今年的CVPR也陸續被大家熟知，錄取的paper也公布出來，大家有興趣的可以深入了解自己感興趣的領域。作為計算機視覺領域三大頂會之一，CVPR2021目前已公布了所有接收論文ID，一共有1663篇論文被接收，接收率為23.7%，雖然接受率相比去年有所上升，但競爭也是非常激烈。

致力于計算機視覺和模式識別包括顏色檢測、跟蹤、運動、物體識別、音響和目標檢測。

圖像目標檢測(Image Object Detection)

Instance Localization for Self-supervised Detection Pretraining

Multiple Instance Active Learning for Object Detection(用于對象檢測的多實例主動學習)

Open-world object detection(開放世界中的目標檢測)

Positive-Unlabeled Data Purification in the Wild for Object Detection(野外檢測對象的陽性無標簽數據提純)

UP-DETR: Unsupervised Pre-training for Object Detection with Transformers

Image-to-image Translation via Hierarchical Style Disentanglement Xinyang Li, Shengchuan Zhang, Jie Hu, Liujuan Cao, Xiaopeng Hong, Xudong Mao, Feiyue Huang, Yongjian Wu, Rongrong Ji

代碼鏈接：?https://github.com/imlixinyang/HiSD

FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation

論文鏈接：https://arxiv.org/pdf/2012.08512.pdf

代碼鏈接：https://tarun005.github.io/FLAVR/Code?https://tarun005.github.io/FLAVR/

Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition Stephen Hausler, Sourav Garg, Ming Xu, Michael Milford, Tobias Fischer

論文鏈接：https://arxiv.org/abs/2103.01486

Depth from Camera Motion and Object Detection Brent A. Griffin, Jason J. Corso

論文鏈接：https://arxiv.org/abs/2103.01468

UP-DETR: Unsupervised Pre-training for Object Detection with Transformers

論文鏈接：https://arxiv.org/pdf/2011.09094.pdf

Multi-Stage Progressive Image Restoration

論文鏈接：https://arxiv.org/abs/2102.02808

代碼鏈接：https://github.com/swz30/MPRNet

Weakly Supervised Learning of Rigid 3D Scene Flow

論文鏈接：https://arxiv.org/pdf/2102.08945.pdf

論文鏈接：https://arxiv.org/pdf/2102.08945.pdf

代碼鏈接：https://3dsceneflow.github.io/

Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning Mamshad Nayeem Rizve, Salman Khan, Fahad Shahbaz Khan, Mubarak Shah

論文鏈接：https://arxiv.org/abs/2103.01315

Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels

論文鏈接：https://arxiv.org/abs/2101.05022

代碼鏈接：https://github.com/naver-ai/relabel_imagenet

Rethinking Channel Dimensions for Efficient Model Design

論文鏈接：https://arxiv.org/abs/2007.00992

代碼鏈接：https://github.com/clovaai/rexnet

Coarse-Fine Networks for Temporal Activity Detection in Videos Kumara Kahatapitiya, Michael S. Ryoo

論文鏈接：https://arxiv.org/abs/2103.01302

A Deep Emulator for Secondary Motion of 3D Characters Mianlun Zheng, Yi Zhou, Duygu Ceylan, Jernej Barbic

論文鏈接：https://arxiv.org/abs/2103.01261

Fair Attribute Classification through Latent Space De-biasing

論文鏈接：https://arxiv.org/abs/2012.01469

代碼鏈接：https://github.com/princetonvisualai/gan-debiasing

https://princetonvisualai.github.io/gan-debiasing/

Auto-Exposure Fusion for Single-Image Shadow Removal Lan Fu, Changqing Zhou, Qing Guo, Felix Juefei-Xu, Hongkai Yu, Wei Feng, Yang Liu, Song Wang

論文鏈接：https://arxiv.org/abs/2103.01255

Less is More: CLIPBERT for Video-and-Language Learning via Sparse Sampling

論文鏈接：https://arxiv.org/pdf/2102.06183.pdf

代碼鏈接：https://github.com/jayleicn/ClipBERT

MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing Zhengjue Wang, Hao Zhang, Ziheng Cheng, Bo Chen, Xin Yuan

論文鏈接：https://arxiv.org/abs/2103.01786

GAN/生成式/對抗式(GAN/Generative/Adversarial)

Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing(利用GAN中潛在的空間維度進行實時圖像編輯)

Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs(Hijack-GAN：意外使用經過預訓練的黑匣子GAN)

Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation(樣式編碼：用于圖像到圖像翻譯的StyleGAN編碼器)

A 3D GAN for Improved Large-pose Facial Recognition(用于改善大姿勢面部識別的3D GAN)

AttentiveNAS: Improving Neural Architecture Search via Attentive

論文鏈接：https://arxiv.org/pdf/2011.09011.pdf

Diffusion Probabilistic Models for 3D Point Cloud Generation Shitong Luo, Wei Hu

論文鏈接：https://arxiv.org/abs/2103.01458

There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge Francisco Rivera Valverde, Juana Valeria Hurtado, Abhinav Valada

http://rl.uni-freiburg.de/research/multimodal-distill

Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation

論文鏈接：https://arxiv.org/abs/2008.00951

代碼鏈接：https://github.com/eladrich/pixel2style2pixel

https://eladrich.github.io/pixel2style2pixel/

Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational Graph Xin Ye, Yezhou Yang

論文鏈接：https://arxiv.org/abs/2103.01350

RepVGG: Making VGG-style ConvNets Great Again

論文鏈接：https://arxiv.org/abs/2101.03697

代碼鏈接：https://github.com/megvii-model/RepVGG

Transformer Interpretability Beyond Attention Visualization

論文鏈接：https://arxiv.org/pdf/2012.09838.pdf

代碼鏈接：https://github.com/hila-chefer/Transformer-Explainability

PREDATOR: Registration of 3D Point Clouds with Low Overlap

論文鏈接：https://arxiv.org/pdf/2011.13005.pdf

代碼鏈接：https://github.com/ShengyuH/OverlapPredator

https://overlappredator.github.io/

總結

以上是生活随笔為你收集整理的计算机视觉三大会议论文,计算机视觉顶级会议CVPR2021 最新出炉的最佳paper，陆续更新中...（附论文地址）...的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。