Filters








182,237 Hits in 11.6 sec

Recent Advances in Zero-shot Recognition [article]

Yanwei Fu, Tao Xiang, Yu-Gang Jiang, Xiangyang Xue, Leonid Sigal, and Shaogang Gong
2017 arXiv   pre-print
One approach to scaling up the recognition is to develop models capable of recognizing unseen categories without any training instances, or zero-shot recognition/ learning.  ...  However, to scale the recognition to a large number of classes with few or now training samples for each class remains an unsolved problem.  ...  Yanwei Fu is supported by The Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning.  ... 
arXiv:1710.04837v1 fatcat:u3mp6dgj2rgqrarjm4dcywegmy

Integrating Local Material Recognition with Large-Scale Perceptual Attribute Discovery [article]

Gabriel Schwartz, Ko Nishino
2017 arXiv   pre-print
Does the same hold true for material attribute and category recognition?  ...  object and scene context.  ...  The Titan X used for part of this research was donated by the NVIDIA Corporation.  ... 
arXiv:1604.01345v4 fatcat:q7igfap7jfdtjf7rnexb3aehme

A Large-Scale Attribute Dataset for Zero-Shot Learning

Bo Zhao, Yanwei Fu, Rui Liang, Jiahong Wu, Yonggang Wang, Yizhou Wang
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
To overcome these problems, we propose a Large-scale Attribute Dataset (LAD) with 78,017 images of 230 classes. 359 attributes of visual, semantic and subjective properties are defined and annotated in  ...  Based on the proposed dataset, Zeroshot Learning Competition of AI Challenger (> 110 teams attended) has been organized for promoting ZSL research.  ...  Object Recognition We use the state-of-the-art object recognition models, namely, Inception-V3 [35] and ResNet [12] to recognize objects.  ... 
doi:10.1109/cvprw.2019.00053 dblp:conf/cvpr/ZhaoFLWWW19 fatcat:rqiwul46w5g5dakjb24npyvdka

MATERIAL CLASSIFICATION SYSTEM: LITERATURE SURVEY

Shama Holla, Shivani Bonageri, Shravya Shetty, K Panimozhi
2020 International Journal of Engineering Applied Sciences and Technology  
From the results obtained from several studies on object detection and image classification using Convolutional Neural Networks (CNNs), it is possible to study the material classification of everyday objects  ...  This paper explores the various visual features and learning techniques for the same.  ...  In the domainselected supervision, evaluation of the concepts that are learned on benchmarks for object detection and scene recognition are done.  ... 
doi:10.33564/ijeast.2020.v05i02.070 fatcat:ijcwfdhbnnczbpqyp757vqussa

Sparse Representations and Distance Learning for Attribute Based Category Recognition [chapter]

Grigorios Tsagkatakis, Andreas Savakis
2012 Lecture Notes in Computer Science  
of the object images and these attributes are subsequently used for the object recognition.  ...  A novel approach in object recognition is attribute based classification, where instead of training classifiers for the recognition of specific object class instances, classifiers are trained on attributes  ...  For each image, the bounding box of each object was first determined and the attributes corresponding to the object within the bounding box were identified.  ... 
doi:10.1007/978-3-642-35749-7_3 fatcat:apdhpawywzazhe3sycnpsl5rbu

Learning Predictive Features in Affordance based Robotic Perception Systems

Gerald Fritz, Lucas Paletta, Ralph Breithaupt, Erich Rome, Georg Dorffner
2006 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems  
In extension to existing functional views on visual feature representations [9], we identify the importance of learning in perceptual cueing for the anticipation of opportunities for interaction of robotic  ...  In addition, we emphasize a new framework for cueing and recognition of affordance-like visual entities that could play an important role in future robot control architectures.  ...  Acknowledgments This work is funded by the European Commission's project MACS (FP6-004381) and by the FWF Austrian joint research project Cognitive Vision under sub-projects S9103-N04 and S9104-N04.  ... 
doi:10.1109/iros.2006.281720 dblp:conf/iros/FritzPBRD06 fatcat:nbbwgi2dlzhxxoba7fkkg4hasu

Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks [article]

Tanmay Gupta, Kevin Shih, Saurabh Singh, Derek Hoiem
2017 arXiv   pre-print
Visual recognition also improves, especially for categories that have relatively few recognition training labels but appear often in the VQA setting.  ...  We show this leads to greater inductive transfer from recognition to VQA than standard multitask learning.  ...  Acknowledgements This work is supported in part by NSF Awards 14-46765 and 10-53768 and ONR MURI N000014-16-1-2007.  ... 
arXiv:1704.00260v2 fatcat:njqnfq7imvfpxhmsl5qq2lctsi

Describing objects by their attributes

Ali Farhadi, Ian Endres, Derek Hoiem, David Forsyth
2009 2009 IEEE Conference on Computer Vision and Pattern Recognition  
", not just "unknown"); and to learn how to recognize new objects with few or no visual examples.  ...  In this paper, we also introduce a novel feature selection method for learning attributes that generalize well across categories.  ...  Learning to Identify New Objects: The first test is to examine standard object recognition in new categories. We use predicted attributes as features and one-vs-all linear SVM as classifier.  ... 
doi:10.1109/cvpr.2009.5206772 dblp:conf/cvpr/FarhadiEHF09 fatcat:zri24py3djfi7htcjrrmhf4qne

