Saurabh Gupta - BHU

Saurabh Gupta
Are you Saurabh Gupta?

Claim your profile, edit publications, add additional information:

Contact Details

Saurabh Gupta

Pubs By Year

Pub Categories

High Energy Physics - Theory (13)
Computer Science - Computer Vision and Pattern Recognition (10)
Computer Science - Computation and Language (3)
High Energy Physics - Phenomenology (3)
High Energy Physics - Experiment (3)
Physics - Fluid Dynamics (2)
Quantitative Biology - Genomics (2)
Computer Science - Learning (2)
Computer Science - Robotics (2)
Computer Science - Artificial Intelligence (2)
Quantum Physics (1)
Quantitative Biology - Quantitative Methods (1)
Nonlinear Sciences - Exactly Solvable and Integrable Systems (1)
Mathematical Physics (1)
Mathematics - Mathematical Physics (1)

Publications Authored By Saurabh Gupta

We introduce a neural architecture for navigation in novel environments. Our proposed architecture learns to map from first-person viewpoints and plans a sequence of actions towards goals in the environment. The Cognitive Mapper and Planner (CMP) is based on two key ideas: a) a unified joint architecture for mapping and planning, such that the mapping is driven by the needs of the planner, and b) a spatial memory with the ability to plan given an incomplete set of observations about the world. Read More

We exploit the techniques of Bonora-Tonin superfield formalism to derive the off-shell nilpotent and absolutely anticommuting (anti-)BRST as well as (anti-)co-BRST symmetry transformations for the (1+1)-dimensional (2D) bosonized vector Schwinger model. In the derivation of above symmetries, we invoke the (dual)-horizontality conditions as well as gauge and (anti-)co-BRST invariant restrictions on the superfields that are defined onto the (2, 2)-dimensional supermanifold. We provide geometrical interpretation of the above nilpotent symmetries (and their corresponding charges). Read More

We analyze the constraints for a system of anti self-dual Yang-Mills (ASDYM) equations by means of the modified Faddeev-Jackiw method in K and J gauges \`{a} la Yang. We also establish the Hamiltonian flow for ASDYM system through the hidden BRS invariance in both the gauges. Finally, we remark on the bi-Hamiltonian nature of ASDYM and the compatibility of the symplectic structures therein. Read More

In this paper we explore two ways of using context for object detection. The first model focusses on people and the objects they commonly interact with, such as fashion and sports accessories. The second model considers more general object detection and uses the spatial relationships between objects and between objects and scenes. Read More

In this work we propose a technique that transfers supervision between images from different modalities. We use learned representations from a large labeled modality as a supervisory signal for training representations for a new unlabeled paired modality. Our method enables learning of rich representations for unlabeled modalities and can be used as a pre-training procedure for new modalities with limited labeled data. Read More

The origin of small mixing among the quarks and a large mixing among the neutrinos has been an open question in particle physics. In order to answer this question, we postulate general relations among the quarks and the leptonic mixing angles at a high scale, which could be the scale of Grand Unified Theories. The central idea of these relations is that the quark and the leptonic mixing angles can be unified at some high scale either due to some quark-lepton symmetry or some other underlying mechanism and as a consequence, the mixing angles of the leptonic sector are proportional to that of the quark sector. Read More

We explore a variety of nearest neighbor baseline approaches for image captioning. These approaches find a set of nearest neighbor images in the training set from which a caption may be borrowed for the query image. We select a caption for the query image by finding the caption that best represents the "consensus" of the set of candidate captions gathered from the nearest neighbor images. Read More

In this paper we introduce the problem of Visual Semantic Role Labeling: given an image we want to detect people doing actions and localize the objects of interaction. Classical approaches to action recognition either study the task of action classification at the image or video clip level or at best produce a bounding box around the person doing the action. We believe such an output is inadequate and a complete understanding can only come when we are able to associate objects in the scene to the different semantic roles of the action. Read More

Two recent approaches have achieved state-of-the-art results in image captioning. The first uses a pipelined process where a set of candidate words is generated by a convolutional neural network (CNN) trained on images, and then a maximum entropy (ME) language model is used to arrange these words into a coherent sentence. The second uses the penultimate activation layer of the CNN as input to a recurrent neural network (RNN) that then generates the caption sequence. Read More

