Top Research Papers on Computer Vision

NOTE: THIS IS A DRAFT DOCUMENT

Current applications such as biodiversity assessment, management and protection, infrastructure inspection and AUVs navigation, amongst others are reviewed, and the current trends in the field are delve upon and the challenges and opportunities are examined.

This image understanding will be seen because the disentangling of symbolic info from image knowledge mistreatment models created with the help of pure mathematics, physics, statistics, and learning theory is seen.

A comprehensive review of Metaverse concepts in computer vision has been made and it is suggested that this technology is a rapidly developing new technology today and needs to be examined from a computer vision and general perspective.

An in-depth review of the vision-based transformer, covering transformers on image object detection, multiple object tracking, action classification, and visual segmentation, and a comprehensive experimental comparison to validate the strength of transformer-based methods.

This article presents a comprehensive review of state-of-the-art vision transformers that have been explored in histopathological image analysis for classification, segmentation, and survival risk regression applications and discusses key challenges revolving around the use of vision transformers.

This article investigates the intersection of Vision Transformers and Medical images and proffered an overview of various ViTs based frameworks that are being used by different researchers in order to decipher the obstacles in Medical Computer Vision.

Imagine a world where machines can see and understand the world the way humans do. Rapid progress in artificial intelligence has led to smartphones that recognize faces, cars that detect pedestrians, and algorithms that suggest diagnoses from clinical images, among many other applications. The success of computer vision is founded on a deep understanding of the neural circuits in the brain responsible for visual processing. This book introduces the neuroscientific study of neuronal computations in the visual cortex alongside of the psychological understanding of visual cognition and the burgeo...

The vision and challenges for satellite computing are presented based on a brief survey of the very recent literature in the “NewSpace” era and a case study of an open research platform on real satellites named Tiansuan constellation is given.

This letter presents a summary of discussions as part of Distributed/Decentralized Hybrid Workshop on Sustainability for Transportation and Logistics (DHW-STL) dedicating to the development of sustainable interaction systems.

This survey first briefly introduces the theory of optimal transport in layman's terms as well as most common numerical techniques to solve it, and presents applications of these numerical technique to solve various computer graphics and vision related problems.

A comprehensive review of the state of the art of computer vision techniques and their applications in manufacturing industries, including the most common methods, including feature detection, recognition, segmentation, and three-dimensional modeling.

This paper presents, to the best of the authors' knowledge, the first review discussing recent advancements of FL in CV applications, comparing them to conventional centralized training paradigms and proposes a taxonomy of FL techniques in CV, outlining their applications and security threats.

A Spatiotemporal Pyramid Network is proposed to dynamically learn different spatiotemporal cues for video deblurring and a Spatiotemporal Pyramid Generative Adversarial Network (SPGAN) is proposed, which conducts adversarial discrimination in the gradient space.

It was found that multi-scale training helps NNs to deal with large blurs, and RNNs outperform CNNs and GANs using a perceptual loss function produce artifacts.

How computer vision is applied to raw sensor data in biosensors and its advantages to biosensing applications is outlined and directions for future work are suggested, underscoring the significant impact of computer vision on advancing biosensing technologies and their applications.

Online versus On-site e-Assessment in Medical Education: are we ready for the change

The problem formulation and quantum computing-based solutions to computer vision tasks that appeared in the major AI/ML conferences in the past years are summarized, providing beneficial insights into the current state of quantum computing usage for computer vision.

This review offers an extensive analysis of this rapidly evolving field by examining four key areas: the development of static or dynamic light-weighted backbone models for the efficient extraction of discriminative deep representations; the specialized network architectures or algorithms tailored for specific computer vision tasks; the techniques employed for compressing deep learning models; and the strategies for deploying efficient deep networks on hardware platforms.

Algorithmic progress in image classification on ImageNet is investigated, informed by work on neural scaling laws, and it is found that compute-augmenting algorithmic advances are made at a pace more than twice as fast as the rate usually associated with Moore's law.

This comprehensive analysis delves into the historical progression and important technological and contemporary advancements of computer vision inside the metaverse, and offers a contemplation on the ethical considerations and duties that arise from the utilization of computer vision in the realm beyond mortal existence.

The application of the deep learning model CNN in image classification, target detection and face recognition is discussed and the classic architecture of CNN will be the classic architecture in this field.

In this paper, an in-depth analysis promotes a broad vision for bringing Serverless to the Edge Computing and issues major challenges for serverless to be met before entering Edge computing.

A retrospective of what was learnt from organizing the workshop Ethical Considerations in Creative applications of Computer Vision at CVPR 2021 conference and, prior to that, a series of workshops on Computer Vision for Fashion, Art and Design at ECCV 2018, ICCV 2019, and CVPR 2020 is offered.

