ICCV 2021 结果出炉！最新200篇ICCV2021论文分方向汇总（更新中）

不久前，计算机视觉三大顶会之一ICCV2021接收结果已经公布，本次ICCV共计 6236 篇有效提交论文，其中有 1617 篇论文被接收，接收率为25.9%。

接收论文ID：https://docs.google.com/spreadsheets/u/1/d/e/2PACX-1vRfaTmsNweuaA0Gjyu58H_Cx56pGwFhcTYII0u1pg0U7MbhlgY0R6Y-BbK3xFhAiwGZ26u3TAtN5MnS/pubhtml

极市平台对此次ICCV2021接收的论文进行了分类汇总，分为检测、分割、估计、跟踪、视觉定位、底层图像处理、图像视频检索、三维视觉等多个方向。所有关于ICCV2021的论文整理都汇总在了我们的Github项目中，该项目目前已收获1300 Star。

这个Github项目将持续更新，项目地址：

目前整理的论文（8月19日更新）：

[12] G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitationpaper

[11] Vector-Decomposed Disentanglement for Domain-Invariant Object Detectionpaper

[10] Oriented R-CNN for Object Detectionpaper | code

[9] Conditional DETR for Fast Training Convergencepaper | code

[8] Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusterspaper | code

[7] GraphFPN: Graph Feature Pyramid Network for Object Detectionpaper解读：复旦&港大提出GraphFPN：用图特征金字塔提升目标检测性能！

[6] SimROD: A Simple Adaptation Method for Robust Object Detectionpaper

[5] Active Learning for Deep Object Detection via Probabilistic Modelingpaper

[4] Detecting Invisible Peoplepaper | project | video

[3] Conditional Variational Capsule Network for Open Set Recognitionpaper | code

[2] MDETR : Modulated Detection for End-to-End Multi-Modal Understanding(Oral)paper | code | project | colab解读：无需检测器提取特征！LeCun团队提出MDETR：实现真正的端到端多模态推理

[1] DetCo: Unsupervised Contrastive Learning for Object Detectionpaper | code解读：性能优于何恺明团队MoCo v2，DetCo：为目标检测定制任务的对比学习

[6] LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detectorpaper

[5] RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detectionpaper

[4] Is Pseudo-Lidar needed for Monocular 3D Object detection?paper

[3] Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weatherpaper | code

[2] Geometry Uncertainty Projection Network for Monocular 3D Object Detectionpaper

[1] Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistencypaper

[2] Specificity-preserving RGB-D Saliency Detectionpaper | code

[1] Disentangled High Quality Salient Object Detectionpaper

[1] TransForensics: Image Forgery Localization with Dense Self-Attentionpaper

[2] DRÆM -- A discriminatively trained reconstruction embedding for surface anomaly detectionpaper

[1] Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detectionpaper

[2] Pixel Difference Networks for Efficient Edge Detectionpaper | code

[1] RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depthpaper

[2] Labels4Free: Unsupervised Segmentation using StyleGANpaper | code | project

[1] Mining Latent Classes for Few-shot Segmentation(Oral)paper | code

[5] Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networkspaper | code

[4] SOTR: Segmenting Objects with Transformerspaper | code

[3] Hierarchical Aggregation for 3D Instance Segmentationpaper | code

[2] Crossover Learning for Fast Online Video Instance Segmentationcode

[1] Instances as Queriespaper | code

[18] Multi-Anchor Active Domain Adaptation for Semantic Segmentation(Oral)paper

[17] Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentationpaper

[16] Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentationpaper

[15] LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation(Oral)paper

[14] Dual Path Learning for Domain Adaptation of Semantic Segmentationpaper | code

[13] Deep Metric Learning for Open World Semantic Segmentationpaper

[12] Complementary Patch for Weakly Supervised Semantic Segmentationpaper

[11] RECALL: Replay-based Continual Learning in Semantic Segmentationpaper

[10] Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformerpaper ｜ code

[9] Learning Meta-class Memory for Few-Shot Semantic Segmentationpaper

[8] Personalized Image Semantic Segmentationpaper

[7] VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentationpaper | code

[6] Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentationpaper

[5] ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation(点云语义分割)paper

[4] Domain Adaptive Video Segmentation via Temporal Consistency Regularization(video semantic segmentation)paper | code

