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

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

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.

Abstract

Non-Fungible Tokens (NFTs) are a relatively unexplored class of assets. Designing strategies to forecast NFT trends is an intricate task due to its extremely volatile nature. The market is largely driven by public sentiment and "hype", which in turn has a high correlation with conversations taking place on social media platforms like Twitter. Prior work done for modelling stock market data does not take into account the extent of impact certain highly influential tweets and their authors can have on the market. Building on these limitations and the nature of the NFT market, we propose a novel reachaware temporal learning approach to make predictions for forecasting future trends in the NFT market. We perform experiments on a new dataset consisting of over 1.3 million tweets and 180 thousand NFT transactions spanning over 15 NFT collections curated by us. Our model (TA-NFT) outperforms other state-ofthe-art methods by an average of 36%. Through extensive quantitative and ablative analysis, we demonstrate the ability of our approach as a practical method for predicting NFT trends.

Abstract

Generating domain-specific content such as legal clauses based on minimal user-provided information can be of significant benefit in automating legal contract generation. In this paper, we propose a controllable graph-based mechanism that can generate legal clauses using only the topic or type of the legal clauses. Our pipeline consists of two stages involving a graph-based planner followed by a clause generator. The planner outlines the content of a legal clause as a sequence of keywords in the order of generic to more specific clause information based on the input topic using a controllable graph-based mechanism. The generation stage takes in a given plan and generates a clause. The pipeline consists of a graph-based planner followed by text generation. We illustrate the effectiveness of our proposed two-stage approach on a broad set of clause topics in contracts.