Abstract

In this work, we propose a method to identify the ragas of an Indian Carnatic music signal. This has several interesting applications in digital music indexing, recommendation and retrieval. However, this problem is hard due to (i) the absence of a fixed frequency for a note (ii) relative scale of notes (iii) oscillations around a note, and (iv) improvisations. In this work, we attempt the raga classification problem in a non-linear SVM framework using a combination of two kernels that represent the similarities of a music signal using two different featurespitch-class profile and n-gram distribution of notes. This differs from the previous pitch-class profile based approaches where the temporal information of notes is ignored. We evaluated the proposed approach on our own raga dataset and CompMusic dataset and show an improvement of 10.19% by combining the information from two features relevant to Indian Carnatic music.

Abstract

Building bilateral semantic associations between images and texts is among the fundamental problems in computer vision. In this paper, we study two complementary cross-modal prediction tasks: (i) predicting text(s) given an image (“Im2Text”), and (ii) predicting image(s) given a piece of text (“Text2Im”). We make no assumption on the specific form of text; i.e., it could be either a set of labels, phrases, or even captions. We pose both these tasks in a retrieval framework. For Im2Text, given a query image, our goal is to retrieve a ranked list of semantically relevant texts from an independent textcorpus (i.e., texts with no corresponding images). Similarly, for Text2Im, given a query text, we aim to retrieve a ranked list of semantically relevant images from a collection of unannotated images (i.e., images without any associated textual meta-data). We propose a novel Structural SVM based unified formulation for these two tasks. For both visual and textual data, two types of representations are investigated. These are based on: (1) unimodal probability distributions over topics learned using latent Dirichlet allocation, and (2) explicitly learned multi-modal correlations using canonical correlation analysis. Extensive experiments on three popular datasets (two medium and one web-scale) demonstrate that our framework gives promising results compared to existing models under various settings, thus confirming its efficacy for both the tasks.

Abstract

The problem of ranking a set of visual samples according to their relevance to a query plays an important role in computer vision. The traditional approach for ranking is to train a binary classifier such as a support vector machine (svm). Binary classifiers suffer from two main deficiencies: (i) they do not optimize a ranking-based loss function, for example, the average precision (ap) loss; and (ii) they cannot incorporate high-order information such as the a priori correlation between the relevance of two visual samples (for example, two persons in the same image tend to perform the same action). We propose two novel learning formulations that allow us to incorporate high-order information for ranking. The first framework, called high-order binary svm (hob-svm), allows for a structured input. The parameters of hob-svm are learned by minimizing a convex upper bound on a surrogate 0-1 loss function. In order to obtain the ranking of the samples that form the structured input, hobsvm sorts the samples according to their max-marginals. The second framework, called high-order average precision svm (hoap-svm), also allows for a structured input and uses the same ranking criterion. However, in contrast to hob-svm, the parameters of hoap-svm are learned by minimizing a difference-of-convex upper bound on the ap loss. Using a standard, publicly available dataset for the challenging problem of action classification, we show that both hob-svm and hoap-svm outperform the baselines that ignore high-order information.

Abstract

Real world applicability of many computer vision solutions is constrained by the mismatch between the training and test domains. This mismatch might arise because of factors such as change in pose, lighting conditions, quality of imaging devices, intra-class variations inherent in object categories etc. In this work, we present a dictionary learning based approach to tackle the problem of domain mismatch. In our approach, we jointly learn dictionaries for the source and the target domains. The dictionaries are partially shared, i.e. some elements are common across both the dictionaries. These shared elements can represent the information which is common across both the domains. The dictionaries also have some elements to represent the domain specific information. Using these dictionaries, we separate the domain specific information and the information which is common across the domains. We use the latter for training cross-domain classifiers i.e., we build classifiers that work well on a new target domain while using labeled examples only in the source domain. We conduct cross-domain object recognition experiments on popular benchmark datasets and show improvement in results over the existing state of art domain adaptation approaches.

