Filters








14,189 Hits in 4.5 sec

The functional role of cue-driven feature-based feedback in object recognition [article]

Sushrut Thorat, Marcel van Gerven, Marius Peelen
2019 arXiv   pre-print
We observe that the feedback provides performance boosts only if the category-specific features about the objects cannot be fully represented in the OPS.  ...  Visual object recognition is not a trivial task, especially when the objects are degraded or surrounded by clutter or presented briefly.  ...  This manuscript reflects only the authors' view, and the Agency is not responsible for any use that may be made of the information it contains.  ... 
arXiv:1903.10446v1 fatcat:uf5d52fgizfw5pnaj7dtc5rgfq

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 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.  ...  We propose a method to learn a diverse collection of discriminative parts from object bounding box annotations.  ...  Our method is an important step in building more general object recognition systems.  ... 
doi:10.1109/cvpr.2013.126 dblp:conf/cvpr/EndresSJH13 fatcat:icbxdvmmmbct7b5ej76ydhlkk4

Multithreading AdaBoost framework for object recognition

Jinhui Chen, Tetsuya Takiguchi, Yasuo Ariki
2015 2015 IEEE International Conference on Image Processing (ICIP)  
channels, which are respectively built to train weak classifiers for each object category.  ...  Our research focuses on the study of effective feature description and robust classifier technique, proposing a novel learning framework, which is capable of processing multiclass objects recognition simultaneously  ...  Experimental results The proposed method used 265 minutes to converge at the 12th boosting iteration stage. The cascade detector generated 5, 994 classifiers of all 20 categories.  ... 
doi:10.1109/icip.2015.7350997 dblp:conf/icip/ChenTA15 fatcat:hq4z5fjpmngvvorkgapwqjyqgq

An Empirical Study of Object Category Recognition: Sequential Testing with Generalized Samples

Liang Lin, Shaowu Peng, Jake Porway, Song-Chun Zhu, Yongtian Wang
2007 2007 IEEE 11th International Conference on Computer Vision  
In this paper we present an empirical study of object category recognition using generalized samples and a set of sequential tests.  ...  To increase the amount of training data we have, we use a compositional object model to learn a representation for each category from which we select 30 additional templates with varied appearance from  ...  The data used in this paper were provided by the Lotus Hill Annotation project [2] , which was partially supported by a subaward from the W.M. Keck Foundation.  ... 
doi:10.1109/iccv.2007.4408873 dblp:conf/iccv/LinPPZW07 fatcat:u6fjtggfy5ar3ggwzfvlnue6bq

Learning Canonical 3D Object Representation for Fine-Grained Recognition [article]

Sunghun Joung, Seungryong Kim, Minsu Kim, Ig-Jae Kim, Kwanghoon Sohn
2021 arXiv   pre-print
We propose a novel framework for fine-grained object recognition that learns to recover object variation in 3D space from a single image, trained on an image collection without using any ground-truth 3D  ...  Our representation also allows us to go beyond existing methods, by incorporating 3D shape variation as an additional cue for object recognition.  ...  It is also challenging to learn 3D shape from images with heavy occlusion, which limits its applicability to generic object recognition tasks in the wild.  ... 
arXiv:2108.04628v1 fatcat:djmdeq2xmffs3khywwkubvekd4

Integrating Spatio-Temporal Context With Multiview Representation for Object Recognition in Visual Surveillance

Xiaobai Liu, Liang Lin, Shuicheng Yan, Hai Jin, Wenbing Tao
2011 IEEE transactions on circuits and systems for video technology (Print)  
Taking the spatio-temporal contextual knowledge as the prior model and deformable template matching as the likelihood model, we formulate the problem of object category recognition as a maximum-a-posteriori  ...  It contains a set of deformable object templates, each of which comprises an ensemble of active features for an object category in a specific view/pose.  ...  The data used in this paper were provided by the Lotus Hill Annotation project [4] .  ... 
doi:10.1109/tcsvt.2010.2087570 fatcat:llzia5bbanag5fazrcqo6tnipm

Probabilistic boosting-tree: learning discriminative models for classification, recognition, and clustering

Zhuowen Tu
2005 Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1  
In this paper, we show the applications of PBT for classification, detection, object recognition. We have also applied the framework in segmentation.  ...  The proposed framework is very general and it has interesting connections to a number of existing methods such as the £ algorithm, decision tree algorithms, generative models, and cascade approaches.  ...  Discriminative Let an image sample Ü and its interpretation Ï bé Ü Ïµ Ï Ý « ¢µ where Ý is the label of the object, e.g., category id. ¢ is the underling template dictionary from which Ü is generated and  ... 
doi:10.1109/iccv.2005.194 dblp:conf/iccv/Tu05a fatcat:7qy4k7vuerexzbc5avoq4ohz7a