This report describes how to construct a parametric model of the face and body, including articulated hands; a rendering pipeline to generate realistic images of humans based on this body model; an approach for training DNNs to regress a dense set of landmarks covering the entire body; and a method for fitting the body model to dense landmarks predicted from multiple views.

This work introduces a new computer vision foundation model, Florence, to expand the representations from coarse (scene) to fine, from static (images) to dynamic (videos), and from RGB to multiple modalities (caption, depth), by incorporating universal visual-language representations from Web-scale image-text data.

Evaluation point toward the fact that while KAN-based architectures perform in line with the original claims, it may often be important to employ more complex functions on the network edges to retain the performance advantage of KANs on more complex visual data.

Advocating a new, physically grounded, computational paradigm centered on thermodynamics and an emerging understanding of using thermodynamics to solve problems.

AdaMix tackling the trade-off arising in visual classification, whereby the most privacy sensitive data, corresponding to isolated points in representation space, are also critical for high classification accuracy, comes with strong theoretical privacy guarantees and convergence analysis.

A progressive and comprehensive review of visual prompt learning as related to AIGC and some promising research directions concerning prompt learning are provided.

This paper gives a brief survey of existing vision-based interactive systems, and describes the basic algorithms used by some systems built at MERL: visionbased computer games, a television set controlled by hand gestures, and 3-D head tracking.

It is argued that as a community with significant stature, computer vision researchers and practitioners need to work towards an inclusive culture that makes transparent and addresses the real emotional toil of its members.

This article aims to provide a survey of state‐of‐the‐art hardware platforms and software frameworks for parallel implementation of traditional CV applications and some possible future directions are discussed.

This document provides an overview of the latest technologies and explanations of theoretical concepts in computer vision, taking advantage of the multi-region application mechanism and data-rich areas to analyze.

This work discusses the experience teaching a diverse group of ecologists to prototype and evaluate computer vision systems in the context of an intensive hands-on summer workshop.

The various uses of computer vision in sports are covered in this paper, including broadcast enhancement, tracking and detection of players and balls, and the issue of players being blocked in multiplayer sports.

Through a detailed analysis of numerous points such as prediction accuracy, win rates, memory, speed, size, or even learning rate, the substantial role that transformers can play in the game of Go is highlighted.

The purpose of this manuscript is to research and analyze computer vision applicable to improve the control and efficiency of manipulators.

The purpose of this survey is to present the first application of ViTs in CV, which is the first of its kind on ViTs for CVs to the best of the authors' knowledge.

The usefulness and generality of AdaVision are demonstrated in user studies, where users find major bugs in state-of-the-art classification, object detection, and image captioning models, and these user-discovered groups have failure rates 2-3x higher than those surfaced by automatic error clustering methods.

This research paper focused on the evaluation of computer vision used in self-driving vehicles, using convolutional neural networks to enhance the autonomous driving conditions.

This work adopts a reinforcement learning approach and shows its surprising effectiveness across multiple computer vision tasks, such as object detection, panoptic segmentation, colorization and image captioning.

The superb vision of insects—biospeculatively combining optical preprocessing and small brains-offers an intriguing example for the development of lightweight visual systems for unmanned aircraft systems and other applications.

This chapter describes the history of IEEE History of Low-Power Computer Vision Challenge 2015–2020.

This special issue shows the diversity of approaches to connoisseurship throughout history and demonstrates how this similarity, but also the significant differences between human and machine approaches can be understood as productive interventions in the discourse around connoiseurship.

Computer vision is an area of research concerned with assisting computers in seeing that may be loosely classified as a branch of artificial intelligence and machine learning, both of which may include using specific techniques and using general-purpose learning methods.

A perspective of the recent evolution of object recognition in computer vision, a flagship research topic that led to the breakthrough data set of ImageNet and its ensuing algorithm developments is provided.

This article aims to present a systematic mapping review, with three research questions, investigating the current status of educational robotics, focusing on the synergies and interdependencies with the field of computer vision, and suggests that computer vision contributes to educational robotics learning outcomes enhancing the learning procedure.

This work reviews the current status of self-steering agricultural vehicles and presents all basic guidelines for adapting computer vision in autonomous in-field navigation and presents state-of-the-art image processing algorithms for in- field navigation route mapping.

A new benchmark named FACET (FAirness in Computer Vision EvaluaTion), a large, publicly available evaluation set of 32k images for some of the most common vision tasks - image classification, object detection and segmentation, shows that classification, detection, segmentation, and visual grounding models exhibit performance disparities across demographic attributes and intersections of attributes.