A Large-scale Attribute Dataset for Zero-shot Learning [article]

Bo Zhao, Yanwei Fu, Rui Liang, Jiahong Wu, Yonggang Wang, Yizhou Wang
2018 arXiv   pre-print
The image number of LAD is larger than the sum of the four most popular attribute datasets. 359 attributes of visual, semantic and subjective properties are defined and annotated in instance-level.  ...  We analyze our dataset by conducting both supervised learning and zero-shot learning tasks. Seven state-of-the-art ZSL algorithms are tested on this new dataset.  ...  For example, the "person" objects occur in many AwA classes with a high frequency. Such correlation may be implicitly learned and utilized as the cues of identifying zero-shot classes.  ... 
arXiv:1804.04314v2 fatcat:7lf5sdvzc5dlrbbusquwou7z54

Describing objects by their attributes

A. Farhadi, I. Endres, D. Hoiem, D. Forsyth
2009 2009 IEEE Conference on Computer Vision and Pattern Recognition  
", not just "unknown"); and to learn how to recognize new objects with few or no visual examples.  ...  In this paper, we also introduce a novel feature selection method for learning attributes that generalize well across categories.  ...  Learning to Identify New Objects: The first test is to examine standard object recognition in new categories. We use predicted attributes as features and one-vs-all linear SVM as classifier.  ... 
doi:10.1109/cvprw.2009.5206772 fatcat:m65i4mddznb35ex7jr4fzoxmc4

Interpretable and Accurate Fine-grained Recognition via Region Grouping [article]

Zixuan Huang, Yin Li
2020 arXiv   pre-print
We present an interpretable deep model for fine-grained visual recognition. At the core of our method lies the integration of region-based part discovery and attribution within a deep neural network.  ...  To facilitate the learning of object parts without direct supervision, we explore a simple prior of the occurrence of object parts.  ...  How can we design an interpretable deep model that learns to discover object parts and estimates their importance for visual recognition?  ... 
arXiv:2005.10411v1 fatcat:zf4kmmuulvexfkcntv3xnhttvm

Towards recognizing "cool"

William Curran, Travis Moore, Todd Kulesza, Weng-Keen Wong, Sinisa Todorovic, Simone Stumpf, Rachel White, Margaret Burnett
2012 Proceedings of the 2012 ACM international conference on Intelligent User Interfaces - IUI '12  
questions for how to develop interactive attribute recognition algorithms.  ...  However, the more idiosyncratic and abstract the notion of an object attribute (e.g., "cool" car), the more challenging the task of attribute recognition.  ...  ACKNOWLEDGMENTS Removed for anonymous review.  ... 
doi:10.1145/2166966.2167019 dblp:conf/iui/CurranMKWTSWB12 fatcat:s6deflglu5f6fdqpq5r6mzrppe

Attribute based object identification

Yuyin Sun, Liefeng Bo, Dieter Fox
2013 2013 IEEE International Conference on Robotics and Automation  
In this paper, we introduce an approach for identifying objects based on natural language containing appearance and name attributes.  ...  a combination of appearance attributes and object names might be used in referral language to identify specific objects in a scene.  ...  Acknowledgments This work was funded in part by the Intel Science and Technology Center for Pervasive Computing and by ARO grant W911NF-12-1-0197  ... 
doi:10.1109/icra.2013.6630858 dblp:conf/icra/SunBF13 fatcat:x7yiewuyonhern6yfllidwf33y

Adding Unlabeled Samples to Categories by Learned Attributes

Jonghyun Choi, Mohammad Rastegari, Ali Farhadi, Larry S. Davis
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
We propose a method to expand the visual coverage of training sets that consist of a small number of labeled examples using learned attributes.  ...  In addition, we propose a method to stably capture example-specific attributes for a small sized training set.  ...  hyper-parameters for balancing the max margin objective terms for both the visual feature and attribute based classifiers. γ is a hyper-parameter for specifying the number of selected images.  ... 
doi:10.1109/cvpr.2013.118 dblp:conf/cvpr/ChoiRFD13 fatcat:pypxjiednrbp3kh5gjp6z6cpai

Attributes as Operators: Factorizing Unseen Attribute-Object Compositions [chapter]

Tushar Nagarajan, Kristen Grauman
2018 Lecture Notes in Computer Science  
We present a new approach to modeling visual attributes.  ...  Our approach learns a semantic embedding that explicitly factors out attributes from their accompanying objects, and also benefits from novel regularizers expressing attribute operators' effects (e.g.,  ...  Acknowledgments: This research is supported in part by ONR PECASE N00014-15-1-2291 and an Amazon AWS Machine Learning Research Award. We gratefully acknowledge Facebook for a GPU donation.  ... 
doi:10.1007/978-3-030-01246-5_11 fatcat:idqvvkx2tnggpocucn56f6qtky
« Previous Showing results 1 — 15 out of 182,237 results