본 포스팅에서는 End-to-End Object Detection with Transformers (ECCV 2020) 논문을 간단히 리뷰하였습니다. 그림과 설명은 논문자료를 참고하였습니다. 원문 링크: https://arxiv.org/abs/2005.12872 End-to-End Object Detection with TransformersWe present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components like ..

본 포스팅에서는 ESCAPE: Encoding Super-keypoints for Category-Agnostic Pose Estimation (CVPR 2024) 논문을 간단히 리뷰하였습니다. 그림과 설명은 논문자료를 참고하였습니다. 원문 링크:https://openaccess.thecvf.com/content/CVPR2024/html/Nguyen_ESCAPE_Encoding_Super-keypoints_for_Category-Agnostic_Pose_Estimation_CVPR_2024_paper.html CVPR 2024 Open Access RepositoryESCAPE: Encoding Super-keypoints for Category-Agnostic Pose Estimation Khoi Du..

본 포스팅에서는 Open-World Semantic Segmentation Including Class Similarity (CVPR 2024) 논문을 간단히 리뷰하였습니다. 그림과 설명은 논문자료를 참고하였습니다. 원문 링크: https://arxiv.org/abs/2403.07532 Open-World Semantic Segmentation Including Class SimilarityInterpreting camera data is key for autonomously acting systems, such as autonomous vehicles. Vision systems that operate in real-world environments must be able to understand th..

본 포스팅에서는 SF-Net: Single-Frame Supervision for Temporal Action Localization(ECCV 2020) 논문을 간단히 리뷰하였습니다. 그림과 설명은 논문자료를 참고하였습니다. 원문 링크: https://arxiv.org/abs/2003.06845 SF-Net: Single-Frame Supervision for Temporal Action Localization In this paper, we study an intermediate form of supervision, i.e., single-frame supervision, for temporal action localization (TAL). To obtain the single-frame superv..

본 포스팅에서는 SRFlow-DA: Super-Resolution Using Normalizing Flowwith Deep Convolutional Block (CVPRW 2021) 논문을 간단히 리뷰하였습니다. 그림과 설명은 논문자료를 참고하였습니다. 원문 링크:https://ieeexplore.ieee.org/document/9523202 SRFlow-DA: Super-Resolution Using Normalizing Flow with Deep Convolutional BlockMultiple high-resolution (HR) images can be generated from a single low-resolution (LR) image, as super-resolution (SR) is an..

본 포스팅에서는 Deep Residual Learning for Image Recognition (CVPR 2015) 논문을 간단히 리뷰하였습니다. 모든 그림과 설명은 논문과 Stanford University CS231n Spring 2017 자료를 참고하였습니다. 원문 링크 : https://arxiv.org/abs/1512.03385 Deep Residual Learning for Image Recognition Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than t..