[3] Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation(Oral)paper

[2] Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation(Oral)paper | code

[1] Calibrated Adversarial Refinement for Stochastic Semantic Segmentationpaper | code

[2] Joint Inductive and Transductive Learning for Video Object Segmentationpaper | code

[1] Full-Duplex Strategy for Video Object Segmentationpaper | project

[1] Vision-Language Transformer and Query Generation for Referring Segmentationpaper | code

[1] FaPN: Feature-aligned Pyramid Network for Dense Image Predictionpaper | code

[1] Learning Facial Representations from the Cycle-consistency of Facepaper

[2] SynFace: Face Recognition with Synthetic Datapaper

[1] PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognitionpaper

[5] FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute Learningpaper

[4] Disentangled Lifespan Face Synthesispaper | code

[3] MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement(音频驱动面部动画)paper | video

[2] Focal Frequency Loss for Image Reconstruction and Synthesispaper | code

[1] HeadGAN: One-shot Neural Head Synthesis and Editingpaper

[1] Exploring Temporal Coherence for More General Video Face Forgery Detectionpaper

[3] Differentiable Surface Rendering via Non-Differentiable Samplingpaper

[2] M3D-VTON: A Monocular-to-3D Virtual Try-On Network(3D试穿)paper

[1] Score-Based Point Cloud Denoisingpaper

[10] ME-PCN: Point Completion Conditioned on Mask Emptiness(点云补全)paper

[9] Adaptive Graph Convolution for Point Cloud Analysispaper | code

[8] PICCOLO: Point Cloud-Centric Omnidirectional Localizationpaper

[7] AdaFit: Rethinking Learning-based Normal Estimation on Point Cloudspaper | code

[6] SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformerpaper | code

[5] DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentationpaper

[4] Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matchingpaper | code

[3] (Just) A Spoonful of Refinements Helps the Registration Error Go Down(Oral)paper

[2] Learning with Noisy Labels for Robust Point Cloud Segmentation(点云分割)paper | code

[1] HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registrationpaper | project

[6] Deep Hybrid Self-Prior for Full 3D Mesh Generationpaper | project

[5] PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-rigid Structure-from-Motionpaper

[4] Learning Canonical 3D Object Representation for Fine-Grained Recognitionpaper

[3] ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Descriptionpaper

[2] Discovering 3D Parts from Image Collectionspaper | project

[1] PlaneTR: Structure-Guided Transformers for 3D Plane Recoverypaper | code

[2] Unifying Nonlocal Blocks for Neural Networkspaper

[1] Energy-Based Open-World Uncertainty Modeling for Confidence Calibration(置信度校准)paper

[3] MicroNet: Improving Image Recognition with Extremely Low FLOPspaper | code1 | code2

[2] Learning to Resize Images for Computer Vision Taskspaper

[1] Bias Loss for Mobile Neural Networkspaper解读：超越MobileNet V3 | 详解SkipNet+Bias Loss=轻量化模型新的里程碑

[4] Residual Attention: A Simple but Effective Method for Multi-Label Recognitionpaper

[3] Fast Convergence of DETR with Spatially Modulated Co-Attentionpaper | code

[2] SCOUTER: Slot Attention-based Classifier for Explainable Image Recognitionpaper | code

[1] FcaNet: Frequency Channel Attention Networkspaper | code

[10] An Empirical Study of Training Self-Supervised Vision Transformers(Oral)paper解读：解决训练不稳定性，何恺明团队新作来了！自监督学习+Transformer=MoCoV3

[9] LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inferencepaper | code解读：FaceBook提出LeViT，0.077ms的单图处理速度却拥有ResNet50的精度

[8] Emerging Properties in Self-Supervised Vision Transformerspaper | code解读：当Transformer遇见自监督学习！Facebook重磅开源DINO

[7] Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetpaper | code解读：ResNet被全面超越了，是Transformer干的：依图科技开源“可大可小”T2T-ViT，轻量版优于MobileNet