In this paper we describe the Microsoft COCO Caption dataset and evaluation server. When completed, the dataset will contain over one and a half million captions describing over 330,000 images. For the training and validation images, five independent human generated captions will be provided. Read More

The goal of this work is to replace objects in an RGB-D scene with corresponding 3D models from a library. We approach this problem by first detecting and segmenting object instances in the scene using the approach from Gupta et al. [13]. Read More

We derive the off-shell nilpotent and absolutely anticommuting Becchi-Rouet-Stora-Tyutin (BRST) as well as anti-BRST transformations s_{(a)b} corresponding to the Yang-Mills gauge transformations of 3D Jackiw-Pi model by exploiting the "augmented" superfield formalism. We also show that the Curci-Ferrari restriction, which is a hallmark of any non-Abelian 1-form gauge theories, emerges naturally within this formalism and plays an instrumental role in providing the proof of absolute anticommutativity of s_{(a)b}. Read More

The flamelet approach offers a viable framework for combustion modeling of homogeneous charge compression ignition (HCCI) engines under stratified mixture conditions. Scalar dissipation rate acts as a key parameter in flamelet-based combustion models which connects the physical mixing space to the reactive space. The aim of this paper is to gain fundamental insights into turbulent mixing in low temperature combustion (LTC) engines and investigate the modeling of scalar dissipation rate. Read More

Cyclic-to-cycle variability, CCV, of intake-jet flow in an optical engine was measured using particle image velocimetry (PIV), revealing the possibility of two different flow patterns. A phase-dependent proper orthogonal decomposition (POD) analysis showed that one or the other flow pattern would appear in the average flow, sampled from test to test or sub-sampled within a single test; each data set contained individual cycles showing one flow pattern or the other. Three-dimensional velocity data from a large-eddy simulation (LES) of the engine showed that the PIV plane was cutting through a region of high shear between the intake jet and another large flow structure. Read More

We derive the complete set of off-shell nilpotent (s^2_{(a)b} = 0) and absolutely anticommuting (s_b s_{ab} + s_{ab} s_b = 0) Becchi-Rouet-Stora-Tyutin (BRST) (s_b) as well as anti-BRST symmetry transformations (s_{ab}) corresponding to the combined Yang-Mills and non-Yang-Mills symmetries of the (2 + 1)-dimensional Jackiw-Pi model within the framework of augmented superfield formalism. The absolute anticommutativity of the (anti-)BRST symmetries is ensured by the existence of two sets of Curci-Ferrari (CF) type of conditions which emerge naturally in this formalism. The presence of CF conditions enables us to derive the coupled but equivalent Lagrangian densities. Read More

This paper presents a novel approach for automatically generating image descriptions: visual detectors, language models, and multimodal similarity models learnt directly from a dataset of image captions. We use multiple instance learning to train visual detectors for words that commonly occur in captions, including many different parts of speech such as nouns, verbs, and adjectives. The word detector outputs serve as conditional inputs to a maximum-entropy language model. Read More

In this paper we study the problem of object detection for RGB-D images using semantically rich image and depth features. We propose a new geocentric embedding for depth images that encodes height above ground and angle with gravity for each pixel in addition to the horizontal disparity. We demonstrate that this geocentric embedding works better than using raw depth images for learning feature representations with convolutional neural networks. Read More

High-throughput DNA sequencers are becoming indispensable in our understanding of diseases at molecular level, in marker-assisted selection in agriculture and in microbial genetics research. These sequencing instruments produce enormous amount of data (often terabytes of raw data in a month) that requires efficient analysis, management and interpretation. The commonly used sequencing instrument today produces billions of short reads (upto 150 bases) from each run. Read More

We investigate the renormalization group evolution of masses and mixing angles of Majorana neutrinos under the `High Scale Mixing Unification' hypothesis. Assuming the unification of quark-lepton mixing angles at a high scale, we show that all the experimentally observed neutrino oscillation parameters can be obtained, within 3-$\sigma$ range, through the running of corresponding renormalization group equations provided neutrinos have same CP parity and are quasi-degenerate. One of the novel results of our analysis is that $\theta_{23}$ turns out to be non-maximal and lies in the second octant. Read More

Starting with high scale mixing unification hypothesis, we investigate the renormalization group evolution of mixing parameters and masses for Dirac type neutrinos. Following this hypothesis, the PMNS mixing angles and phase are taken to be identical to the CKM ones at a unifying high scale. Then, they are evolved to a low scale using renormalization-group equations. Read More

