Abstract

In order to perform speech summmarization it is necessary to identify important segments in speech signal. The importance of a speech segment can be effectively determined by using infomation from lexical and prosodic features. Standard speech summarization systems depend on ASR transcripts or gold standard human reference summaries to train a supervised system which combines lexical and prosodic features to choose a segment into summary. We propose a method which uses prominence values of syllables in a speech segment to rank the segment for summarization. The proposed method does not depend on ASR transcripts or gold standard human summaries. Evaluation results showed that summaries generated by the proposed method are as good as the summaries generated using tf* idf scores and supervised system trained on gold standard summaries.

Abstract

In this report, we present details about the participation of IIIT Hyderabad in Guided Summarization and Knowledge Base Population tracks at TAC 2010. This year, we enhanced our summaization system with knowledge based measures and utilized domain and sentence tag models to score sentences to suit guided summarization track. We have used an external tool, WikiMiner to identify key concepts in the documents and extract important sentences. We adopted an Information Retrieval based approach for the Entity Linking and Slot Filling tasks. In Entity Linking we identified potential nodes from the Knowledge Base and then identified the mapping node using tf-idf similarity. We achieved very good performance in the Entity Linking task. For Slot Filling task we identified documents from the document collection that might contain attribute information. We extracted the attribute information using a rule based approach.

Abstract

MapReduce has become a popular paradigm for large scale data processing in the cloud. The sheer scale of MapReduce deployments make task assignment in MapReduce an interesting problem. The scale of MapReduce applications presents unique opportunity to use data driven algorithms in resource management. We present a learning based scheduler that uses pattern classification for utilization oriented task assignment in MapReduce. We also present the application of our algorithm to the Hadoop platform. The scheduler assigns tasks by classifying them in two classes, good and bad. From the tasks labeled as good it selects a task that is least likely to overload a worker node. We allow users to plug in their own policy schemes for prioritizing jobs. The scheduler learns the impact of different applications on utilization rather quickly and achieves a user specified level of utilization. Our results show that our scheduler reduces response times of jobs in certain cases by a factor of two.

Abstract

One of the most common computer vision tasks is that of recognizing the category of objects present in a given image. Previous work has mostly focused on building accurate classifiers based on carefully selected features. Classification is often carried on individual test images, while most of the practical situations, such as webscale image indexing, demand the simultaneous classification of a large collection of images. This is especially true for real-world datasets, that already contain numerous un-indexed images and videos. In this paper, we work towards developing a computationally efficient approach towards object recognition, that is inspired by retrieval schemes. We perform an offline indexing of the features from the collection, so that the classifier only needs to work on a small subset of the entire feature set. Over a set of 2 Million features extracted from 7000 images, classification against 5 object categories using a standard SVM would require more than 260 hours. Over the same test case, the classification time using our indexing based approach is reduced to less than 13 hours. The compromise on the accuracy is less than 7% for the 20X speedup achieved.

Abstract

In this paper, we present an approach to discover characteristic patterns in videos. We characterize the videos based on frequently occurring patterns like scenes, characters, sequence of frames in an unsupervised setting. With our approach, we are able to detect the representative scenes and characters of movies. We also present a method for detecting video stop-words in broadcast news videos based on the frequency of occurrence of sequence of frames. These are analogous to stop-words in text classification and search. We employ two different video mining schemes; both aimed at detecting frequent and representative patterns. For one of our mining approaches, we use an efficient frequent pattern mining algorithm over a quantized feature space. Our second approach uses a Random Forest to first represent video data as sequences, and then mine the frequent patterns. We validate the proposed approaches on broadcast news videos and our database of 81 Oscar winning movies.