[6] Vision Transformer with Progressive Samplingpaper | code

[5] Rethinking and Improving Relative Position Encoding for Vision Transformerpaper | code解读：Vision Transformer中的相对位置编码

[4] AutoFormer: Searching Transformers for Visual Recognitionpaper | code

[3] Rethinking Spatial Dimensions of Vision Transformerspaper | code

[2] Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers(Oral)paper | code

[1] Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions(Oral)paper | code解读：金字塔视觉Transformer(PVT)：用于密集预测的多功能backbone

[3] BN-NAS: Neural Architecture Search with Batch Normalizationpaper

[2] NASOA: Towards Faster Task-oriented Online Fine-tuning with a Zoo of Modelspaper

[1] AutoFormer: Searching Transformers for Visual Recognitionpaper | code

[3] Rank & Sort Loss for Object Detection and Instance Segmentation(Oral)paper | code解读：拒绝调参，显著提点！检测分割任务的新损失函数RS Loss开源

[2] Focal Frequency Loss for Image Reconstruction and Synthesispaper | code

[1] Orthogonal Projection Losspaper | code

[1] Finding Representative Interpretations on Convolutional Neural Networkspaper

[3] MultiTask-CenterNet (MCN): Efficient and Diverse Multitask Learning using an Anchor Free Approach(多任务学习)paper

[2] Impact of Aliasing on Generalization in Deep Convolutional Networkspaper

[1] Learning Compatible Embeddingspaper | code

[1] Learning with Noisy Labels via Sparse Regularizationpaper | code

[1] ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot(Oral)paper | code

[2] Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learningpaper

[1] CODEs: Chamfer Out-of-Distribution Examples against Overconfidence Issuepaper

[4] G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitationpaper

[3] Online Multi-Granularity Distillation for GAN Compressionpaper | code

[2] Distilling Holistic Knowledge with Graph Neural Networkspaper | code

[1] AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric Learningpaper | code

[2] Distance-aware Quantizationpaper

[1] Generalizable Mixed-Precision Quantization via Attribution Rank Preservationpaper | code

[7] Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates(手势生成)paper | code

[6] Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generationpaper | code

[5] ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models(Oral)paper

[4] Toward Spatially Unbiased Generative Modelspaper

[3] A Light Stage on Every Deskpaper | project

[2] Handwriting Transformerspaper

[1] On Generating Transferable Targeted Perturbationspaper | code

[1] PixelSynth: Generating a 3D-Consistent Experience from a Single Imagepaper | project

[13] Unsupervised Geodesic-preserved Generative Adversarial Networks for Unconstrained 3D Pose Transferpaper ｜ code

[12] Online Multi-Granularity Distillation for GAN Compressionpaper | code

[11] AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric Learningpaper | code

[10] Meta Gradient Adversarial Attackpaper

[9] Sketch Your Own GANpaper | code | project解读：用一张草图创建GAN模型，新手也能玩转，朱俊彦团队新研究入选ICCV 2021

[8] Feature Importance-aware Transferable Adversarial Attackspaper | code

[7] From Continuity to Editability: Inverting GANs with Consecutive Imagespaper | code

[6] Learnable Boundary Guided Adversarial Trainingpaper | code

[5] Transporting Causal Mechanisms for Unsupervised Domain Adaptation(Oral)paper

[4] Robustness via Cross-Domain Ensembles(Oral)paper | code | model | homepage | video

[3] HeadGAN: One-shot Neural Head Synthesis and Editingpaper

[2] Labels4Free: Unsupervised Segmentation using StyleGANpaper | code | project

[1] EigenGAN: Layer-Wise Eigen-Learning for GANspaper | code

[3] Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescalingpaper | code

[2] Accelerating Atmospheric Turbulence Simulation via Learned Phase-to-Space Transformpaper

[1] Equivariant Imaging: Learning Beyond the Range Space(Oral)paper

[2] Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolutionpaper | code

[1] Learning for Scale-Arbitrary Super-Resolution from Scale-Specific Networkspaper | code

