Abstract

The proposed work exploits acoustic cues at various levels and incorporates them in the present (Spoken Term Detection) STD frame work. Recently proposed new syllabification method [1] for speech signal is being used for STD. In STD, a query and reference speech signals are provided, these speech signals are syllabified using the new syllabification method and features like Mel-frequency cepstral coefficients (MFCC), posterior grams are extracted. These features are then matched using template based match techniques like dynamic time warping (DTW) at syllable level instead of regular frame level. This essentially reduces the unwanted matching done at frame level.

Abstract

Software systems often serve as the agents of operation for both enterprise systems and embedded systems. Engineering such systems is a knowledge-centric activity. A clear understanding of the relationship between knowledge, systems and engineering can help us to establish firm theoretical foundations for software and systems engineering. Currently we have a strong intuitive understanding of how knowledge flows into engineering, while our understanding of the relationship between systems and knowledge is part explicit and part tacit. A symptom of this is that we have difficulty in building unified models of large systems such as telescopes and enterprises that span multiple knowledge domains and viewpoints. We are able to build multiple models covering various aspects and particular viewpoints. However, we have challenges in integrating them into a single unified model. Another symptom is that software and systems engineering practice are widely viewed as empirical fields, without sufficiently strong theoretical foundations. This work attempts to explicate and synthesize our common intuitive understanding in this space to develop a conceptual model of the relationships. It then explores the validity of this model by examining the extent to which it is able to explain and illuminate current engineering practices and issues. This is an initial strawman version of the model, presented with a view to obtaining feedback and inputs from the community.

Abstract

e datasets. We propose an EEG (Electroencephalogram)-based image annotation system. While humans can recognize objects in 20–200 ms, the need to manually label images results in a low annotation throughput. Our system employs brain signals captured via a consumer EEG device to achieve an annotation rate of up to 10 images per second. We exploit the P300 event-related potential (ERP) signature to identify target images during a rapid serial visual presentation (RSVP) task. We further perform unsupervised outlier removal to achieve an F1-score of 0.88 on the test set. The proposed system does not depend on category-specific EEG signatures enabling the annotation of any new image category without any model pre-training.

Abstract

Popularity of wearable cameras in life logging, law enforcement, assistive vision and other similar applications is leading to explosion in generation of egocentric video content. First person action recognition is an important aspect of automatic analysis of such videos. Annotating such videos is hard, not only because of obvious scalability constraints, but also because of privacy issues often associated with egocentric videos. This motivates the use of unsupervised methods for egocentric video analysis. In this work, we propose a robust and generic unsupervised approach for first person action clustering. Unlike the contemporary approaches, our technique is neither limited to any particular class of action nor requires priors such as pre-training, fine-tuning, etc. We learn time sequenced visual and flow features from an array of weak feature extractors based on convolutional and LSTM autoencoder networks. We demonstrate that clustering of such features leads to the discovery of semantically meaningful actions present in the video. We validate our approach on four disparate public egocentric actions datasets amounting to approximately 50 hours of videos. We show that our approach surpasses the supervised state of the art accuracies without using the action labels.

Abstract

Color and strokes are the salient features of text regions in an image. In this work, we use both these features as cues, and introduce a novel energy function to formulate the text binarization problem. The minimum of this energy function corresponds to the optimal binarization. We minimize the energy function with an iterative graph cut-based algorithm. Our model is robust to variations in foreground and background as we learn Gaussian mixture models for color and strokes in each iteration of the graph cut. We show results on word images from the challenging ICDAR 2003/2011, born-digital image and street view text datasets, as well as full scene images containing text from ICDAR 2013 datasets, and compare our performance with state-of-the-art methods. Our approach shows significant improvements in performance under a variety of performance measures commonly used to assess text binarization …

Abstract

We propose an active learning based solution for efficient, scalable and accurate annotations of objects in video sequences. Recent computer vision solutions use machine learning. Effectiveness of these solutions relies on the amount of available annotated data which again depends on the generation of huge amount of accurately annotated data. In this paper, we focus on reducing the human annotation efforts with simultaneous increase in tracking accuracy to get precise, tight bounding boxes around an object of interest. We use a novel combination of two different tracking algorithms to track an object in the whole video sequence. We propose a sampling strategy to sample the most informative frame which is given for human annotation. This newly annotated frame is used to update the previous annotations. Thus, by collaborative efforts of both human and the system we obtain accurate annotations with minimal effort. Using the proposed method, user efforts can be reduced to half without compromising on the annotation accuracy. We have quantitatively and qualitatively validated the results on eight different datasets.

Abstract

A method and a system are provided to derive one or more observations between a plurality of parameters in customer care data. The method includes receiving customer care data from a plurality of data sources. Thereafter the customer care data is transformed to create a plurality of data structures utilizing one or more semantic web protocols. The plurality of data structures represents a relationship between one or more parameters in the customer care data. Thereafter a subset of data structures is extracted from the plurality of data structures based on a query received via a query interface. One or more graph analytics techniques are applied on the subset of data structures to determine one or more observations associated with the subset of data structures. Thereafter the one or more observations pertaining to the subset of data structures are displayed on a display screen.

Abstract

Person recognition methods that use multiple body regions have shown significant improvements over traditional face-based recognition. One of the primary challenges in full-body person recognition is the extreme variation in pose and view point. In this work,(i) we present an approach that tackles pose variations utilizing multiple models that are trained on specific poses, and combined using pose-aware weights during testing.(ii) For learning a person representation, we propose a network that jointly optimizes a single loss over multiple body regions.(iii) Finally, we introduce new benchmarks to evaluate person recognition in diverse scenarios and show significant improvements over previously proposed approaches on all the benchmarks including the photo album setting of PIPA.

Abstract

End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of freely available multi-modal content to train computer vision algorithms without human supervision. We put forward the idea of performing self-supervised learning of visual features by mining a large scale corpus of multi-modal (text and image) documents. We show that discriminative visual features can be learnt efficiently by training a CNN to predict the semantic context in which a particular image is more probable to appear as an illustration. For this we leverage the hidden semantic structures discovered in the text corpus with a well-known topic modeling technique. Our experiments demonstrate state of the art performance in image classification, object detection, and multi-modal retrieval compared to recent self-supervised or natural-supervised approaches.

Abstract

Recordings of stage performances are easy to capture with a high-resolution camera, but are difficult to watch because the actors’ faces are too small. We present an approach to automatically create a split screen video that transforms these recordings to show both the context of the scene as well as close-up details of the actors. Given a static recording of a stage performance and tracking information about the actors positions, our system generates videos showing a focus+context view based on computed close-up camera motions using crop-and zoom. The key to our approach is to compute these camera motions such that they are cinematically valid close-ups and to ensure that the set of views of the different actors are properly coordinated and presented. We pose the computation of camera motions as convex optimization that creates detailed views and smooth movements, subject to cinematic constraints such as not cutting faces with the edge of the frame. Additional constraints link the close up views of each actor, causing them to merge seamlessly when actors are close. Generated views are placed in a resulting layout that preserves the spatial relationships between actors. We demonstrate our results on a variety of staged theater and dance performances.