Related papers: Generalized Jersey Number Recognition Using Multi-…
In this paper, we present a method of clothes retargeting; generating the potential poses and deformations of a given 3D clothing template model to fit onto a person in a single RGB image. The problem is fundamentally ill-posed as attaining…
Multi-task learning is assumed as a powerful inference method, specifically, where there is a considerable correlation between multiple tasks, predicting them in an unique framework may enhance prediction results. This research challenges…
Adversarial representation learning aims to learn data representations for a target task while removing unwanted sensitive information at the same time. Existing methods learn model parameters iteratively through stochastic gradient…
A wide range of practically important problems is nowadays efficiently solved using artificial neural networks. This gave momentum to intensive development of their optical implementations, among which, the so-called diffractive neural…
The re-ranking approach leverages high-confidence retrieved samples to refine retrieval results, which have been widely adopted as a post-processing tool for image retrieval tasks. However, we notice one main flaw of re-ranking, i.e., high…
Image anomaly detection is a popular research direction, with many methods emerging in recent years due to rapid advancements in computing. The use of artificial intelligence for image anomaly detection has been widely studied. By analyzing…
For many practical computer vision applications, the learned models usually have high performance on the datasets used for training but suffer from significant performance degradation when deployed in new environments, where there are…
Intelligent reflecting surface (IRS) has the potential to enhance sensing performance, due to its capability of reshaping the echo signals. Different from the existing literature, which has commonly focused on IRS beamforming optimization,…
In sports analytics, an understanding of accurate on-field 3D knee joint moments (KJM) could provide an early warning system for athlete workload exposure and knee injury risk. Traditionally, this analysis has relied on captive laboratory…
Automatic Number Plate Recognition System (ANPRS) is a mass surveillance embedded system that recognizes the number plate of the vehicle. This system is generally used for traffic management applications. It should be very efficient in…
Recurrent Neural Networks (RNNs) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high. Therefore, there is a great interest in optimizing the…
In this paper we propose a real-time and robust solution to large-scale multiple rotation averaging. Until recently, Multiple rotation averaging problem had been solved using conventional iterative optimization algorithms. Such methods…
The limited and dynamically varied resources on edge devices motivate us to deploy an optimized deep neural network that can adapt its sub-networks to fit in different resource constraints. However, existing works often build sub-networks…
Handwritten digit recognition remains a fundamental challenge in computer vision, with applications ranging from postal code reading to document digitization. This paper presents an ensemble-based approach that combines Convolutional Neural…
Fine-tuning is widely applied in image classification tasks as a transfer learning approach. It re-uses the knowledge from a source task to learn and obtain a high performance in target tasks. Fine-tuning is able to alleviate the challenge…
Achieving a universally high accuracy in object detection is quite challenging, and the mainstream focus in the industry currently lies on detecting specific classes of objects. However, deploying one or multiple object detection networks…
Existing oriented object detection methods commonly use metric AP$_{50}$ to measure the performance of the model. We argue that AP$_{50}$ is inherently unsuitable for oriented object detection due to its large tolerance in angle deviation.…
How to improve discriminative feature learning is central in classification. Existing works address this problem by explicitly increasing inter-class separability and intra-class similarity, whether by constructing positive and negative…
We address the problem of cross-domain image retrieval, considering the following practical application: given a user photo depicting a clothing image, our goal is to retrieve the same or attribute-similar clothing items from online…
Person re-identification (PRe-ID) is a crucial task in security, surveillance, and retail analysis, which involves identifying an individual across multiple cameras and views. However, it is a challenging task due to changes in…