[1] Rethinking Coarse-to-Fine Approach in Single Image Deblurringpaper | code

[1] Occlusion-Aware Video Object Inpainting(视频修复)paper

[5] SSH: A Self-Supervised Framework for Image Harmonization(图像协调)paper | code

[4] Domain-Aware Universal Style Transferpaper

[3] AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transferpaper | code1 | code2

[2] ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity(风格迁移)paper

[1] Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts(字体生成)paper | code

[1] MUSIQ: Multi-scale Image Quality Transformerpaper

[8] Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationpaper | code

[7] EventHPE: Event-based 3D Human Pose and Shape Estimationpaper

[6] HandFoldingNet: A 3D Hand Pose Estimation Network Using Multiscale-Feature Guided Folding of a 2D Hand Skeletonpaper | code

[5] Online Knowledge Distillation for Efficient Pose Estimationpaper

[4] Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowspaper

[3] Human Pose Regression with Residual Log-likelihood Estimation(Oral)paper | code

[2] PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop(Oral)paper | code | project

[1] HuMoR: 3D Human Motion Model for Robust Pose Estimation(Oral)paper | video | project

[4] Self-supervised Monocular Depth Estimation for All Day Images using Domain Separationpaper

[3] Towards Interpretable Deep Networks for Monocular Depth Estimationpaper | code

[2] Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Darkpaper

[1] MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environmentspaper

[5] ASMR: Learning Attribute-Based Person Search with Adaptive Semantic Margin Regularizerpaper

[4] Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Modelspaper | code

[3] DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Featurespaper

[2] Hand Image Understanding via Deep Multi-Task Learning(手部图像理解)paper

[1] Cross-Sentence Temporal and Semantic Relations in Video Activity Localisationpaper

[7] Group-aware Contrastive Regression for Action Quality Assessment(动作质量评估)paper

[6] Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization(动作定位)paper | code

[5] Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization(动作定位)paper | code

[4] Elaborative Rehearsal for Zero-shot Action Recognitionpaper | code

[3] Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learningpaper

[2] Enriching Local and Global Contexts for Temporal Action Localizationpaper

[1] Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitionpaper | code

[6] Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondencespaper

[5] Towards Discriminative Representation Learning for Unsupervised Person Re-identificationpaper

[4] Learning Instance-level Spatial-Temporal Patterns for Person Re-identificationpaper | Cleaned database

[3] An Intermediate Domain Module for Domain Adaptive Person Re-ID(Oral)paper | code

[2] Spatio-Temporal Representation Factorization for Video-based Person Re-Identificationpaper

[1] TransReID: Transformer-based Object Re-Identificationpaper | code解读：来自Transformer的降维打击：ReID各项任务全面领先，阿里&浙大提出TransReID

[1] End-to-End Dense Video Captioning with Parallel Decodingpaper | code

[4] PICCOLO: Point Cloud-Centric Omnidirectional Localizationpaper

[3] Normalization Matters in Weakly Supervised Object Localizationpaper

[2] TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localizationpaper | code

[1] Boundary-sensitive Pre-training for Temporal Localization in Videospaper

[5] Pixel-Perfect Structure-from-Motion with Featuremetric Refinementpaper | code

[4] Progressive Correspondence Pruning by Consensus Learningpaper | code | project解读：CLNet：基于一致性学习的渐进式匹配筛选

[3] Multi-scale Matching Networks for Semantic Correspondencepaper

[2] Warp Consistency for Unsupervised Learning of Dense Correspondences(Oral)paper | code

[1] COTR: Correspondence Transformer for Matching Across Imagespaper

[1] MVTN: Multi-View Transformation Network for 3D Shape Recognitionpaper

[8] Learning Spatio-Temporal Transformer for Visual Trackingpaper | code解读：屠榜目标跟踪！大连理工和MSRA提出STARK：基于Transformer的目标跟踪器

[7] Box-Aware Feature Enhancement for Single Object Tracking on Point Cloudspaper

[6] Video Annotation for Visual Tracking via Selection and Refinementpaper

[5] Saliency-Associated Object Trackingpaper

[4] Learn to Match: Automatic Matching Network Design for Visual Trackingpaper | code

