef Sivic
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
element detectors on a common dataset of negative images, and (iii) matching visual elements to the test image allowing for small mutual deformations but preserving the viewpoint and style constraints  ...  This is achieved by (i) representing each 3D model using a set of view-dependent mid-level visual elements learned from synthesized views in a discriminative fashion, (ii) carefully calibrating the individual  ...  We are grateful to the anonymous reviewers for their constructive comments.  ... 
doi:10.1109/cvpr.2014.487 dblp:conf/cvpr/AubryMERS14 fatcat:y4x6gxrcebglxcoqjmbcx3rrgq

Fine-Grained Crowdsourcing for Fine-Grained Recognition

Jia Deng, Jonathan Krause, Li Fei-Fei
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
This necessitates the use of stronger prior for feature selection. In this work, we include humans in the loop to help computers select discriminative features.  ...  Fine-grained recognition concerns categorization at sub-ordinate levels, where the distinction between object classes is highly local.  ...  Acknowledgments We thank Alexandre Alahi, Michelle Greene, Olga Russakovsky, Bangpeng Yao, and anonymous reviewers for their comments.  ... 
doi:10.1109/cvpr.2013.81 dblp:conf/cvpr/DengK013 fatcat:4n4brjjy7fb3pbufe7apode4ea

Human Attribute Recognition by Rich Appearance Dictionary

Jungseock Joo, Shuo Wang, Song-Chun Zhu
2013 2013 IEEE International Conference on Computer Vision  
We present a part-based approach to the problem of human attribute recognition from a single image of a human body.  ...  To this end, we propose to learn a rich appearance part dictionary of human with significantly less supervision by decomposing image lattice into overlapping windows at multi-scales and iteratively refining  ...  In this paper, we learn the dictionary of discriminative parts for the task of attribute recognition directly from training images.  ... 
doi:10.1109/iccv.2013.95 dblp:conf/iccv/JooWZ13 fatcat:uxnf33mdx5eqbdiozdnjv3pd6u

The Multi-level Learning and Classification of Multi-class Parts-Based Representations of U.S. Marine Postures [chapter]

Deborah Goshorn, Juan Wachs, Mathias Kölsch
2009 Lecture Notes in Computer Science  
This paper primarily investigates the possibility of using multi-level learning of sparse parts-based representations of US Marine postures in an outside and often crowded environment for training exercises  ...  The first approach uses a two-level learning method which consists of simple clustering of interest patches extracted from a set of training images for each posture, in addition to learning the nonparametric  ...  In the former, parts-based representations are learned for the sole purpose of object detection of that object type. There is no learning of parts that are discriminant between other object types.  ... 
doi:10.1007/978-3-642-10268-4_59 fatcat:5o4ntduu3zfldowte6ri7ncv6u

Learning coarse-to-fine sparselets for efficient object detection and scene classification

Gong Cheng, Junwei Han, Lei Guo, Tianming Liu
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
More recently the "sparselets" work [1] [2] [3] were introduced to serve as a universal set of shared basis learned from a large number of part detectors, resulting in notable speedup.  ...  In order to adequately explore the discriminative information hidden in the part detectors and to achieve sparsity, we propose to optimize a new discriminative objective function by imposing L0-norm sparsity  ...  [15] proposed a discriminative variant of mean-shift algorithm for finding mid-level visual elements, which learned 200 the most frequently-occurring elements per class, for a total of 13,400 part detectors  ... 
doi:10.1109/cvpr.2015.7298721 dblp:conf/cvpr/ChengH0L15 fatcat:ia2fprq4nbbsjlliqge26wzbgu

Scale-Invariant Object Categorization Using a Scale-Adaptive Mean-Shift Search [chapter]

Bastian Leibe, Bernt Schiele
2004 Lecture Notes in Computer Science  
That is, given a novel image we want to recognize and localize unseen-before objects based on their similarity to a learned object category.  ...  The goal of our work is object categorization in real-world scenes.  ...  Acknowledgments: This work is part of the CogVis project, funded by the Comission of the EU (IST-2000-29375) and the Swiss Federal Office for Education and Science (BBW 00.0617).  ... 
doi:10.1007/978-3-540-28649-3_18 fatcat:6tsr3l63cfawzirinuphtgumuu

When was that made? [article]

Sirion Vittayakorn, Alexander C. Berg, Tamara L. Berg
2016 arXiv   pre-print
In this paper, we explore deep learning methods for estimating when objects were made.  ...  We also provide several analyses of what our networks have learned, and demonstrate applications to identifying temporal inspiration in fashion collections.  ...  parts of actions [26] , cities [6] , or objects [21] .  ... 
arXiv:1608.03914v1 fatcat:rihyzdatjbffng6h7uybmlntia

Back to the Future: Learning Shape Models from 3D CAD Data

Michael Stark, Michael Goesele, Bernt Schiele
2010 Procedings of the British Machine Vision Conference 2010  
In this paper, we go back to the ideas from the early days of computer vision, by using 3D object models as the only source of information for building a multi-view object class detector.  ...  In particular, we use these models for learning 2D shape that can be robustly matched to 2D natural images.  ...  This work has been funded, in part, by the DFG Emmy Noether grant GO1752/3-1.  ... 
doi:10.5244/c.24.106 dblp:conf/bmvc/StarkGS10 fatcat:scsrtma62rhcnlcu3mpo6h4rzm

Semi-supervised Learning of Feature Hierarchies for Object Detection in a Video

Yang Yang, Guang Shu, Mubarak Shah
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
We propose a novel approach to boost the performance of generic object detectors on videos by learning videospecific features using a deep neural network.  ...  The insight behind our proposed approach is that an object appearing in different frames of a video clip should share similar features, which can be learned to build better detectors.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon.  ... 
doi:10.1109/cvpr.2013.216 dblp:conf/cvpr/YangSS13 fatcat:nuyo7xh7w5fxtpubfak4r5zrcm
« Previous Showing results 1 — 15 out of 21,824 results