Abstract

In this paper, we present a practical vision based Simultaneous Localization and Mapping (SLAM) system for a highly dynamic environment. We adopt a multibody Structure from Motion (SfM) approach, which is the generalization of classical SfM to dynamic scenes with multiple rigidly moving objects. The proposed framework of multibody visual SLAM allows choosing between full 3D reconstruction or simply tracking of the moving objects, which adds flexibility to the system, for scenes containing non-rigid objects or objects having insufficient features for reconstruction. The solution demands a motion segmentation framework that can segment feature points belonging to different motions and maintain the segmentation with time. We propose a realtime incremental motion segmentation algorithm for this purpose. The motion segmentation is robust and is capable of segmenting difficult degenerate motions, where the moving objects is followed by a moving camera in the same direction. This robustness is attributed to the use of efficient geometric constraints and a probability framework which propagates the uncertainty in the system. The motion segmentation module is tightly coupled with feature tracking and visual SLAM, by exploring various feed-backs in between these modules. The integrated system can simultaneously perform realtime visual SLAM and tracking of multiple moving objects using only a single monocular camera.

Abstract

An important pre-requisite for many tasks like Visual Servoing and visual SLAM is the task of tracking the underlying features. The use of planar features for these purposes has gained importance recently. Complementing current planar tracking works in the robotics literature, which use multiple features, we formulate the tracking problem using multiple planes. Inspired by the maturity in understanding of geometric quantities like the homography in computer vision, we develop a system based on the Unscented Kalman Filter (UKF) that localizes the camera and estimates the plane parameters of a scene, using homographies as measurement. Homographies are estimated using tracked feature points. We show that this framework provides significant robustness and stability to the system under significant changes of illumination, occlusion etc. Finally, we also propose a Convex optimization based solution for the initialization of this system, which is capable of producing globally optimal estimates, and is a useful algorithm in its own right. Several synthetic and real results are presented to demonstrate the efficacy of our approach.

Abstract

Semantic analysis of a document collection can be viewed as an unsupervised clustering of the constituent words and documents around hidden or latent concepts. This has shown to improve the performance of visual bag of words in image retrieval. However, the enhancement in performance depends heavily on the right choice of number of semantic concepts. Most of the semantic indexing schemes are also computationally costly. In this paper, we employ a bipartite graph model (BGM) for image retrieval. BGM is a scalable datastructure that aids semantic indexing in an efficient manner. It can also be incrementally updated. BGM uses tf-idf values for building a semantic bipartite graph. We also introduce a graph partitioning algorithm that works on the BGM to retrieve semantically relevant images from a database. We demonstrate the properties as well as performance of our semantic indexing scheme through a series of experiments. We also compare our methods with incremental pLSA

Abstract

In this paper, we present a monocular camera based terrain classification scheme. The uniqueness of the proposed scheme is that it inherently incorporates spatial smoothness while segmenting a image, without requirement of post-processing smoothing methods. The algorithm is extremely fast because it is build on top of a Random Forest classifier. The baseline algorithm uses color, texture and their combination with classifiers such as SVM and Random Forests. We present comparison across features and classifiers. We further enhance the algorithm through a label transfer method. The efficacy of the proposed solution can be seen as we reach a low error rates on both our dataset and other publicly available datasets.

Abstract

Kernel methods yield state-of-the-art performance in certain applications such as image classification and object detection. However, large scale problems require machine learning techniques of at most linear complexity and these are usually limited to linear kernels. This unfortunately rules out gold-standard kernels such as the generalized RBF kernels (e.g. exponential-χ 2 ). Recently, Maji and Berg [13] and Vedaldi and Zisserman [20] proposed explicit feature maps to approximate the additive kernels (intersection, χ 2 , etc.) by linear ones, thus enabling the use of fast machine learning technique in a non-linear context. An analogous technique was proposed by Rahimi and Recht [14] for the translation invariant RBF kernels. In this paper, we complete the construction and combine the two techniques to obtain explicit feature maps for the generalized RBF kernels. Furthermore, we investigate a learning method using l 1 regularization to encourage sparsity in the final vector representation, and thus reduce its dimension. We evaluate this technique on the VOC 2007 detection challenge, showing when it can improve on fast additive kernels, and the trade-offs in complexity and accuracy