[3] HiFT: Hierarchical Feature Transformer for Aerial Trackingpaper | code

[2] Learning to Adversarially Blur Visual Object Trackingpaper | code

[1] Detecting Invisible Peoplepaper | project | video

[2] Recurrent Mask Refinement for Few-Shot Medical Image Segmentationpaper

[1] Generative Adversarial Registration for Improved Conditional Deformable Templatespaper | code | homepage

[4] Adaptive Boundary Proposal Network for Arbitrary Shape Text Detectionpaper

[3] Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognitionpaper

[2] Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillationpaper

[1] Towards the Unseen: Iterative Text Recognition by Distilling from Errorspaper

[4] Structured Outdoor Architecture Reconstruction by Exploration and Classificationpaper

[3] Change is Everywhere Single-Temporal Supervised Object Change Detection for High Spatial Resolution Remote Sensing Imagery(变化检测)paper | code

[2] Geography-Aware Self-Supervised Learningpaper

[1] Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data(迁移学习)paper ｜ code

[4] Target Adaptive Context Aggregation for Video Scene Graph Generationpaper | code

[3] Unconditional Scene Graph Generationpaper

[2] Spatial-Temporal Transformer for Dynamic Scene Graph Generationpaper解读：用于视频场景图生成的时空上下文Transformer

[1] Unconstrained Scene Generation with Locally Conditioned Radiance Fieldspaper

[1] Generative Compositional Augmentations for Scene Graph Predictionpaper | code

[1] MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworkspaper解读：“白嫖”性能的MixMo，一种新的数据增强or模型融合方法

[3] A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictionpaper | code

[2] Weakly Supervised Temporal Anomaly Segmentation with Dynamic Time Warpingpaper

[1] Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningpaper | code

[4] Self-Supervised Visual Representations Learning by Contrastive Mask Predictionpaper

[3] Collaborative Unsupervised Visual Representation Learning from Decentralized Datapaper

[2] Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimizationpaper

[1] In-Place Scene Labelling and Understanding with Implicit Scene Representation(Oral)paper | project

[4] Instance Similarity Learning for Unsupervised Feature Representationpaper | code

[3] Graph Constrained Data Representation Learning for Human Motion Segmentation(人体运动分割)paper

[2] Improve Unsupervised Pretraining for Few-label Transferpaper

[1] Clustering by Maximizing Mutual Information Across Viewspaper

[3] Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoderpaper

[2] Transductive Few-Shot Classification on the Oblique Manifoldpaper

[1] FREE: Feature Refinement for Generalized Zero-Shot Learningpaper | code

[3] Continual Neural Mapping: Learning An Implicit Scene Representation from Sequential Observationspaper

[2] RECALL: Replay-based Continual Learning in Semantic Segmentationpaper

[1] Few-Shot and Continual Learning with Attentive Independent Mechanismspaper | code

[14] PIT: Position-Invariant Transform for Cross-FoV Domain Adaptationpaper | code

[13] Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentationpaper

[12] Semantic Concentration for Domain Adaptationpaper

[11] Dual Path Learning for Domain Adaptation of Semantic Segmentationpaper | code

[10] Zero-Shot Domain Adaptation with a Physics Prior(Oral)paper | code

[9] BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentationpaper

[8] Domain Generalization via Gradient Surgery

paper

[7] Generalizing Gaze Estimation with Outlier-guided Collaborative Adaptationpaper | code

[6] Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iteratepaper

[5] Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation(Oral)paper

[4] Improve Unsupervised Pretraining for Few-label Transferpaper

[3] Generalized Source-free Domain Adaptationhomepage | code

[2] Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data(迁移学习)paper ｜ code

[1] Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling(迁移学习)paper

[4] Towards Interpretable Deep Metric Learning with Structural Matchingpaper | code

[3] AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric Learningpaper | code

[2] Deep Metric Learning for Open World Semantic Segmentationpaper

[1] Learning with Memory-based Virtual Classes for Deep Metric Learningpaper

[2] Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgettingpaper | code

[1] Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learningpaper | code | project

