Abstract

Complementary fashion recommendation aims at identifying items from different categories (e.g. shirt, footwear, etc.) that "go well together" as an outfit. Most existing approaches learn representation for this task using labeled outfit datasets containing manually curated compatible item combinations. In this work, we propose to learn representations for compatibility prediction from in-the-wild street fashion images through self-supervised learning by leveraging the fact that people often wear compatible outfits. Our pretext task is formulated such that the representations of different items worn by the same person are closer compared to those worn by other people. Additionally, to reduce the domain gap between in-the-wild and catalog images during inference, we introduce an adversarial loss that minimizes the difference in feature distribution between the two domains. We conduct our experiments on two popular fashion compatibility benchmarks - Polyvore and Polyvore-Disjoint outfits, and outperform existing self-supervised approaches, particularly significant in cross-dataset setting where training and testing images are from different sources.

Abstract

The fidelity of a pose transfer system depends on its ability to generate realistic images of a person under novel poses while preserving the desired human attributes (like face, hairstyle, and clothes). However, the visual fidelity is often compromised as the existing methods fail to extract rich appearance and pose features since they propagate the pose and the appearance information through the same pathway. Also, the repeated downsampling in these pathways leads to the loss of finer details, thus producing blurry results. Further, these methods use vanilla convolution that treats all the pixels as important and fail to focus primarily on significant regions needed for the desired transformation. This work proposes an appearance-consistent human pose transfer framework that progressively transforms the person in the source image to the desired target pose using the information from three pathways: an image pathway, a pose pathway, and an appearance pathway. We propose the use of gated convolution to dynamically extract features relevant for generating the transformed image. The appearance pathway generates an appearance code to produce an image consistent in appearance with that of the source image. We establish the efficacy of the proposed framework through an extensive set of experiments on DeepFashion, Market-1501, and the Action Class dataset. We also generate coherent action sequences through a given set of desired poses from the action class dataset that contains humans in three actions: golf,

Abstract

Due to hardware constraints, standard off-the-shelf digital cameras suffers from low dynamic range (LDR) and low frame per second (FPS) outputs. Previous works in high dynamic range (HDR) video reconstruction uses sequence of alternating exposure LDR frames as input, and align the neighbouring frames using optical flow based networks. However, these methods often result in motion artifacts in challenging situations. This is because, the alternate exposure frames have to be exposure matched in order to apply alignment using optical flow. Hence, over-saturation and noise in the LDR frames results in inaccurate alignment. To this end, we propose to align the input LDR frames using a pre-trained video frame interpolation network. This results in better alignment of LDR frames, since we circumvent the error-prone exposure matching step, and directly generate intermediate missing frames from the same exposure inputs. Furthermore, it allows us to generate high FPS HDR videos by recursively interpolating the intermediate frames. Through this work, we propose to use video frame interpolation for HDR video reconstruction, and present the first method to generate high FPS HDR videos. Experimental results demonstrate the efficacy of the proposed framework against optical flow based alignment methods, with an absolute improvement of 2.4 PSNR value on standard HDR video datasets [1], [2] and further benchmark our method for high FPS HDR video generation.

Abstract

The channel output entropy of a transmitted word is the entropy of the possible channel outputs and similarly the input entropy of a received word is the entropy of all possible transmitted words. The goal of this work is to study these entropy values for the k-deletion, k-insertion channel, where exactly k symbols are deleted, inserted in the transmitted word, respectively. If all possible words are transmitted with the same probability then studying the input and output entropies is equivalent. For both the 1-insertion and 1-deletion channels, it is proved that among all words with a fixed number of runs, the input entropy is minimized for words with a skewed distribution of their run lengths and it is maximized for words with a balanced distribution of their run lengths. Among our results, we establish a conjecture by Atashpendar et al. which claims that for the binary 1-deletion, the input entropy is maximized for the alternating words. For the 2-deletion channel, it is proved that constant words with a single run minimize the input entropy.

Abstract

The current approach to marking attendance in colleges is tedious and time consuming. I propose AttenFace, a standalone system to analyze, track and grant attendance in real time using face recognition. Using snapshots of class from live camera feed, the system identifies students and marks them as present in a class based on their presence in multiple snapshots taken throughout the class duration. Face recognition for each class is performed independently and in parallel, ensuring that the system scales with number of concurrent classes. Further, the separation of the face recognition server from the backend server for attendance calculation allows the face recognition module to be integrated with existing attendance tracking software like Moodle. The face recognition algorithm runs at 10 minute intervals on classroom snapshots, significantly reducing computation compared to direct processing of live camera feed. This method also provides students the flexibility to leave class for a short duration (such as for a phone call) without losing attendance for that class. Attendance is granted to a student if he remains in class for a number of snapshots above a certain threshold. The system is fully automatic and requires no professor intervention or any form of manual attendance or even camera set-up, since the back-end directly interfaces with inclass cameras. AttenFace is a first-of-its-kind one-stop solution for face-recognition-enabled attendance in educational institution

