極市一直非常關注CVPR,在每年都會進行CVPR相關的論文資源整理,包括論文解讀、代碼、技術直播、分方向盤點、最佳論文匯總等,也得到了許多開發者的支持,在Github上,極市的CVPR盤點已經識訓了5.7K star,在今年,我們也會對CVPR2021進行實時跟進,


Github專案地址:
https://github.com/extreme-assistant/CVPR2021-Paper-Code-Interpretation
以下是我們對本次CVPR2021最新論文的整理:
CVPR2021最新資訊及論文下載(Papers/Codes/Project/PaperReading/Demos/直播分享/論文分享會等)
官網鏈接:http://cvpr2021.thecvf.com
時間:2021年6月19日-6月25日
論文接收公布時間:2021年2月28日
相關問題:
- 如何評價CVPR 2021的論文接收結果?
- CVPR 2021接收結果出爐!錄用1663篇,接受率提升,你的論文中了嗎?(附論文下載)
目錄
1. CVPR2021接受論文/代碼(持續更新)
2. To do list
1.CVPR2021接受論文/代碼(持續更新)
61.Coarse-Fine Networks for Temporal Activity Detection in Videos(用于視頻中的時間活動檢測的粗細網路)
60.Instance Localization for Self-supervised Detection Pretraining(自監督檢測預訓練的實體定位)
paper|code
59.Weakly-supervised Grounded Visual Question Answering using Capsules(使用膠囊進行弱監督的地面視覺問答)
58.FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation(FLAVR:用于快速幀插值的與流無關的視頻表示)
paper|code|project
57.4D Panoptic LiDAR Segmentation(4D全景LiDAR分割)
paper
56.Dogfight: Detecting Drones from Drone Videos(從無人機視頻中檢測無人機)
55.Multiple Instance Active Learning for Object Detection(用于物件檢測的多實體主動學習)
paper|code
54.Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels(重新標記ImageNet:從單標簽到多標簽,從全域標簽到本地標簽)
paper|code
53.Probabilistic Embeddings for Cross-Modal Retrieval(跨模態檢索的概率嵌入)
paper
52.PLOP: Learning without Forgetting for Continual Semantic Segmentation(PLOP:學習而不會忘記連續的語意分割)
paper
51.Rainbow Memory: Continual Learning with a Memory of Diverse Samples(不斷學習與多樣本的記憶)
50.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影像編輯)
48.Rethinking Channel Dimensions for Efficient Model Design(重新考慮通道尺寸以進行有效的模型設計)
paper|code
46.Reconsidering Representation Alignment for Multi-view Clustering(重新考慮多視圖聚類的表示對齊方式)
45.Self-supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Map(道路動力學和成本圖的自監督式多步同時預測)
44.IIRC: Incremental Implicitly-Refined Classification(增量式隱式定義的分類)
paper|project
43.Fair Attribute Classification through Latent Space De-biasing(通過潛在空間去偏的公平屬性分類)
paper|code|project
42.Information-Theoretic Segmentation by Inpainting Error Maximization(修復誤差最大化的資訊理論分割)
paper
41.Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking(多目標跟蹤的概率小波計分和修復)
paper
40.Few-shot Open-set Recognition by Transformation Consistency(轉換一致性很少的開放集識別)
39.Meta Batch-Instance Normalization for Generalizable Person Re-Identification(通用批處理人員重新標識的元批實體規范化)
paper
37.UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pretraining(UC2:通用跨語言跨模態視覺和語言預培訓)
36.Less is More: CLIPBERT for Video-and-Language Learning via Sparse Sampling(T通過稀疏采樣進行視頻和語言學習)
paper|code
35.3D Graph Anatomy Geometry-Integrated Network for Pancreatic Mass Segmentation, Diagnosis, and Quantitative Patient Management(用于胰腺腫塊分割,診斷和定量患者管理的3D圖形解剖學幾何集成網路)
34.Deep Lesion Tracker: Monitoring Lesions in 4D Longitudinal Imaging Studies(深部病變追蹤器:在4D縱向成像研究中監控病變)
paper