[4] Improving Contrastive Learning by Visualizing Feature Transformationpaper ｜ visualization tools and codes

[3] Parametric Contrastive Learningpaper | code

[2] Geography-Aware Self-Supervised Learningpaper

[1] CoMatch: Semi-supervised Learning with Contrastive Graph Regularizationpaper | code

[2] Semi-Supervised Active Learning with Temporal Output Discrepancypaper | code

[1] Active Learning for Deep Object Detection via Probabilistic Modelingpaper

[3] Greedy Gradient Ensemble for Robust Visual Question Answeringpaper | code

[2] On the hidden treasure of dialog in video question answeringpaper

[1] Just Ask: Learning to Answer Questions from Millions of Narrated Videos(Oral)paper | code | project

[1] The Right to Talk: An Audio-Visual Transformer Approachpaper

[7] MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction(人体运动预测)paper ｜ code

[6] RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting(运动预测)paper | project

[5] SLAMP: Stochastic Latent Appearance and Motion Prediction(运动预测)paper

[4] Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction(轨迹预测)paper

[3] Personalized Trajectory Prediction via Distribution Discrimination(轨迹预测)paper | code

[2] Human Trajectory Prediction via Counterfactual Analysis(轨迹预测)paper | code

[1] On Exposing the Challenging Long Tail in Future Prediction of Traffic Actorspaper

[7] LOKI: Long Term and Key Intentions for Trajectory Prediction(轨迹预测)paper | dataset

[6] Who's Waldo? Linking People Across Text and Images(Oral)paper | project

[5] Towards Real-World Prohibited Item Detection: A Large-Scale X-ray Benchmark(违禁物品检测)paper

[4] Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision(地标照片集)paper | project

[3] Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approachpaper | dataset

[2] OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wildpaper | project

[1] 4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface(4D重建)paper | dataset | video

Stochastic Scene-Aware Motion Prediction(运动合成)(运动预测)paper | project

End-to-End Urban Driving by Imitating a Reinforcement Learning Coach(自动驾驶)(强化学习)paper

Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervisionpaper | code

Asymmetric Bilateral Motion Estimation for Video Frame Interpolation(视频插帧)paper | code

Focus on the Positives: Self-Supervised Learning for Biodiversity Monitoringpaper

DiagViB-6: A Diagnostic Benchmark Suite for Vision Models in the Presence of Shortcut and Generalization Opportunitiespaper

MT-ORL: Multi-Task Occlusion Relationship Learningpaper | code

ProAI: An Efficient Embedded AI Hardware for Automotive Applications - a Benchmark Studypaper

Invisible Backdoor Attack with Sample-Specific Triggers(后门学习)paper解读：具有样本特定触发器的隐形后门攻击

SUNet: Symmetric Undistortion Network for Rolling Shutter Correctionpaper

Learning to Cut by Watching Moviespaper | project

Paint Transformer: Feed Forward Neural Painting with Stroke Prediction(Oral)paper | code

Internal Video Inpainting by Implicit Long-range Propagationpaper

CanvasVAE: Learning to Generate Vector Graphic Documentspaper

TkML-AP: Adversarial Attacks to Top-k Multi-Label Learning(多标签学习)paper

Out-of-Core Surface Reconstruction via Global TGV Minimizationpaper

Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting(人群计数)paper

Spatial Uncertainty-Aware Semi-Supervised Crowd Counting(人群计数)paper

Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework(Oral)(人群计数)paper | code

Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting(人群计数)paper | code

Self-Conditioned Probabilistic Learning of Video Rescaling(视频压缩)paper

Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives(手势生成)paper

Temporal-wise Attention Spiking Neural Networks for Event Streams Classificationpaper

Long-Term Temporally Consistent Unpaired Video Translation from Simulated Surgical 3D Data（视频翻译/医学/视频合成）paper

Pathdreamer: A World Model for Indoor Navigation(视觉导航)paper

IPOKE: POKING A STILL IMAGE FOR CONTROLLED STOCHASTIC VIDEO SYNTHESISpaper | code | project

Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesispaper | project

KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPspaper | code