We address the problem of estimating location information of an image using principles from automated representation learning. We pursue a hierarchical sparse coding approach that learns features useful in discriminating images across locations, by initializing it with a geometric prior corresponding to transformations between image appearance space and their corresponding location grouping space using the notion of parallel transport on manifolds. We then extend this approach to account for the availability of heterogeneous data modalities such as geo-tags and videos pertaining to different locations, and also study a relatively under-addressed problem of transferring knowledge available from certain locations to infer the grouping of data from novel locations. We evaluate our approach on several standard datasets such as im2gps, San Francisco and MediaEval2010, and obtain state-of-the-art results.

With unconstrained data acquisition scenarios widely prevalent, the ability to handle changes in data distribution across training and testing data sets becomes important. One way to approach this problem is through domain adaptation, and in this paper we primarily focus on the unsupervised scenario where the labeled source domain training data is accompanied by unlabeled target domain test data. We present a two-stage data-driven approach by generating intermediate data representations that could provide relevant information on the domain shift. Starting with a linear representation of domains in the form of generative subspaces of same dimensions for the source and target domains, we first utilize the underlying geometry of the space of these subspaces, the Grassmann manifold, to obtain a `shortest' geodesic path between the two domains. We then sample points along the geodesic to obtain intermediate cross-domain data representations, using which a discriminative classifier is learnt to estimate the labels of the target data. We subsequently incorporate non-linear representation of domains by considering a Reproducing Kernel Hilbert Space representation, and a low-dimensional manifold representation using Laplacian Eigenmaps, and also examine other domain adaptation settings such as (i) semi-supervised adaptation where the target domain is partially labeled, and (ii) multi-domain adaptation where there could be more than one domain in source and/or target data sets. Finally, we supplement our adaptation technique with (i) fine-grained reference domains that are created by blending samples from source and target data sets to provide some evidence on the actual domain shift, and (ii) a multi-class boosting analysis to obtain robustness to the choice of algorithm parameters. We evaluate our approach for object recognition problems and report competitive results on two widely used Office and Bing adaptation data sets.

Estimating geographic location from images is a challenging problem that is receiving recent attention. In contrast to many existing methods that primarily model discriminative information corresponding to different locations, we propose joint learning of information that images across locations share and vary upon. Starting with generative and discriminative subspaces pertaining to domains, which are obtained by a hierarchical grouping of images from adjacent locations, we present a top-down approach that first models cross-domain information transfer by utilizing the geometry of these subspaces, and then encodes the model results onto individual images to infer their location. We report competitive results for location recognition and clustering on two public datasets, im2GPS and San Francisco, and empirically validate the utility of various design choices involved in the approach.

While the notion of joint sparsity in understanding common and innovative components of a multi-receiver signal ensemble has been well studied, we investigate the utility of such joint sparse models in representing information contained in a single video signal. By decomposing the content of a video sequence into that observed by multiple spatially and/or temporally distributed receivers, we first recover a collection of common and innovative components pertaining to individual videos. We then present modeling strategies based on subspace-driven manifold metrics to characterize patterns among these components, across other videos in the system, to perform subsequent video analysis. We demonstrate the efficacy of our approach for activity classification and clustering by reporting competitive results on standard datasets such as, HMDB, UCF-50, Olympic Sports and KTH.

Understanding the effect of blur is an important problem in unconstrained visual analysis. We address this problem in the context of image-based recognition by a fusion of image-formation models and differential geometric tools. First, we discuss the space spanned by blurred versions of an image and then, under certain assumptions, provide a differential geometric analysis of that space. More specifically, we create a subspace resulting from convolution of an image with a complete set of orthonormal basis functions of a prespecified maximum size (that can represent an arbitrary blur kernel within that size), and show that the corresponding subspaces created from a clean image and its blurred versions are equal under the ideal case of zero noise and some assumptions on the properties of blur kernels. We then study the practical utility of this subspace representation for the problem of direct recognition of blurred faces by viewing the subspaces as points on the Grassmann manifold and present methods to perform recognition for cases where the blur is both homogenous and spatially varying. We empirically analyze the effect of noise, as well as the presence of other facial variations between the gallery and probe images, and provide comparisons with existing approaches on standard data sets.

Road scene analysis is a challenging problem that has applications in autonomous navigation of vehicles. An integral component of this system is the robust detection and tracking of lane markings. It is a hard problem primarily due to large appearance variations in lane markings caused by factors such as occlusion (traffic on the road), shadows (from objects like trees), and changing lighting conditions of the scene (transition from day to night). In this paper, we address these issues through a learning-based approach using visual inputs from a camera mounted in front of a vehicle. We propose the following: 1) a pixel-hierarchy feature descriptor to model the contextual information shared by lane markings with the surrounding road region; 2) a robust boosting algorithm to select relevant contextual features for detecting lane markings; and 3) particle filters to track the lane markings, without knowledge of vehicle speed, by assuming the lane markings to be static through the video sequence and then learning the possible road scene variations from the statistics of tracked model parameters. We investigate the effectiveness of our algorithm on challenging daylight and night-time road video sequences.

Given a unlabelled set of points X ϵ ℝNbelonging to k groups, we propose a method to identify cluster assignments that provides maximum separating margin among the clusters. We address this problem by exploiting sparsity in data points inherent to margin regions, which a max-margin classifier would produce under a supervised setting to separate points belonging to different groups. By analyzing the projections of X on the set of all possible lines L in ℝN, we first establish some basic results that are satisfied only by those line intervals lying outside a cluster, under assumptions of linear separability of clusters and absence of outliers. We then encode these results into a pair-wise similarity measure to determine cluster assignments, where we accommodate non-linearly separable clusters using the kernel trick. We validate our method on several UCI datasets and on some computer vision problems, and empirically show its robustness to outliers, and in cases where the exact number of clusters is not available. The proposed approach offers an improvement in clustering accuracy of about 6% on the average, and up to 15% when compared with several existing methods.

Adapting the classifier trained on a source domain to recognize instances from a new target domain is an important problem that is receiving recent attention. In this paper, we present one of the first studies on unsupervised domain adaptation in the context of object recognition, where we have labeled data only from the source domain (and therefore do not have correspondences between object categories across domains). Motivated by incremental learning, we create intermediate representations of data between the two domains by viewing the generative subspaces (of same dimension) created from these domains as points on the Grassmann manifold, and sampling points along the geodesic between them to obtain subspaces that provide a meaningful description of the underlying domain shift. We then obtain the projections of labeled source domain data onto these subspaces, from which a discriminative classifier is learnt to classify projected data from the target domain. We discuss extensions of our approach for semi-supervised adaptation, and for cases with multiple source and target domains, and report competitive results on standard datasets.

The challenging problem of planning manipulation tasks for dexterous robotic hands can be significantly simplified if the robot system has the ability to learn manipulation skills by observing a human demonstrator. Toward this goal, we present a novel computer vision based hand posture recognition system to serve as an intelligent interface for skill transfer in robotic manipulation. We use the inner distance shape context (IDSC) as a hand shape descriptor to capture variations in the hand state (open or closed) under large in-plane rotations and considerable out-of-plane rotations. The proposed technique is further examined in applications involving grasp recognition and gesture based communications. The experiments show that the proposed approach can be generalized to recognizing a selected taxonomy of grasp types. At present, skin color is used to segment the hand region from the scene, but this method has its own limitations. We show preliminary results suggesting that the IDSC can be used to segment parts of the articulated object, including segmenting the hand from the human body silhouette without using skin color information.