Abstract

A limiting factor for readout fidelity for superconducting qubits is the relaxation of the qubit to the ground state before the time needed for the resonator to reach its final target state. A technique known as excited state promoted (ESP) readout was proposed to reduce this effect and further improve the readout contrast on superconducting hardware. In this work, we use readout data from IBM’s five-qubit quantum systems to measure the effectiveness of using deep neural networks, like feedforward neural networks, and various classification algorithms, like knearest neighbors, decision trees, and Gaussian naive Bayes, for single-qubit and multi-qubit discrimination. These methods were compared to standardly used linear and quadratic discriminant analysis algorithms based on their qubit-state-assignment fidelity performance, robustness to readout crosstalk, and training time. Index Terms—Quantum Computing, Qubit Readout, Machine Learning, Deep Learning

Abstract

India Meteorological Department (IMD) is delivering agromet advisories, i.e., weather-based crop risk management advisories based on the medium-range weather forecast (five days) across India. Based on the weather prediction, once in five days, agromet advisory is provided for major crops and livestock by considering the district/block as a unit. In the literature, a framework was proposed to improve the process of advisory preparation by employing the notion of reuse. In that framework, an approach was explored to reuse the advisory prepared for the given weather situation to prepare advisory for similar weather situations in the future. For this, a notion of category-based weather condition (CWC) was proposed to model a given

Abstract

Historians and economists working on the Indian railways refer to what they term the ‘railway mania’ of Britain in the 1840s, resulting ultimately in two principal achievements of the industrial revolution (the steamship and the steam engine) being brought to the colonies.1 Multiple rationales have been ofered to explain the spread of this ‘mania’ to India. Recounting the debate around the Indian railways, Bipan Chandra reminds us of the ‘strong political and economic pressure’ from textile manufacturers in Lancashire, who wished to access the vast supplies of cotton and wheat in India.2 Apart from being a source of opulent raw materials, India could also become a huge consumer of textile and other products manufactured in Britain, Daniel Thorner points out.3 In addition to the commercial and economic advantages, once put in place, the railways could be used to transport military personnel from one part of the vast colony to another in a relatively short time.4 These economic and political justifcations apart—many of which have been dealt with in great detail by a number of scholars of colonial India—we are left with the undeniable fact that railway construction remained a crucial endeavour of colonial rule in British India. The frst passenger railway line in India, covering 34 km between Bori Bunder (Bombay) and Thane, was opened to trafc on 16 April 1853, barely 28 years after the world’s frst successful train ran between Stockton and Darlington in England in 1825. This was one of the frst railway lines in the country. Before passenger trains were introduced, there were a few trains used to transport stone and other material, such as on the Red Hill line in Chennai in South India. The frst short lines were followed by a rapid escalation of railway construction.5 In Ian Kerr’s estimate, by 1870, ‘excluding Russia (and thus Russian Asia), ffty-fve per cent of all operating railway mileage in Africa, Asia, and Latin America combined was located in India’. The fact that neither China nor Japan had operating lines at the time stresses the unique nature of railway construction in India.6 During these initial tumultuous years, the railway building project was

Abstract

Decay heat removal(DHR) system plays a crucial role in maintaining the reactor safety with the ultimate cooling arrangement in case all the other intended systems are unavailable. As a special case, the system shall also ensure that the reactor is not overcooled so that the coolant is not frozen. In this regard, a passive device is to be developed to meet the requirement of monitoring DHR system temperature. Toward this, a self-sustained instrument has been designed and tested with all the necessary compensation and calibration for the entire reactor life. This paper explains the design of such a sensor and its future scope.

Abstract

Evaluation in machine learning is usually informed by past choices, for example which datasets or metrics to use. This standardization enables the comparison on equal footing using leaderboards, but the evaluation choices become sub-optimal as better alternatives arise. This problem is especially pertinent in natural language generation which requires everimproving suites of datasets, metrics, and human evaluation to make definitive claims. To make following best model evaluation practices easier, we introduce GEMv2. The new version of the Generation, Evaluation, and Metrics Benchmark introduces a modular infrastructure for dataset, model, and metric developers to benefit from each others work. GEMv2 supports 40 documented datasets in 51 languages. Models for all datasets can be evaluated online and our interactive data card creation and rendering tools make it easier to add new datasets to the living benchmark.