Abstract

In this paper we propose a framework for recognition and retrieval tasks in the context of scene text images. In contrast to many of the recent works, we focus on the case where an image-specific list of words, known as the small lexicon setting, is unavailable. We present a conditional random field model defined on potential character locations and the interactions between them. Observing that the interaction potentials computed in the large lexicon setting are less effective than in the case of a small lexicon, we propose an iterative method, which alternates between finding the most likely solution and refining the interaction potentials. We evaluate our method on public datasets and show that it improves over baseline and state-of-the-art approaches. For example, we obtain nearly 15% improvement in recognition accuracy and precision for our retrieval task over baseline methods on the IIIT-5K word dataset, with a large lexicon containing 0.5 million words.

Abstract

Computer vision applications today run on a wide range of mobile devices. Even though these devices are becoming more ubiquitous and general purpose, we continue to see a whole spectrum of processing and storage capabilities within this class. Moreover, even as the processing and storage capacity of devices are increasing, the complexity of vision solutions and the variety of use cases create greater demands on these resources. This requires appropriate adaptation of the mobile vision applications with minimal changes in the algorithm or implementation. In this work, we focus on optimizing the memory usage for storage intensive vision applications. In this paper, we propose a framework to configure memory requirements of vision applications. We start from a gold standard desktop application, and reduce the the size for a given the memory constraint. We formulate the storage optimization problem as mixed integer programming (mip) based optimization to select the most relevant subset of data to be retained. For large data sets, we use a greedy approximate solution which is empirically comparable to the optimal mip solution. We demonstrate the method in two different use cases: (a) Instance retrieval task where an image of a query object is looked up for instant recognition/annotation, and (b) Augmented reality where computational requirement is minimized by rendering and storing precomputed views. In both the cases, we show that our method allows a reduction in storage by almost 5× with no significant performance loss.

Abstract

In this paper, we present a solution to generate semantically richer descriptions and instructions for driver assistance and safety. Our solution builds upon a set of computer vision and machine learning modules. We start with low-level image processing and finally generate high-level descriptions. We do this by combining the results of the image pattern recognition module with the prior knowledge on traffic rules and larger context present in the video sequence. For recognition of road markings, we use a SVM based classifier and HOG based classifier. We test our method on real data captured in urban settings, and report impressive performance. Qualitative and quantitative performance of various modules are presented.

Abstract

The ability to detect floor regions from an image enables a variety of applications such as indoor scene understanding, mobility assessment, robot navigation, path planning and surveillance. In this work, we propose a framework for estimating floor regions in cluttered indoor environments. The problem of floor detection and segmentation is challenging in situations where floor and non-floor regions have similar appearances. It is even harder to segment floor regions when clutter, specular reflections, shadows and textured floors are present within the scene. Our framework utilizes a generic classifier trained from appearance cues as well as floor density estimates, both trained from a variety of indoor images. The results of the classifier is then adapted to a specific test image where we integrate appearance, position and geometric cues in an iterative framework. A Markov Random Field framework is used to integrate the cues to segment floor regions. In contrast to previous settings that relied on optical flow, depth sensors or multiple images in a calibrated setup, our method can work on a single image. It is also more flexible as we avoid assumptions like Manhattan world scene or restricting clutter only to wall-floor boundaries. Experimental results on the public MIT Scene dataset as well as a more challenging dataset that we acquired, demonstrate the robustness and efficiency of our framework on the above mentioned complex situations.

Abstract

We consider the problem of automatic identification of faces in videos such as movies, given a dictionary of known faces from a public or an alternate database. This has applications in video indexing, content based search, surveillance, and real time recognition on wearable computers. We propose a two stage approach for this problem. First, we recognize the faces in a video using a sparse representation framework using l1-minimization and select a few key-frames based on a robust confidence measure.We then use transductive learning to propagate the labels from the key-frames to the remaining frames by incorporating constraints simultaneously in temporal and feature spaces. This is in contrast to some of the previous approaches where every test frame/track is identified independently, ignoring the correlation between the faces in video tracks. Having a few key frames belonging to few subjects for label propagation rather than a large dictionary of actors reduces the amount of confusion. We evaluate the performance of our algorithm on Movie Trailer face dataset and five movie clips, and achieve a significant improvement in labeling accuracy compared to previous approaches

Abstract

No Results Found