ECCV2022 &CVPR2022论文速递2022.7.25！
最新成果demo展示：
ECCV 2022 | 无惧遮挡！3D 交互手部姿势估计
最新论文整理
ECCV2022
Updated on : 25 Jul 2022
total number : 24
Panoptic Scene Graph Generation
论文/Paper: http://arxiv.org/pdf/2207.11247
代码/Code: https://github.com/Jingkang50/OpenPSG
Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay
论文/Paper: http://arxiv.org/pdf/2207.11213
代码/Code: None
Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark
论文/Paper: http://arxiv.org/pdf/2207.11169
代码/Code: https://github.com/amazon-research/few-shot-object-detection-benchmark.
InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images
论文/Paper: http://arxiv.org/pdf/2207.11148
代码/Code: None
RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos
论文/Paper: http://arxiv.org/pdf/2207.11075
代码/Code: https://github.com/megvii-research/RealFlow
3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal
论文/Paper: http://arxiv.org/pdf/2207.11061
代码/Code: https://github.com/MengHao666/HDR.
POP: Mining POtential Performance of new fashion products via webly cross-modal query expansion
论文/Paper: http://arxiv.org/pdf/2207.11001
代码/Code: https://github.com/HumaticsLAB/POP-Mining-POtential-Performance
Few-shot Object Counting and Detection
论文/Paper: http://arxiv.org/pdf/2207.10988
代码/Code: \url{https://github.com/VinAIResearch/Counting-DETR}.
Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection
论文/Paper: http://arxiv.org/pdf/2207.10955
代码/Code: None
Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection
论文/Paper: http://arxiv.org/pdf/2207.10948
代码/Code: https://github.com/Beyond-Zw/DLAN-AC.
Long-tailed Instance Segmentation using Gumbel Optimized Loss
论文/Paper: http://arxiv.org/pdf/2207.10936
代码/Code: https://github.com/kostas1515/GOL
Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness
论文/Paper: http://arxiv.org/pdf/2207.10899
代码/Code: https://github.com/pantheon5100/DeACL.
Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation
论文/Paper: http://arxiv.org/pdf/2207.10892
代码/Code: None
FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification
论文/Paper: http://arxiv.org/pdf/2207.10888
代码/Code: https://github.com/Bernardo1998/FairGRAPE
My View is the Best View: Procedure Learning from Egocentric Videos
论文/Paper: http://arxiv.org/pdf/2207.10883
代码/Code: https://github.com/Sid2697/EgoProceL-egocentric-procedure-learning
Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation
论文/Paper: http://arxiv.org/pdf/2207.10866
代码/Code: None
Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation
论文/Paper: http://arxiv.org/pdf/2207.10856
代码/Code: https://github.com/Hongbin98/ProCA.git
Spatio-Temporal Deformable Attention Network for Video Deblurring
论文/Paper: http://arxiv.org/pdf/2207.10852
代码/Code: None
Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments
论文/Paper: http://arxiv.org/pdf/2207.10785
代码/Code: https://github.com/VinAIResearch/fsvc-ata.
Auto-regressive Image Synthesis with Integrated Quantization
论文/Paper: http://arxiv.org/pdf/2207.10776
代码/Code: None
Towards Interpretable Video Super-Resolution via Alternating Optimization
论文/Paper: http://arxiv.org/pdf/2207.10765
代码/Code: None
MeshLoc: Mesh-Based Visual Localization
论文/Paper: http://arxiv.org/pdf/2207.10762
代码/Code: None
DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection
论文/Paper: http://arxiv.org/pdf/2207.10758
代码/Code: https://github.com/abhi1kumar/DEVIANT
Optimizing Image Compression via Joint Learning with Denoising
论文/Paper: http://arxiv.org/pdf/2207.10869
代码/Code: https://github.com/felixcheng97/DenoiseCompression.