2015 IEEE International Conference on Computer Vision (ICCV)

7-13 Dec. 2015

Filter Results

Displaying Results 1 - 25 of 537
  • [Title page i]

    Publication Year: 2015, Page(s): i
    Request permission for commercial reuse | |PDF file iconPDF (100 KB)
    Freely Available from IEEE
  • [Title page iii]

    Publication Year: 2015, Page(s): iii
    Request permission for commercial reuse | |PDF file iconPDF (137 KB)
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2015, Page(s): iv
    Request permission for commercial reuse | |PDF file iconPDF (118 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2015, Page(s):v - xxxv
    Request permission for commercial reuse | |PDF file iconPDF (227 KB)
    Freely Available from IEEE
  • Message from the General Chair and Program Chairs

    Publication Year: 2015, Page(s):xxxvi - xxxvii
    Request permission for commercial reuse | |PDF file iconPDF (74 KB) | HTML iconHTML
    Freely Available from IEEE
  • Organizing Committee

    Publication Year: 2015, Page(s):xxxviii - xxxix
    Request permission for commercial reuse | |PDF file iconPDF (73 KB)
    Freely Available from IEEE
  • ICCV 2015 Area Chairs

    Publication Year: 2015, Page(s): xl
    Request permission for commercial reuse | |PDF file iconPDF (72 KB)
    Freely Available from IEEE
  • ICCV 2015 Reviewers

    Publication Year: 2015, Page(s): xli
    Request permission for commercial reuse | |PDF file iconPDF (72 KB)
    Freely Available from IEEE
  • Sponsors

    Publication Year: 2015, Page(s): xlii
    Request permission for commercial reuse | |PDF file iconPDF (262 KB)
    Freely Available from IEEE
  • Ask Your Neurons: A Neural-Based Approach to Answering Questions about Images

    Publication Year: 2015, Page(s):1 - 9
    Cited by:  Papers (34)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (478 KB) | HTML iconHTML

    We address a question answering task on real-world images that is set up as a Visual Turing Test. By combining latest advances in image representation and natural language processing, we propose Neural-Image-QA, an end-to-end formulation to this problem for which all parts are trained jointly. In contrast to previous efforts, we are facing a multi-modal problem where the language output (answer) i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing

    Publication Year: 2015, Page(s):10 - 18
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1184 KB) | HTML iconHTML

    We introduce Segment-Phrase Table (SPT), a large collection of bijective associations between textual phrases and their corresponding segmentations. Leveraging recent progress in object recognition and natural language semantics, we show how we can successfully build a high-quality segment-phrase table using minimal human supervision. More importantly, we demonstrate the unique value unleashed by ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books

    Publication Year: 2015, Page(s):19 - 27
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2400 KB) | HTML iconHTML

    Books are a rich source of both fine-grained information, how a character, an object or a scene looks like, as well as high-level semantics, what someone is thinking, feeling and how these states evolve through a story. This paper aims to align books to their movie releases in order to provide rich descriptive explanations for visual content that go semantically far beyond the captions available i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning Query and Image Similarities with Ranking Canonical Correlation Analysis

    Publication Year: 2015, Page(s):28 - 36
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2461 KB) | HTML iconHTML

    One of the fundamental problems in image search is to learn the ranking functions, i.e., similarity between the query and image. The research on this topic has evolved through two paradigms: feature-based vector model and image ranker learning. The former relies on the image surrounding texts, while the latter learns a ranker based on human labeled query-image pairs. Each of the paradigms has its ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning to See by Moving

    Publication Year: 2015, Page(s):37 - 45
    Cited by:  Papers (37)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (356 KB) | HTML iconHTML

    The current dominant paradigm for feature learning in computer vision relies on training neural networks for the task of object recognition using millions of hand labelled images. Is it also possible to learn features for a diverse set of visual tasks using any other form of supervision? In biology, living organisms developed the ability of visual perception for the purpose of moving and acting in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Object Detection Using Generalization and Efficiency Balanced Co-Occurrence Features

    Publication Year: 2015, Page(s):46 - 54
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (434 KB) | HTML iconHTML

    In this paper, we propose a high-accuracy object detector based on co-occurrence features. Firstly, we introduce three kinds of local co-occurrence features constructed by the traditional Haar, LBP, and HOG respectively. Then the boosted detectors are learned, where each weak classifier corresponds to a local image region with a co-occurrence feature. In addition, we propose a Generalization and E... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mining And-Or Graphs for Graph Matching and Object Discovery

    Publication Year: 2015, Page(s):55 - 63
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1615 KB) | HTML iconHTML