We derive nilpotent and absolutely anticommuting (anti-)co-BRST symmetry transformations for the bosonized version of (1+1)-dimensional (2D) vector Schwinger model. These symmetry transformations turn out to be the analogue of co-exterior derivative of differential geometry as the total gauge-fixing term remains invariant under it. The exterior derivative is realized in terms of the (anti-)BRST symmetry transformations of the theory whereas the bosonic symmetries find their analogue in the Laplacian operator. Read More

We report SInC (SNV, Indel and CNV) simulator and read generator, an open-source tool capable of simulating biological variants taking into account a platform-specific error model. SInC is capable of simulating and generating single- and paired-end reads with user-defined insert size with high efficiency compared to the other existing tools. SInC, due to its multi-threaded capability during read generation, has a low time footprint. Read More

We derive the off-shell nilpotent and absolutely anticommuting Becchi-Rouet-Stora-Tyutin (BRST) as well as anti-BRST symmetry transformations corresponding to the non-Yang-Mills symmetry transformations of (2 + 1)- dimensional Jackiw-Pi (JP) model within the framework of "augmented" superfield formalism. The Curci-Ferrari restriction, which is a hallmark of non-Abelian 1-form gauge theories, does not appear in this case. One of the novel features of our present investigation is the derivation of proper (anti-)BRST symmetry transformations corresponding to the auxiliary field \rho that can not be derived by any conventional means. Read More

We derive the canonical (anti-)commutation relations amongst the creation and annihilation operators of the various basic fields, present in the four (3 + 1)-dimensional (4D) free Abelian 2-from gauge theory, with the help of continuous symmetry transformations within the framework of Becchi-Rouet-Stora-Tyutin (BRST) formalism. We show that all the six continuous symmetries of the theory lead to the exactly the same non-vanishing (anti-)commutator amongst the creation and annihilation operators of the normal mode expansion of the basic fields of the theory. Read More

We apply the superfield approach to the toy model of a rigid rotor and show the existence of the nilpotent and absolutely anticommuting Becchi-Rouet-Stora-Tyutin (BRST) and anti-BRST symmetry transformations, under which, the kinetic term and action remain invariant. Furthermore, we also derive the off-shell nilpotent and absolutely anticommuting (anti-) co-BRST symmetry transformations, under which, the gauge-fixing term and Lagrangian remain invariant. The anticommutator of the above nilpotent symmetry transformations leads to the derivation of a bosonic symmetry transformation, under which, the ghost terms and action remain invariant. Read More

We demonstrate that the four (3 + 1)-dimensional free Abelian 2-form gauge theory presents a tractable field theoretical model for the Hodge theory where the well-defined symmetry transformations correspond to the de Rham cohomological operators of differential geometry. The conserved charges, corresponding to the above continuous symmetry transformations, obey an algebra that is reminiscent of the algebra obeyed by the cohomological operators. The discrete symmetry transformation of the theory represents the realization of the Hodge duality operation that exists in the relationship between the exterior and co-exterior derivatives of differential geometry. Read More

We show that the previously known off-shell nilpotent (s_{(a)b}^2 = 0) and absolutely anticommuting (s_b s_{ab} + s_{ab} s_b = 0) Becchi-Rouet-Stora-Tyutin (BRST) transformations (s_b) and anti-BRST transformations (s_{ab}) are the symmetry transformations of the appropriate Lagrangian densities of a four (3 + 1)-dimensional (4D) free Abelian 2-form gauge theory which do not explicitly incorporate a very specific constrained field condition through a Lagrange multiplier 4D vector field. The above condition, which is the analogue of the Curci-Ferrari restriction of the non-Abelian 1-form gauge theory, emerges from the Euler-Lagrange equations of motion of our present theory and ensures the absolute anticommutativity of the transformations s_{(a)b}. Thus, the coupled Lagrangian densities, proposed in our present investigation, are aesthetically more appealing and more economical. Read More

We consider a couple of examples to study the pseudo-Hermitian interaction in relativistic quantum mechanics. Rasbha interaction, commonly used to study the spin Hall effect, is considered with imaginary coupling. The corresponding Dirac Hamiltonian is shown to be parity pseudo-Hermitian. Read More