Object Detection in Real Images [article]

Dilip K. Prasad
2013 arXiv   pre-print
We propose a new object detection/recognition method, which improves over the existing methods in every stage of the object detection/recognition process.  ...  Object detection and recognition are important problems in computer vision.  ...  Feature types Most object detection and recognition methods can be classified into two categories based on the feature type they use in their methods.  ... 
arXiv:1302.5189v1 fatcat:qdjqvh44qra6lemyu7nzpsldfa

Object Templates for Visual Place Categorization [chapter]

Hao Yang, Jianxin Wu
2013 Lecture Notes in Computer Science  
To be specific, we propose a local objects classifier that can automatically and effectively select key local objects of a semantic category from randomly sampled patches by the structural similarity support  ...  The Visual Place Categorization (VPC) problem refers to the categorization of the semantic category of a place using only visual information collected from an autonomous robot.  ...  Hence, being able to label the semantic category of a place should boost the performance of object recognition and visual search.  ... 
doi:10.1007/978-3-642-37447-0_36 fatcat:6ebqw64nfvdungjcnaznmaxpgu

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
Elevation Models from Shadowing Cues Hoiem, Derek Comparative Object Similarity for Improved Recognition with Few or No Examples Attribute-Centeric Recognition for Cross-category Generalization Workshop  ...  Farhadi, Ali Attribute-Centeric Recognition for Cross-category Generalization Workshop: The Benefits and Challenges of Collecting Richer Object Annotations Favaro, Paolo Recovering Thin Structures  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

A stochastic graph grammar for compositional object representation and recognition

Liang Lin, Tianfu Wu, Jake Porway, Zijian Xu
2009 Pattern Recognition  
This paper illustrates a hierarchical generative model for representing and recognizing compositional object categories with large intra-category variance.  ...  embedded in an And-Or graph for each compositional object category.  ...  We present a general and scalable framework for many general object recognition.  ... 
doi:10.1016/j.patcog.2008.10.033 fatcat:34kfgs37j5hwdgref3scrmmvne

Detecting Objects Using Deformation Dictionaries

Bharath Hariharan, C. Lawrence Zitnick, Piotr Dollar
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
In addition, we discover that the set of deformation bases is actually transferable across object categories and that learning shared bases across similar categories can boost accuracy.  ...  In this paper, we show the counter-intuitive result that it is possible to achieve similar accuracy using a small dictionary of deformations.  ...  Winn and Jojic [25] propose a generative model for recognition that uses a deformation field to model intraclass variation.  ... 
doi:10.1109/cvpr.2014.256 dblp:conf/cvpr/HariharanZD14 fatcat:3qic5fjmibblveryiv7xahhf7u

Sharing Visual Features for Multiclass and Multiview Object Detection

Antonio Torralba, Kevin P. Murphy, William T. Freeman
2007 IEEE Transactions on Pattern Analysis and Machine Intelligence  
It seems unlikely that such an approach will scale up to allow recognition of hundreds or thousands of objects.  ...  Those generic features generalize better and reduce considerably the computational cost of an algorithm for multi-class object detection. 1 .  ...  Multi-class object detection As mentioned in the introduction, it is helpful to distinguish four categories of work: object recognition (which assumes the object has been segmented out from the background  ... 
doi:10.1109/tpami.2007.1055 pmid:17356204 fatcat:7dzdvu23sjbnro3egcmuwhmxxm

Survey on Various Gesture Recognition Techniques for Interfacing Machines Based on Ambient Intelligence

C Harshith, Karthik.R. Shastry, Manoj Ravindran, M.V.V.N.S Srikanth, Naveen Lakshmikhanth
2010 International Journal of Computer Science & Engineering Survey  
The traditional methods can be broadly classified into three categories: template based methods,appearance based methods and feature based methods.  ...  The main goal of gesture recognition is to create a system which can recognize specific human gestures and use them to convey information or for device control.  ...  ACKNOWLEDGEMENTS We would like to thank our parents for the blessings that they showered on us and the continuous support we received.  ... 
doi:10.5121/ijcses.2010.1203 fatcat:ae4tw6b5urgi7pnuccw35tavqe

Learning visual biases from human imagination [article]

Carl Vondrick, Hamed Pirsiavash, Aude Oliva, Antonio Torralba
2015 arXiv   pre-print
Our results suggest that transferring this human bias into machines may help object recognition systems generalize across datasets and perform better when very little training data is available.  ...  We introduce a novel method that, inspired by well-known tools in human psychophysics, estimates the biases that the human visual system might use for recognition, but in computer vision feature spaces  ...  To evaluate this, we use the visual biases c directly as a classifier for object recognition.  ... 
arXiv:1410.4627v2 fatcat:rw7rn42pvbgc7ng5thjisipifm
« Previous Showing results 1 — 15 out of 14,189 results