    This paper reformulates the theory of graph mining on the technical basis of graph matching, and extends its scope of applications to computer vision. Given a set of attributed relational graphs (ARGs), we propose to use a hierarchical And-Or Graph (AoG) to model the pattern of maximal-size common subgraphs embedded in the ARGs, and we develop a general method to mine the AoG model from the unlabe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pose Induction for Novel Object Categories

    Publication Year: 2015, Page(s):64 - 72
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (857 KB) | HTML iconHTML

    We address the task of predicting pose for objects of unannotated object categories from a small seed set of annotated object classes. We present a generalized classifier that can reliably induce pose given a single instance of a novel category. In case of availability of a large collection of novel instances, our approach then jointly reasons over all instances to improve the initial estimates. W... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic Texture Recognition via Orthogonal Tensor Dictionary Learning

    Publication Year: 2015, Page(s):73 - 81
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (246 KB) | HTML iconHTML

    Dynamic textures (DTs) are video sequences with stationary properties, which exhibit repetitive patterns over space and time. This paper aims at investigating the sparse coding based approach to characterizing local DT patterns for recognition. Owing to the high dimensionality of DT sequences, existing dictionary learning algorithms are not suitable for our purpose due to their high computational ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Convolutional Channel Features

    Publication Year: 2015, Page(s):82 - 90
    Cited by:  Papers (43)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (591 KB) | HTML iconHTML

    Deep learning methods are powerful tools but often suffer from expensive computation and limited flexibility. An alternative is to combine light-weight models with deep representations. As successful cases exist in several visual problems, a unified framework is absent. In this paper, we revisit two widely used approaches in computer vision, namely filtered channel features and Convolutional Neura... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Local Convolutional Features with Unsupervised Training for Image Retrieval

    Publication Year: 2015, Page(s):91 - 99
    Cited by:  Papers (22)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1223 KB) | HTML iconHTML

    Patch-level descriptors underlie several important computer vision tasks, such as stereo-matching or content-based image retrieval. We introduce a deep convolutional architecture that yields patch-level descriptors, as an alternative to the popular SIFT descriptor for image retrieval. The proposed family of descriptors, called Patch-CKN, adapt the recently introduced Convolutional Kernel Network (... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • RIDE: Reversal Invariant Descriptor Enhancement

    Publication Year: 2015, Page(s):100 - 108
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (669 KB) | HTML iconHTML

    In many fine-grained object recognition datasets, image orientation (left/right) might vary from sample to sample. Since handcrafted descriptors such as SIFT are not reversal invariant, the stability of image representation based on them is consequently limited. A popular solution is to augment the datasets by adding a left-right reversed copy for each original image. This strategy improves recogn... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Discrete Tabu Search for Graph Matching

    Publication Year: 2015, Page(s):109 - 117
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (684 KB) | HTML iconHTML

    Graph matching is a fundamental problem in computer vision. In this paper, we propose a novel graph matching algorithm based on tabu search [13]. The proposed method solves graph matching problem by casting it into an equivalent weighted maximum clique problem of the corresponding association graph, which we further penalize through introducing negative weights. Subsequent tabu search optimization... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Discriminative Learning of Deep Convolutional Feature Point Descriptors

    Publication Year: 2015, Page(s):118 - 126
    Cited by:  Papers (39)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (806 KB) | HTML iconHTML

    Deep learning has revolutionalized image-level tasks such as classification, but patch-level tasks, such as correspondence, still rely on hand-crafted features, e.g. SIFT. In this paper we use Convolutional Neural Networks (CNNs) to learn discriminant patch representations and in particular train a Siamese network with pairs of (non-)corresponding patches. We deal with the large number of potentia... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Amodal Completion and Size Constancy in Natural Scenes

    Publication Year: 2015, Page(s):127 - 135
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (993 KB) | HTML iconHTML

    We consider the problem of enriching current object detection systems with veridical object sizes and relative depth estimates from a single image. There are several technical challenges to this, such as occlusions, lack of calibration data and the scale ambiguity between object size and distance. These have not been addressed in full generality in previous work. Here we propose to tackle these is... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning Where to Position Parts in 3D

    Publication Year: 2015, Page(s):136 - 144
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (433 KB) | HTML iconHTML

    A common issue in deformable object detection is finding a good way to position the parts. This issue is even more outspoken when considering detection and pose estimation for 3D objects, where parts should be placed in a three-dimensional space. Some methods extract the 3D shape of the object from 3D CAD models. This limits their applicability to categories for which such models are available. Ot... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.