Abstract

We propose a semi-supervised self-training method for fine-tuning human pose estimations in videos that provides accurate estimations even for complex sequences. We surpass state-of-the-art on most of the datasets used and also show a 2.33% gain over the baseline on our new dataset of unrestricted sports videos. The self-training model presented has two components: a static Pictorial Structure (PS) based model and a dynamic ensemble of exemplars. We present a pose quality criteria that is primarily used for batch selection and automatic parameter selection. The same criteria works as a low-level pose evaluator used in post-processing. We set a new challenge by introducing a full human body-parts annotated complex dataset, CVIT-SPORTS, which contains complex videos from the sports domain. The strength of our method is demonstrated by adapting to videos of complex activities such as cricket …

Abstract

Crowded urban environments are composed of different types of dynamic and static elements. Learning and classification of features is a major task in solving the localization problem in such environments. This work presents a gradual learning methodology to learn the useful features using multiple experiences. The usefulness of an observed element is evaluated by a scoring mechanism which uses two scores – reliability and distinctiveness. The visual features thus learned are used to partition the visual map into smaller regions. The robot is efficiently localized in such a partitioned environment using two-level localization. The concept of active map (AM) is proposed here, which is a map that represents one partition of the environment in which there is a high probability of the robot existing. High-level localization is used to track the mode of the AMs using discrete Bayes filter. Low-level localization uses a bag-of …

Abstract

We focus on the problem of wearer's action recognition in first person aka egocentric videos. This problem is more challenging than third person activity recognition due to unavailability of wearer's pose and sharp movements in the videos caused by the natural head motion of the wearer. Carefully crafted features based on hands and objects cues for the problem have been shown to be successful for limited targeted datasets. We propose convolutional neural networks (CNNs) for end to end learning and classification of wearer's actions. The proposed network makes use of egocentric cues by capturing hand pose, head motion and saliency map. It is compact. It can also be trained from relatively small number of labeled egocentric videos that are available. We show that the proposed network can generalize and give state of the art performance on various disparate egocentric action datasets.

Abstract

Classical visual servoing approaches use visual features based on geometry of the object such as points, lines, region, etc. to attain the desired camera pose. However, geometrical features are not suited for visual servoing across different object instances due to large variations in appearance and shape. In this paper, we present a new framework for visual servoing across object instances. Our approach is based on a discriminative learning framework where the desired pose is estimated using previously seen examples. Specifically, we learn a binary classifier that separates the desired pose from all other poses for that object category. The classification error is then used to control the end-effector so that the desired pose is attained. We present controllers for linear, kernel and exemplar Support Vector Machine (SVM) and empirically discuss their performance in the visual servoing context. To address large intra-category variation in appearance, we propose a modified version of Histogram of Oriented Gradients (HOG) features for visual servoing. We show effective servoing across diverse instances over 3 object categories with zero terminal velocity and acceptable camera pose error at termination.

Abstract

Egocentric videos are characterized by their ability to have the first person view. With the popularity of Google Glass and GoPro, use of egocentric videos is on the rise. With the substantial increase in the number of egocentric videos, the value and utility of recognizing actions of the wearer in such videos has also thus increased. Unstructured movement of the camera due to natural head motion of the wearer causes sharp changes in the visual field of the egocentric camera causing many standard third person action recognition techniques to perform poorly on such videos. Objects present in the scene and hand gestures of the wearer are the most important cues for first person action recognition but are difficult to segment and recognize in an egocentric video. We propose a novel representation of the first person actions derived from feature trajectories. The features are simple to compute using standard point tracking and do not assume segmentation of hand/objects or recognizing object or hand pose unlike in many previous approaches. We train a bag of words classifier with the proposed features and report a performance improvement of more than 11% on publicly available datasets. Although not designed for the particular case, we show that our technique can also recognize wearer's actions when hands or objects are not visible.

