Abstract

We propose a novel scheme for improving the word recognition accuracy using word image embeddings. We use a trained text recognizer, which can predict multiple text hypothesis for a given word image. Our fusion scheme improves the recognition process by utilizing the word image and text embeddings obtained from a trained word image embedding network. We propose EmbedNet, which is trained using a triplet loss for learning a suitable embedding space where the embedding of the word image lies closer to the embedding of the corresponding text transcription. The updated embedding space thus helps in choosing the correct prediction with higher confidence. To further improve the accuracy, we propose a plug-and-play module called Confidence based Accuracy Booster (CAB). The CAB module takes in the confidence scores obtained from the text recognizer and Euclidean distances between the embeddings to generate an updated distance vector. The updated distance vector has lower distance values for the correct words and higher distance values for the incorrect words. We rigorously evaluate our proposed method systematically on a collection of books in the Hindi language. Our method achieves an absolute improvement of around 10 percent in terms of word recognition accuracy.

Abstract

Localizing page elements/objects such as tables, figures, equations, etc. is the primary step in extracting information from document images. We propose a novel end-to-end trainable deep network,(CDeC-Net) for detecting tables present in the documents. The proposed network consists of a multistage extension of Mask R-CNN with a dual backbone having deformable convolution for detecting tables varying in scale with high detection accuracy at higher IoU threshold. We empirically evaluate CDeC-Net on all the publicly available benchmark datasets-ICDAR-2013, ICDAR-2017, ICDAR-2019, UNLV, Marmot, PubLayNet, and TableBank-with extensive experiments. Our solution has three important properties:(i) a single trained model CDeC-Net‡ performs well across all the popular benchmark datasets;(ii) we report excellent performances across multiple, including higher, thresholds of IoU;(iii) by following the same protocol of the recent papers for each of the benchmarks, we consistently demonstrate the superior quantitative performance. Our code and models will be publicly released for enabling the reproducibility of the results.

Abstract

his paper presents results of Document Visual Question Answering Challenge organized as part of" Text and Documents in the Deep Learning Era" workshop, in CVPR 2020. The challenge introduces a new problem-Visual Question Answering on document images. The challenge comprised two tasks. The first task concerns with asking questions on a single document image. On the other hand, the second task is set as a retrieval task where the question is posed over a collection of images. For the task 1 a new dataset is introduced comprising 50,000 questions-answer (s) pairs defined over 12,767 document images. For task 2 another dataset has been created comprising 20 questions over 14,362 document images which share the same document template.

Abstract

A Theory of Magnitude (ATOM) suggests that space, time, and quantities are processed through a generalized magnitude system. ATOM posits that task-irrelevant magnitudes interfere with the processing of task-relevant magnitudes as all the magnitudes are processed by a common system. Many behavioural and neuroimaging studies have found support in favour of a common magnitude processing system. However, it is largely unknown whether such cross-domain monotonic mapping arises from a change in accuracy of the magnitude judgments or results from changes in precision of the processing of magnitude. Therefore, in the present study, we examined whether large numerical magnitude affects temporal accuracy or temporal precision or both. In other words, whether numerical magnitudes change our temporal experience or simply bias our duration judgments. The temporal discrimination (between …

Abstract

The task of identifying emotions from a given music track has been an active pursuit in the Music Information Retrieval (MIR) community for years. Music emotion recognition has typically relied on acoustic features, social tags, and other metadata to identify and classify music emotions. The role of lyrics in music emotion recognition remains under-appreciated in spite of several studies reporting superior performance of music emotion classifiers based on features extracted from lyrics. In this study, we use the transformer-based approach model using XLNet as the base architecture which, till date, has not been used to identify emotional connotations of music based on lyrics. Our proposed approach outperforms existing methods for multiple datasets. We used a robust methodology to enhance web-crawlers' accuracy for extracting lyrics. This study has important implications in improving applications involved in playlist generation of music based on emotions in addition to improving music recommendation systems.

Abstract

Reducing electricity consumption has emerged as a key area of concern according to the National Mission of Sustainable Habitat of Government of India. Among the Indian cities, Delhi’s electricity consumption is the highest. This paper aims to evaluate the impact of UHI on electricity consumption of Delhi. The study utilizes the satellite land surface temperature (LST) data to compute the district-wise urban heat island intensity (UHII) in Delhi. The electricity consumption and LST data are used to examine the association between them. The scatter plots between percapita net electricity consumption and night-time LST of each district show strong association between them and polynomial curves best fit this association. The equations of these polynomial curves are then used to estimate the electricity consumption of each district assuming their LSTs to be equal to that of the surrounding rural strip (i.e. without UHI effect). The difference between the observed and estimated electricity consumption at observed and assumed (i.e. rural) LSTs provided the increase in electricity consumption due to UHI. The study shows that UHI formation caused an increased electricity consumption of 2600 GWh (i.e. 11.4%) annually on an average over eight districts of Delhi during the period April 2012 to March 2017.