33.Automatic Vertebra Localization and Identification in CT by Spine Rectification and Anatomically-constrained Optimization(通過脊柱矯正和解剖學約束優化在CT中自動進行椎骨定位和識別)
paper
31.3D CNNs with Adaptive Temporal Feature Resolutions(具有自適應時間特征解析度的3D CNN)
paper
30.KeepAugment: A Simple Information-Preserving Data Augmentation(一種簡單的保存資訊的資料擴充)
paper
29.AttentiveNAS: Improving Neural Architecture Search via Attentive(通過注意力改善神經架構搜索)
paper
28.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)
paper
27.D-NeRF: Neural Radiance Fields for Dynamic Scenes(D-NeRF:動態場景的神經輻射場)
project
26.Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation(樣式編碼:用于影像到影像翻譯的StyleGAN編碼器)
project
25.A 3D GAN for Improved Large-pose Facial Recognition(用于改善大姿勢面部識別的3D GAN)
paper
24.Rotation Equivariant Siamese Networks for Tracking(旋轉等距連體網路進行跟蹤)
paper
23.Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning(探索少量學習的不變表示形式和等變表示形式的互補強度)
22.Open-world object detection(開放世界中的目標檢測)
code
21.Multi-Stage Progressive Image Restoration(多階段漸進式影像復原)
paper|code
20.Weakly Supervised Learning of Rigid 3D Scene Flow(剛性3D場景流的弱監督學習)
paper|code|project
19.PREDATOR: Registration of 3D Point Clouds with Low Overlap(預測器:低重疊的3D點云的注冊)
paper|code|project
18.Sequential Graph Convolutional Network for Active Learning(主動學習的順序圖卷積網路)
paper
17.Multiresolution Knowledge Distillation for Anomaly Detection(用于例外檢測的多解析度知識蒸餾)
paper
16.Positive-Unlabeled Data Purification in the Wild for Object Detection(野外檢測物件的陽性無標簽資料提純)
15.Data-Free Knowledge Distillation For Image Super-Resolution(DAFL演算法的SR版本)
14.Manifold Regularized Dynamic Network Pruning(動態剪枝的程序中考慮樣本復雜度與網路復雜度的約束)
13.Distilling Object Detectors via Decoupled Features(前景背景分離的蒸餾技術)
12.Inverting the Inherence of Convolution for Visual Recognition(顛倒卷積的固有性以進行視覺識別)
11.Representative Batch Normalization with Feature Calibration(具有特征校準功能的代表性批量歸一化)
10.PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation(語意流經點以進行航空影像分割)
9.Learning the Superpixel in a Non-iterative and Lifelong Manner(以非迭代和終身的方式學習超像素)
8.RepVGG: Making VGG-style ConvNets Great Again
paper|code
解讀:RepVGG:極簡架構,SOTA性能,讓VGG式模型再次偉大
7.Transformer Interpretability Beyond Attention Visualization(注意力可視化之外的Transformer可解釋性)
paper|code
6.UP-DETR: Unsupervised Pre-training for Object Detection with Transformers
paper
解讀:無監督預訓練檢測器
5.Pre-Trained Image Processing Transformer(底層視覺預訓練模型)
paper
4.ReNAS: Relativistic Evaluation of Neural Architecture Search(NAS predictor當中ranking loss的重要性)
paper
3.AdderSR: Towards Energy Efficient Image Super-Resolution(將加法網路應用到影像超解析度中)
paper|code
解讀:華為開源加法神經網路
2.Learning Student Networks in the Wild(一種不需要原始訓練資料的模型壓縮和加速技術)
paper|code
解讀:華為諾亞方舟實驗室提出無需資料網路壓縮技術
1.HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens(降低NAS的成本)
paper
2.To do list
- CVPR2021論文解讀
- CVPR2021 Oral
- CVPR2021論文分享
轉載請註明出處,本文鏈接:https://www.uj5u.com/ruanti/265443.html
標籤:其他
上一篇:Ubuntu18.04+python3.6+pcl-1.8+opencv3+realsense D415環境搭建
