|
極市導(dǎo)讀 ICCV2021結(jié)果出爐！你的論文中了嗎？ >>加入極市CV技術(shù)交流群，走在計算機視覺的最前沿  神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)設(shè)計(Neural Network Structure Design)Transformer[3] Rethinking Spatial Dimensions of Vision Transformers [2] Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers(Oral) [1] Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions(Oral) 檢測圖像目標檢測(2D Object Detection)[5] Active Learning for Deep Object Detection via Probabilistic Modeling [4] Detecting Invisible People [3] Conditional Variational Capsule Network for Open Set Recognition [2] MDETR : Modulated Detection for End-to-End Multi-Modal Understanding(Oral) [1] DetCo: Unsupervised Contrastive Learning for Object Detection 分割(Segmentation)圖像分割(Image Segmentation)[2] Labels4Free: Unsupervised Segmentation using StyleGAN [1] Mining Latent Classes for Few-shot Segmentation(Oral) 實例分割(Instance Segmentation)[2] Crossover Learning for Fast Online Video Instance Segmentation [1] Instances as Queries 語義分割(Semantic Segmentation)[1] Calibrated Adversarial Refinement for Stochastic Semantic Segmentation GAN/生成式/對抗式(GAN/Generative/Adversarial)[2] Labels4Free: Unsupervised Segmentation using StyleGAN [1] EigenGAN: Layer-Wise Eigen-Learning for GANs 圖像處理(Image Processing)[1] Equivariant Imaging: Learning Beyond the Range Space(Oral) 超分辨率(Super Resolution)[1] Learning for Scale-Arbitrary Super-Resolution from Scale-Specific Networks 風(fēng)格遷移(Style Transfer)[1] Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts(字體生成) 估計(Estimation)姿態(tài)估計(Human Pose Estimation)[1] HuMoR: 3D Human Motion Model for Robust Pose Estimation(Oral) 圖像&視頻檢索/理解(Image&Video Retrieval/Video Understanding)行人重識別/檢測(Re-Identification/Detection)[1] TransReID: Transformer-based Object Re-Identification 視覺定位(Visual Localization)[2] TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization [1] Boundary-sensitive Pre-training for Temporal Localization in Videos 圖像匹配(Image Matching)[1] COTR: Correspondence Transformer for Matching Across Images 三維視覺(3D Vision)[1] MVTN: Multi-View Transformation Network for 3D Shape Recognition 目標跟蹤(Object Tracking)[1] Detecting Invisible People 遙感圖像(Remote Sensing Image)[1] Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data 場景圖(Scene Graph場景圖生成(Scene Graph Generation)[1] Unconstrained Scene Generation with Locally Conditioned Radiance Fields 場景圖預(yù)測(Scene Graph Prediction)[1] Generative Compositional Augmentations for Scene Graph Prediction 數(shù)據(jù)處理(Data Processing)數(shù)據(jù)增廣(Data Augmentation)[1] MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks 異常檢測(Anomaly Detection)[1] Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning 表征學(xué)習(xí)(Representation Learning)[1] In-Place Scene Labelling and Understanding with Implicit Scene Representation(Oral) 遷移學(xué)習(xí)(Transfer Learning)[2] Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data [1] Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling 度量學(xué)習(xí)(Metric Learning)[1] Learning with Memory-based Virtual Classes for Deep Metric Learning 增量學(xué)習(xí)(Incremental Learning)[1] Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning 對比學(xué)習(xí)(Contrastive Learning)[1] CoMatch: Semi-supervised Learning with Contrastive Graph Regularization 主動學(xué)習(xí)(Active Learning)[1] Active Learning for Deep Object Detection via Probabilistic Modeling 視覺推理/視覺問答(Visual Reasoning/VQA)[2] On the hidden treasure of dialog in video question answering [1] Just Ask: Learning to Answer Questions from Millions of Narrated Videos(Oral) 數(shù)據(jù)集(Dataset)[1] 4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface(4D重建) 其他分類Pathdreamer: A World Model for Indoor Navigation(視覺導(dǎo)航) IPOKE: POKING A STILL IMAGE FOR CONTROLLED STOCHASTIC VIDEO SYNTHESIS Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs |
|
|