Abstract

Univariate meteorological drought indices are inadequate to represent the complexity of hydrological conditions under the intensification of hydrological cycle due to climate change at catchment scale. In this study, Stand­ ardised Precipitation Actual Evapotranspiration Index (SPAEI) was proposed, which can combine both meteo­ rological and hydrological drought characteristics at catchment scale. The proposed new drought index considers the hydrologically calibrated AET to account for the water use in addition to meteorological effect. The proposed hydrometeorological drought index was potential in identifying meteorological and hydrological drought events accounting for the time-lag effects and comparable with Global Land Evaporation Amsterdam Model (GLEAM) remote sensing AET data-based drought index. The PET based drought index of SPEI, which is based on energy demand, has shown intensified drought characteristics compared to SPAEI, which is based on both energy de­ mand and available moisture supply and can be a promising variable in the drought estimation. The climate change projections of precipitation and temperatures downscaled using statistical downscaling model based on K-means clustering, Classification and Regression Trees and Support Vector Regression were used using three General Circulation Model outputs. Intensified drought characteristics under climate change has been predicted over Krishna River basin, India, in terms of increase of drought areal extent of about 25%-31%, with increase of drought frequency as 5 years per 20 years and durations as 4–5 months based on the proposed hydrometeoro­ logical drought index of SPAEI.

Abstract

It is known that beyond 2 ⊗ 2 and 2 ⊗ 3 dimensional quantum systems, Peres-Hordecki criterion is no longer sufficient as an entanglement detection criterion as there are entangled states with both positive and negative partial transpose (PPT and NPT). Further, it is also true that all PPT entangled states are bound entangled states. However, in the class of NPT states, there can exist bound entangled states as well as free entangled states. All free/useful/distillable entanglement is a part of the class of NPT entangled states. In this article, we ask the question that given an NPT entangled state in 3 ⊗ 3 dimensional system as a resource, how much entanglement can we broadcast so that resource still remains NPT. We have chosen 3 ⊗ 3 system as a first step to understand broadcasting of NPT states in higher dimensional systems. In particular, we find out the range of broadcasting of NPT entanglement for Two parameter Class of States (TPCS) and Isotropic States (IS). Interestingly, as a derivative of this process we are also able to locate the existence of absolute PPT states (ABPPT) in 3 ⊗ 3 dimensional system. Here we implement the strategy of broadcasting through approximate cloning operations.

Abstract

Large gains in the rate of cache-aided broadcast communication are obtained using coded caching, but to obtain this most existing centralized coded caching schemes require that the files at the server be divisible into a large number of parts (this number is called subpacketization). In fact, most schemes require the subpacketization to be growing asymptotically as exponential in some root of the number of users . On the other extreme, few schemes having subpacketization linear in are known; however they require large number of users to exist, or they offer only little gain in rate. In this work, we propose a new framework known astextit {caching line graphs} for centralized coded caching and utilize projective geometries over finite fields to construct two new coded caching schemes with low subpacketization and moderate rate gains. Both the schemes achieve the same asymptotic subpacketization, which is …

Abstract

In this paper, we investigate a constrained formulation of neural networks where the output is a convex function of the input. We show that the convexity constraints can be enforced on both fully connected and convolutional layers, making them applicable to most architectures. The convexity constraints include restricting the weights (for all but the first layer) to be non-negative and using a non-decreasing convex activation function. Albeit simple, these constraints have profound implications on the generalization abilities of the network. We draw three valuable insights: (a) Input Output Convex Networks (IOC-NN) self regularize and almost uproot the problem of overfitting; (b) Although heavily constrained, they come close to the performance of the base architectures; and (c) The ensemble of convex networks can match or outperform the non convex counterparts. We demonstrate the efficacy of the proposed idea using thorough experiments and ablation studies on MNIST, CIFAR10, and CIFAR100 datasets with three different neural network architectures. The code for this project is publicly available at: https://github.com/sarathsp1729/Convex-Networks.