Abstract

A good post processing module is an indispensable part of an OCR pipeline. In this paper, we propose a novel method for error detection in Indian language OCR output. Our solution uses a recurrent neural network ( RNN ) for classification of a word as an error or not. We propose a generic error detection method and demonstrate its effectiveness on four popular Indian languages. We divide the words into their constituent aksharas and use their bigram and trigram level information to build a feature representation. In order to train the classifier on incorrect words, we use the mis-recognized words in the output of the OCR . In addition to RNN , we also explore the effectiveness of a generative model such as GMM for our task and demonstrate an improved performance by combining both the approaches. We tested our method on four popular Indian languages and report an average error detection performance above 80%.

Abstract

Facial fiducial detection is a challenging problem for several reasons like varying pose, appearance, expression, partial occlusion and others. In the past, several approaches like mixture of trees [32], regression based methods [8], exemplar based methods [7] have been proposed to tackle this challenge. In this paper, we propose an exemplar based approach to select the best solution from among outputs of regression and mixture of trees based algorithms (which we call candidate algorithms). We show that by using a very simple SIFT and HOG based descriptor, it is possible to identify the most accurate fiducial outputs from a set of results produced by candidate algorithms on any given test image. Our approach manifests as two algorithms, one based on optimizing an objective function with quadratic terms and the other based on simple kNN. Both algorithms take as input fiducial locations produced by running state-of-the-art candidate algorithms on an input image, and output accurate fiducials using a set of automatically selected exemplar images with annotations. Our surprising result is that in this case, a simple algorithm like kNN is able to take advantage of the seemingly huge complementarity of these candidate algorithms, better than optimization based algorithms. We do extensive experiments on several datasets, and show that our approach outperforms state-of-the-art consistently. In some cases, we report as much as a 10% improvement in accuracy. We also extensively analyze each component of our approach, to illustrate its efficacy. An implementation and extended technical report of our approach is available www.sites.google.com/site/wacv2016facefiducialexemplars.

Abstract

Automatic image annotation is the computer vision task of assigning a set of appropriate textual tags to a novel image. The aim is to eventually bridge the semantic gap of visual and textual representations with the help of these tags. This also has applications in designing scalable image retrieval systems and providing multilingual interfaces. Though a wide varieties of powerful machine learning algorithms have been explored for the image annotation problem in the recent past, nearest neighbor techniques still yield superior results to them. A challenge ahead of the present day annotation schemes is the lack of sufficient training data. In this paper, an active Learning based image annotation model is proposed. We leverage the image-to-image and image-to-tag similarities to decide the best set of tags describing the semantics of an image. The advantages of the proposed model includes: (a). It is able to output the …

Abstract

Egocentric cameras are wearable cameras mounted on a person's head or shoulder. With their ability to have first person view, such cameras are spawning new set of exciting applications in computer vision. Recognising activity of the wearer from an egocentric video is an important but challenging problem. The task is made especially difficult because of unavailability of wearer's pose as well as extreme camera shake due to motion of wearer's head. Solutions suggested so far for the problem, have either focussed on short term actions such as pour, stir etc. or long term activities such as walking, driving etc. The features used in both the styles are very different and the technique developed for one style often fail miserably on other kind. In this paper we propose a technique to identify if a long term or a short term action is present in an egocentric video segment. This allows us to have a generic first-person action …

Abstract

Instance retrieval (IR) is the problem of retrieving specific instances of a particular object, like a monument, from a collection of images. Currently, the most popular methods for IR use Bag of words (BoW) features for retrieval. However, a prominent problem for IR remains the tendency of BoW based methods to retrieve near-identical images as most relevant results. In this paper, we define diversity in IR as variation of physical properties among most relevant retrieved results for a query image. To achieve this, we propose both an ITML algorithm that re-fashions the BoW feature space into one that appreciates diversity better, and a measure to evaluate diversity in retrieval results for IR applications. Additionally, we also generate 200 hand-labeled images from the Paris dataset, for use in further research in this area. Experiments on the popular Paris dataset show that our method outperforms the standard BoW model …