분류 전체보기 (83) 썸네일형 리스트형 OrdinalCLIP : Learning Rank Prompts for Language-Guided Ordinal Regression https://arxiv.org/abs/2206.02338 OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal RegressionThis paper presents a language-powered paradigm for ordinal regression. Existing methods usually treat each rank as a category and employ a set of weights to learn these concepts. These methods are easy to overfit and usually attain unsatisfactory performaarxiv.org text와 image를 align시키는 cont.. Medical SAM Adapter : Adapting Segment Anything Model for Medical Image Segmentation https://arxiv.org/abs/2304.12620 Medical SAM Adapter: Adapting Segment Anything Model for Medical Image SegmentationThe Segment Anything Model (SAM) has recently gained popularity in the field of image segmentation due to its impressive capabilities in various segmentation tasks and its prompt-based interface. However, recent studies and individual experiments have showarxiv.org Abstract Segment.. Matcher : Segment Anything With One Shot Using All-Purpose Feature Matching https://openreview.net/forum?id=yzRXdhk2he Matcher: Segment Anything with One Shot Using All-Purpose Feature...Powered by large-scale pre-training, vision foundation models exhibit significant potential in open-world image understanding. However, unlike large language models that excel at directly tackling...openreview.net Abstract 대규모의 사전학습 덕분에 vision foundation model은 open-world image unders.. Sparse R-CNN : An End-to-End Framework for Object Detection 논문 정리 https://arxiv.org/abs/2011.12450 Sparse R-CNN: End-to-End Object Detection with Learnable ProposalsWe present Sparse R-CNN, a purely sparse method for object detection in images. Existing works on object detection heavily rely on dense object candidates, such as $k$ anchor boxes pre-defined on all grids of image feature map of size $H\times W$. In our marxiv.org Abstractobject detection에 대해 .. Say As You Wish : Fine-grained Control of Image Caption Generation with Abstract Scene Graphs Abstract 사람은 원하는 만큼 image contents를 거친 수준부터 정밀한 수준까지 묘사할 수 있습니다. 그러나 대부분의 image captioning model들은 사용자의 의도에 따른 다양한 설명들을 생성할 수 없는 'intention-agnostic'입니다. 논문에선 fine-grained level에서 사용자의 의도를 표현하고 어떤 description을 얼마나 생성할지 조절하는 'Abstract Scene Graph(ASG)'를 제안했습니다. ASG는 구체적인 semantic label없이 image에 근거를 둔 3가지 타입의 abstract node로 구성되어 있는 directed graph입니다. 그렇기 때문에 직접적으로도 자동적으로도 얻기 쉽습니다.ASG를 이용해, novel A.. Scene Graph Generation by Iterative Message Passing 정리 https://arxiv.org/abs/1701.02426 Scene Graph Generation by Iterative Message PassingUnderstanding a visual scene goes beyond recognizing individual objects in isolation. Relationships between objects also constitute rich semantic information about the scene. In this work, we explicitly model the objects and their relationships using scenearxiv.org 이 모델은 standard RNN을 이용해 scene graph inference 문.. PointNet : Deep Learning on Point Sets for 3D Classification and Segmentation 정리 https://openaccess.thecvf.com/content_cvpr_2017/html/Qi_PointNet_Deep_Learning_CVPR_2017_paper.html CVPR 2017 Open Access RepositoryCharles R. Qi, Hao Su, Kaichun Mo, Leonidas J. Guibas; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 652-660 Point cloud is an important type of geometric data structure. Due to its irregular format, most ropenaccess.. NeRF : Representing Scenes as Neural Radiance Fields for View Synthesis 설명 https://arxiv.org/abs/2003.08934 NeRF: Representing Scenes as Neural Radiance Fields for View SynthesisWe present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. Our algorithm represents a scene using a fully-conarxiv.org 이번에 공부할 논문은 NeRF입니다. ECCV 20.. 이전 1 2 3 4 5 ··· 11 다음
