|
|
|
| e-Pub |
Previous | 
Home
Section: New Results
Category-level object and scene recognition
Learning Graphs to Match
Participants : Minsu Cho, Karteek Alahari, Jean Ponce.
Many tasks in computer vision are formulated as graph matching problems. Despite the NP-hard nature of the problem, fast and accurate approximations have led to significant progress in a wide range of applications. Learning graph models from observed data, however, still remains a challenging issue. This work presents an effective scheme to parameterize a graph model, and learn its structural attributes for visual object matching. For this, we propose a graph representation with histogram-based attributes, and optimize them to increase the matching accuracy. Experimental evaluations on synthetic and real image datasets demonstrate the effectiveness of our approach, and show significant improvement in matching accuracy over graphs with pre-defined structures. The work is illustrated in Figure 3 . This work has been published ICCV 2013 [3] .
|
Finding Matches in a Haystack: A Max-Pooling Strategy for Graph Matching in the Presence of Outliers
Participants : Minsu Cho, Olivier Duchenne [Intel] , Jian Sun, Jean Ponce.
A major challenge in real-world matching problems is to tolerate the numerous outliers arising in typical visual tasks. Variations in object appearance, shape, and structure within the same object class make it hard to distinguish inliers from outliers due to clutters. In this project, we propose a novel approach to graph matching, which is not only resilient to deformations but also remarkably tolerant to outliers. By adopting a max-pooling strategy within the graph matching framework, the proposed algorithm evaluates each candidate match using its most promising neighbors, and gradually propagates the corresponding scores to update the neighbors. As final output, it assigns a reliable score to each match together with its supporting neighbors, thus providing contextual information for further verification. We demonstrate the robustness and utility of our method with synthetic and real image experiments. This work has been submitted to CVPR 2014.
Decomposing Bag of Words Histograms
Participants : Ankit Gandhi [IIIT India] , Karteek Alahari, C.v. Jawahar [IIIT India] .
We aim to decompose a global histogram representation of an image into histograms of its associated objects and regions. This task is formulated as an optimization problem, given a set of linear classifiers, which can effectively discriminate the object categories present in the image. Our decomposition bypasses harder problems associated with accurately localizing and segmenting objects. We evaluate our method on a wide variety of composite histograms, and also compare it with MRF-based solutions. In addition to merely measuring the accuracy of decomposition, we also show the utility of the estimated object and background histograms for the task of image classification on the PASCAL VOC 2007 dataset. This work has been published at ICCV 2013 [5] .
Image Retrieval using Textual Cues
Participants : Anand Mishra [IIIT India] , Karteek Alahari, C.v. Jawahar [IIIT India] .
We present an approach for the text-to-image retrieval problem based on textual content present in images. Given the recent developments in understanding text in images, an appealing approach to address this problem is to localize and recognize the text, and then query the database, as in a text retrieval problem. We show that such an approach, despite being based on state-of-the-art methods, is insufficient, and propose a method, where we do not rely on an exact localization and recognition pipeline. We take a query-driven search approach, where we find approximate locations of characters in the text query, and then impose spatial constraints to generate a ranked list of images in the database. The retrieval performance is evaluated on public scene text datasets as well as three large datasets, namely IIIT scene text retrieval, Sports-10K and TV series-1M, we introduce. This work has been published at ICCV 2013 [7] .
Learning Discriminative Part Detectors for Image Classification and Cosegmentation
Participants : Jian Sun, Jean Ponce.
In this work, we address the problem of learning discriminative part detectors from image sets with category labels. We propose a novel latent SVM model regularized by group sparsity to learn these part detectors. Starting from a large set of initial parts, the group sparsity regularizer forces the model to jointly select and optimize a set of discriminative part detectors in a max-margin framework. We propose a stochastic version of a proximal algorithm to solve the corresponding optimization problem. We apply the proposed method to image classification and cosegmentation, and quantitative experiments with standard bench- marks show that it matches or improves upon the state of the art. This work has been published at CVPR 2013 [8] .
Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks
Participants : Maxime Oquab, Leon Bottou [MSR New York] , Ivan Laptev, Josef Sivic.
Convolutional neural networks (CNN) have recently shown outstanding image classification performance in the large-scale visual recognition challenge (ILSVRC2012). The success of CNNs is attributed to their ability to learn rich mid-level image representations as opposed to hand-designed low-level features used in other image classification methods. Learning CNNs, however, amounts to estimating millions of parameters and requires a very large number of annotated image samples. This property currently prevents application of CNNs to problems with limited training data. In this work we show how image representations learned with CNNs on large-scale annotated datasets can be efficiently transferred to other visual recognition tasks with limited amount of training data. We design a method to reuse layers trained on the ImageNet dataset to compute mid-level image representation for images in the PASCAL VOC dataset. We show that despite differences in image statistics and tasks in the two datasets, the transferred representation leads to significantly improved results for object and action classification, outperforming the current state of the art on Pascal VOC 2007 and 2012 datasets. We also show promising results for object and action localization. The pre-print of this work is available online [11] . Results are illustrated in Figure 4 .
|
Seeing 3D chairs: exemplar part-based 2D-3D alignment using a large dataset of CAD models
Participants : Mathieu Aubry, Bryan Russell [Intel labs] , Alyosha Efros [UC Berkeley] , Josef Sivic.
We present an approach for the text-to-image retrieval problem based on textual content present in images. Given the recent developments in understanding text in images, an appealing approach to address this problem is to localize and recognize the text, and then query the database, as in a text retrieval problem. We show that such an approach, despite being based on state-of-the-art methods, is insufficient, and propose a method, where we do not rely on an exact localization and recognition pipeline. We take a query-driven search approach, where we find approximate locations of characters in the text query, and then impose spatial constraints to generate a ranked list of images in the database. The retrieval performance is evaluated on public scene text datasets as well as three large datasets, namely IIIT scene text retrieval, Sports-10K and TV series-1M, we introduce. This work has been submitted to CVPR 2014.