Research Article Hub

Explore the latest peer-reviewed research with AI-generated summaries, key findings, and insights for easy understanding. All content is legally sourced from academic metadata with links to original papers.

2,222Articles
5Disciplines
3Live Sources
🔍
🤖 Artificial Intelligence OpenAlex

Protein complex prediction with AlphaFold-Multimer

📅 Oct 2021 👤 Richard Evans, M. E. O’Neill, Alexander Pritzel et al. 📊 4,037 citations

While the vast majority of well-structured single protein chains can now be predicted to high accuracy due to the recent AlphaFold model, the prediction of multi-chain protein complexes remains a chal...

🤖 Artificial Intelligence OpenAlex

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

📅 Oct 2021 👤 Ze Liu, Yutong Lin, Yue Cao et al. 📊 29,920 citations

This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. The hierarchical design and the shifted window approach al...

🤖 Artificial Intelligence OpenAlex

Emerging Properties in Self-Supervised Vision Transformers

📅 Oct 2021 👤 Mathilde Caron, Hugo Touvron, Ishan Misra et al. 📊 4,980 citations

In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets). We implement our findings into...

🤖 Artificial Intelligence OpenAlex

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions

📅 Oct 2021 👤 Wenhai Wang, Enze Xie, Xiang Li et al. 📊 4,679 citations

Although convolutional neural networks (CNNs) have achieved great success in computer vision, this work investigates a simpler, convolution-free backbone network use-fid for many dense prediction task...

🤖 Artificial Intelligence OpenAlex

SwinIR: Image Restoration Using Swin Transformer

📅 Oct 2021 👤 Jingyun Liang, Jiezhang Cao, Guolei Sun et al. 📊 4,178 citations

Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). We conduct experiments o...

🤖 Artificial Intelligence OpenAlex

Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

📅 Oct 2021 👤 Li Yuan, Yunpeng Chen, Tao Wang et al. 📊 2,247 citations

Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. For example, T2T-ViT with comp...

🤖 Artificial Intelligence OpenAlex

Point Transformer

📅 Oct 2021 👤 Hengshuang Zhao, Li Jiang, Jiaya Jia et al. 📊 2,161 citations

Self-attention networks have revolutionized natural language processing and are making impressive strides in image analysis tasks such as image classification and object detection. Our Point Transform...

🤖 Artificial Intelligence OpenAlex

TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captu...

📅 Oct 2021 👤 Xingkui Zhu, Shuchang Lyu, Xu Wang et al. 📊 2,045 citations

Object detection on drone-captured scenarios is a recent popular task. On VisDrone Challenge 2021, TPH-YOLOv5 wins 5 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/...

🤖 Artificial Intelligence OpenAlex

CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification

📅 Oct 2021 👤 Chun-Fu Richard Chen, Quanfu Fan, Rameswar Panda 📊 1,938 citations

The recently developed vision transformer (ViT) has achieved promising results on image classification compared to convolutional neural networks. For example, on the ImageNet1K dataset, with some arch...

🤖 Artificial Intelligence OpenAlex

Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data

📅 Oct 2021 👤 Xintao Wang, Liangbin Xie, Chao Dong et al. 📊 1,448 citations

Though many attempts have been made in blind super-resolution to restore low-resolution images with unknown and complex degradations, they are still far from addressing general real-world degraded ima...

🤖 Artificial Intelligence OpenAlex

An Empirical Study of Training Self-Supervised Vision Transformers

📅 Oct 2021 👤 Xinlei Chen, Saining Xie, Kaiming He 📊 1,446 citations

This paper does not describe a novel method. We discuss the currently positive evidence as well as challenges and open questions.

🤖 Artificial Intelligence OpenAlex

The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization

📅 Oct 2021 👤 Dan Hendrycks, Steven Basart, Norman Mu et al. 📊 1,037 citations

We introduce four new real-world distribution shift datasets consisting of changes in image style, image blurriness, geographic location, camera operation, and more. Overall we find that some methods...

🤖 Artificial Intelligence OpenAlex

Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition

📅 Oct 2021 👤 Yuxin Chen, Ziqi Zhang, Chunfeng Yuan et al. 📊 911 citations

Graph convolutional networks (GCNs) have been widely used and achieved remarkable results in skeleton-based action recognition. Combining CTR-GC with temporal modeling modules, we develop a powerful g...

🤖 Artificial Intelligence OpenAlex

The physics of higher-order interactions in complex systems

📅 Oct 2021 👤 Federico Battiston, Enrico Amico, Alain Barrat et al. 📊 878 citations

This research explores physics of higher-order interactions in complex systems, contributing new insights to the field of Artificial Intelligence.

🤖 Artificial Intelligence OpenAlex

DRÆM – A discriminatively trained reconstruction embedding for surface anomaly detection

📅 Oct 2021 👤 Vitjan Zavrtanik, Matej Kristan, Danijel Skočaj 📊 862 citations

Visual surface anomaly detection aims to detect local image regions that significantly deviate from normal appearance. On the challenging MVTec anomaly detection dataset, DRÆM outperforms the current...

🤖 Artificial Intelligence OpenAlex

PlenOctrees for Real-time Rendering of Neural Radiance Fields

📅 Oct 2021 👤 Alex Yu, Ruilong Li, Matthew Tancik et al. 📊 798 citations

We introduce a method to render Neural Radiance Fields (NeRFs) in real time using PlenOctrees, an octree-based 3D representation which supports view-dependent effects. Our real-time neural rendering a...

🤖 Artificial Intelligence OpenAlex

Addressing bias in big data and AI for health care: A call for open science

📅 Oct 2021 👤 Natalia Norori, Qiyang Hu, Florence M. Aellen et al. 📊 790 citations

Artificial intelligence (AI) has an astonishing potential in assisting clinical decision making and revolutionizing the field of health care. If the training data is misrepresentative of the populatio...

🤖 Artificial Intelligence OpenAlex

Conformer: Local Features Coupling Global Representations for Visual Recognition

📅 Oct 2021 👤 Zhiliang Peng, Wei Huang, Shanzhi Gu et al. 📊 781 citations

Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations. On MSCOCO, it outperforms ResNe...

🤖 Artificial Intelligence OpenAlex

MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo

📅 Oct 2021 👤 Anpei Chen, Zexiang Xu, Fuqiang Zhao et al. 📊 727 citations

We present MVSNeRF, a novel neural rendering approach that can efficiently reconstruct neural radiance fields for view synthesis. Our approach can generalize across scenes (even indoor scenes, complet...

🤖 Artificial Intelligence OpenAlex

Rethinking Coarse-to-Fine Approach in Single Image Deblurring

📅 Oct 2021 👤 Sung‐Jin Cho, Seo-Won Ji, Jun-Pyo Hong et al. 📊 720 citations

Coarse-to-fine strategies have been extensively used for the architecture design of single image deblurring networks. Extensive experiments on the GoPro and RealBlur datasets demonstrate that the prop...

📜 Legal Notice: All articles are sourced via open-access academic APIs (OpenAlex, arXiv, PubMed). Only metadata (titles, authors, publication dates, DOIs) and AI-generated plain-English summaries are displayed — never full copyrighted article text. Original abstracts are not copied or reproduced. Each article links back to the original source for full access.