Search For:

Displaying 1-27 out of 27 total
Which Edges Matter?
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Aayush Bansal,Adarsh Kowdle,Devi Parikh,Andrew Gallagher,Larry Zitnick
Issue Date:December 2013
pp. 578-585
In this paper, we investigate the ability of humans to recognize objects using different types of edges. Edges arise in images because of several different physical phenomena, such as shadow boundaries, changes in material albedo or reflectance, changes to...
 
Spoken Attributes: Mixing Binary and Relative Attributes to Say the Right Thing
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Amir Sadovnik,Andrew Gallagher,Devi Parikh,Tsuhan Chen
Issue Date:December 2013
pp. 2160-2167
In recent years, there has been a great deal of progress in describing objects with attributes. Attributes have proven useful for object recognition, image search, face verification, image description, and zero-shot learning. Typically, attributes are eith...
 
Learning the Visual Interpretation of Sentences
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By C. Lawrence Zitnick,Devi Parikh,Lucy Vanderwende
Issue Date:December 2013
pp. 1681-1688
Sentences that describe visual scenes contain a wide variety of information pertaining to the presence of objects, their attributes and their spatial relations. In this paper we learn the visual features that correspond to semantic phrases derived from sen...
 
Attribute Dominance: What Pops Out?
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Naman Turakhia,Devi Parikh
Issue Date:December 2013
pp. 1225-1232
When we look at an image, some properties or attributes of the image stand out more than others. When describing an image, people are likely to describe these dominant attributes first. Attribute dominance is a result of a complex interplay between the var...
 
Implied Feedback: Learning Nuances of User Behavior in Image Search
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Devi Parikh,Kristen Grauman
Issue Date:December 2013
pp. 745-752
User feedback helps an image search system refine its relevance predictions, tailoring the search towards the user's preferences. Existing methods simply take feedback at face value: clicking on an image means the user wants things like it, commenting that...
 
Exploring Tiny Images: The Roles of Appearance and Contextual Information for Machine and Human Object Recognition
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Devi Parikh,C. Lawrence Zitnick,Tsuhan Chen
Issue Date:October 2012
pp. 1978-1991
Typically, object recognition is performed based solely on the appearance of the object. However, relevant information also exists in the scene surrounding the object. In this paper, we explore the roles that appearance and contextual information play in o...
 
Relative attributes
Found in: Computer Vision, IEEE International Conference on
By Devi Parikh,Kristen Grauman
Issue Date:November 2011
pp. 503-510
Human-nameable visual
 
Extracting adaptive contextual cues from unlabeled regions
Found in: Computer Vision, IEEE International Conference on
By Congcong Li,Devi Parikh, Tsuhan Chen
Issue Date:November 2011
pp. 511-518
Existing approaches to contextual reasoning for enhanced object detection typically utilize other labeled categories in the images to provide contextual information. As a consequence, they inadvertently commit to the granularity of information implicit in ...
 
Recognizing jumbled images: The role of local and global information in image classification
Found in: Computer Vision, IEEE International Conference on
By Devi Parikh
Issue Date:November 2011
pp. 519-526
The performance of current state-of-the-art computer vision algorithms at image classification falls significantly short as compared to human abilities. To reduce this gap, it is important for the community to know what problems to solve, and not just how ...
 
Interactively building a discriminative vocabulary of nameable attributes
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Devi Parikh,Kristen Grauman
Issue Date:June 2011
pp. 1681-1688
Human-nameable visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be inefficient (costing substantial effort or expertise) and/or insufficient (descripti...
 
The role of features, algorithms and data in visual recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Devi Parikh, C. Lawrence Zitnick
Issue Date:June 2010
pp. 2328-2335
There are many computer vision algorithms developed for visual (scene and object) recognition. Some systems focus on involved learning algorithms, some leverage millions of training images, and some systems focus on modeling relevant information (features)...
 
Beyond trees: MRF inference via outer-planar decomposition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Dhruv Batra, A. C. Gallagher, Devi Parikh, Tsuhan Chen
Issue Date:June 2010
pp. 2496-2503
Maximum a posteriori (MAP) inference in Markov Random Fields (MRFs) is an NP-hard problem, and thus research has focussed on either finding efficiently solvable subclasses (e.g. trees), or approximate algorithms (e.g. Loopy Belief Propagation (BP) and Tree...
 
iCoseg: Interactive co-segmentation with intelligent scribble guidance
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Dhruv Batra, Adarsh Kowdle, Devi Parikh, Jiebo Luo, Tsuhan Chen
Issue Date:June 2010
pp. 3169-3176
This paper presents an algorithm for Interactive Co-segmentation of a foreground object from a group of related images. While previous approaches focus on unsupervised co-segmentation, we use successful ideas from the interactive object-cutout literature. ...
 
From appearance to context-based recognition: Dense labeling in small images
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Devi Parikh, C. Lawrence Zitnick, Tsuhan Chen
Issue Date:June 2008
pp. 1-8
Traditionally, object recognition is performed based solely on the appearance of the object. However, relevant information also exists in the scene surrounding the object. As supported by our human studies, this contextual information is necessary for accu...
 
Localization and Segmentation of A 2D High Capacity Color Barcode
Found in: Applications of Computer Vision, IEEE Workshop on
By Devi Parikh, Gavin Jancke
Issue Date:January 2008
pp. 1-6
A 2D color barcode can hold much more information than a binary barcode. Barcodes are often intended for consumer use where using a cellphone, a consumer can take an image of a barcode on a product, and retrieve relevant information about the product. The ...
 
Hierarchical Semantics of Objects (hSOs)
Found in: Computer Vision, IEEE International Conference on
By Devi Parikh, Tsuhan Chen
Issue Date:October 2007
pp. 1-8
We introduce hSOs: Hierarchical Semantics of Objects. An hSO is learnt from a collection of images taken from a particular scene category. The hSO captures the interactions between the objects that tend to co-occur in the scene, and hence are potentially s...
 
Classification-Error Cost Minimization Strategy: DCMS
Found in: Statistical Signal Processing, IEEE/SP Workshop on
By Devi Parikh, Tsuhan Chen
Issue Date:August 2007
pp. 620-624
Several classification applications such as intrusion detection, biometric recognition, etc. have different costs associated with different classification errors. In such scenarios, the goal is to minimize the cost incurred, and not the classification erro...
 
Unsupervised Learning of Hierarchical Semantics of Objects (hSOs)
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Devi Parikh, Tsuhan Chen
Issue Date:June 2007
pp. 1-8
A successful representation of objects in the literature is as a collection of patches, or parts, with a certain appearance and position. The relative locations of the different parts of an object are constrained by the geometry of the object. Going beyond...
 
Feature-based Part Retrieval for Interactive 3D Reassembly
Found in: Applications of Computer Vision, IEEE Workshop on
By Devi Parikh, Rahul Sukthankar, Tsuhan Chen, Mei Chen
Issue Date:February 2007
pp. 14
We propose a novel framework for 3D reassembly, the task of assembling a solid object from its broken pieces. The primary challenge in this under-explored problem is to robustly establish compatibility between parts from one object. Feature-based technique...
 
Adopting Abstract Images for Semantic Scene Understanding
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By C. Lawrence Zitnick,Ramakrishna Vedantam,Devi Parikh
Issue Date:February 2015
pp. 1
Relating visual information to its linguistic semantic meaning remains an open and challenging area of research. The semantic meaning of images depends on the presence of objects, their attributes and their relations to other objects. But precisely charact...
 
What Makes a Photograph Memorable?
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Phillip Isola,Jianxiong Xiao,Devi Parikh,Antonio Torralba,Aude Oliva
Issue Date:July 2014
pp. 1-1
When glancing at a magazine, or browsing the Internet, we are continuously exposed to photographs. Despite this overflow of visual information, humans are extremely good at remembering thousands of pictures along with some of their visual details. But not ...
 
What Makes a Photograph Memorable?
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Phillip Isola,Jianxiong Xiao,Devi Parikh,Antonio Torralba,Aude Oliva
Issue Date:October 2013
pp. 1
When glancing at a magazine, or browsing the Internet, we are continuously exposed to photographs. Despite this overflow of visual information, humans are extremely good at remembering thousands of pictures along with some of their visual details. But not ...
 
Bringing Semantics into Focus Using Visual Abstraction
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By C. Lawrence Zitnick,Devi Parikh
Issue Date:June 2013
pp. 3009-3016
Relating visual information to its linguistic semantic meaning remains an open and challenging area of research. The semantic meaning of images depends on the presence of objects, their attributes and their relations to other objects. But precisely charact...
 
Simultaneous Active Learning of Classifiers & Attributes via Relative Feedback
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Arijit Biswas,Devi Parikh
Issue Date:June 2013
pp. 644-651
Active learning provides useful tools to reduce annotation costs without compromising classifier performance. However it traditionally views the supervisor simply as a labeling machine. Recently a new interactive learning paradigm was introduced that allow...
 
Multi-attribute Queries: To Merge or Not to Merge?
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Mohammad Rastegari,Ali Diba,Devi Parikh,Ali Farhadi
Issue Date:June 2013
pp. 3310-3317
Users often have very specific visual content in mind that they are searching for. The most natural way to communicate this content to an image search engine is to use key-words that specify various properties or attributes of the content. A naive way of d...
 
Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Roozbeh Mottaghi,Sanja Fidler,Jian Yao,Raquel Urtasun,Devi Parikh
Issue Date:June 2013
pp. 3143-3150
Recent trends in semantic image segmentation have pushed for holistic scene understanding models that jointly reason about various tasks such as object detection, scene recognition, shape analysis, contextual reasoning. In this work, we are interested in u...
 
Semi-supervised co-training and active learning based approach for multi-view intrusion detection
Found in: Proceedings of the 2009 ACM symposium on Applied Computing (SAC '09)
By Ching-Hao Mao, Devi Parikh, Hahn-Ming Lee, Si-Yu Huang, Tsuhan Chen
Issue Date:March 2009
pp. 1-5
Although there is immense data available from networks and hosts, a very small proportion of this data is labeled due to the cost of obtaining expert labels. This proves to be a significant bottle-neck for developing supervised intrusion detection systems ...
     
 1