ICCV2023论文速递（2023.8.15）！

整理：AI算法与图像处理

CVPR2023论文和代码整理：https://github.com/DWCTOD/CVPR2023-Papers-with-Code-Demo

欢迎关注公众号 AI算法与图像处理，获取更多干货：

大家好,  最近正在优化每周分享的CVPR论文, 目前考虑按照不同类别去分类,方便不同方向的小伙伴挑选自己感兴趣的论文哈

最新成果demo展示：

ICCV 2023

Updated on : 15 Aug 2023

total number : 0

Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation

• 论文/Paper: http://arxiv.org/pdf/2308.07313

• 代码/Code: https://github.com/michel-liu/grouppose

Distance Matters For Improving Performance Estimation Under Covariate Shift

• 论文/Paper: http://arxiv.org/pdf/2308.07223

• 代码/Code: https://github.com/melanibe/distance_matters_performance_estimation

HyperSparse Neural Networks: Shifting Exploration to Exploitation through Adaptive Regularization

• 论文/Paper: http://arxiv.org/pdf/2308.07163

• 代码/Code: https://github.com/greenautoml4fas/hypersparse

DELO: Deep Evidential LiDAR Odometry using Partial Optimal Transport

• 论文/Paper: http://arxiv.org/pdf/2308.07153

• 代码/Code: None

Diffusion Based Augmentation for Captioning and Retrieval in Cultural Heritage

• 论文/Paper: http://arxiv.org/pdf/2308.07151

• 代码/Code: None

CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation

• 论文/Paper: http://arxiv.org/pdf/2308.07146

• 代码/Code: https://github.com/kevinlight831/ctp

SCSC: Spatial Cross-scale Convolution Module to Strengthen both CNNs and Transformers

• 论文/Paper: http://arxiv.org/pdf/2308.07110

• 代码/Code: None

Masked Motion Predictors are Strong 3D Action Representation Learners

• 论文/Paper: http://arxiv.org/pdf/2308.07092

• 代码/Code: https://github.com/maoyunyao/MAMP.

S3IM: Stochastic Structural SIMilarity and Its Unreasonable Effectiveness for Neural Fields

• 论文/Paper: http://arxiv.org/pdf/2308.07032

• 代码/Code: https://github.com/Madaoer/S3IM.

ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasion

• 论文/Paper: http://arxiv.org/pdf/2308.07009

• 代码/Code: None

Global Features are All You Need for Image Retrieval and Reranking

• 论文/Paper: http://arxiv.org/pdf/2308.06954

• 代码/Code: https://github.com/shihaoshao-gh/superglobal

Knowing Where to Focus: Event-aware Transformer for Video Grounding

• 论文/Paper: http://arxiv.org/pdf/2308.06947

• 代码/Code: https://github.com/jinhyunj/eatr

Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking

• 论文/Paper: http://arxiv.org/pdf/2308.06904

• 代码/Code: https://github.com/kangben258/hit

Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization

• 论文/Paper: http://arxiv.org/pdf/2308.06879

• 代码/Code: None

RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networks

• 论文/Paper: http://arxiv.org/pdf/2308.06787

• 代码/Code: None

Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning

• 论文/Paper: http://arxiv.org/pdf/2308.06777

• 代码/Code: https://github.com/LiheYoung/ShrinkMatch

Dual Meta-Learning with Longitudinally Generalized Regularization for One-Shot Brain Tissue Segmentation Across the Human Lifespan

• 论文/Paper: http://arxiv.org/pdf/2308.06774

• 代码/Code: https://github.com/ladderlab-xjtu/DuMeta.

AerialVLN: Vision-and-Language Navigation for UAVs

• 论文/Paper: http://arxiv.org/pdf/2308.06735

• 代码/Code: https://github.com/AirVLN/AirVLN.

Compositional Feature Augmentation for Unbiased Scene Graph Generation

• 论文/Paper: http://arxiv.org/pdf/2308.06712

• 代码/Code: None

Isomer: Isomerous Transformer for Zero-shot Video Object Segmentation

• 论文/Paper: http://arxiv.org/pdf/2308.06693

• 代码/Code: https://github.com/dlut-yyc/isomer

Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training

• 论文/Paper: http://arxiv.org/pdf/2308.06689

• 代码/Code: https://github.com/dravenalg/reste

3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking

• 论文/Paper: http://arxiv.org/pdf/2308.06635

• 代码/Code: https://github.com/dsx0511/3dmotformer

DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning

• 论文/Paper: http://arxiv.org/pdf/2308.06622

• 代码/Code: https://github.com/nis-research/dfmx-augmentation

On the Interplay of Convolutional Padding and Adversarial Robustness

• 论文/Paper: http://arxiv.org/pdf/2308.06612

• 代码/Code: None

Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction

• 论文/Paper: http://arxiv.org/pdf/2308.06554

• 代码/Code: https://github.com/hygenie1228/CycleAdapt_RELEASE.

Revisiting Vision Transformer from the View of Path Ensemble

• 论文/Paper: http://arxiv.org/pdf/2308.06548

• 代码/Code: None

SegPrompt: Boosting Open-world Segmentation via Category-level Prompt Learning

• 论文/Paper: http://arxiv.org/pdf/2308.06531

• 代码/Code: https://github.com/aim-uofa/segprompt

BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation

• 论文/Paper: http://arxiv.org/pdf/2308.06530

• 代码/Code: None

Tiny and Efficient Model for the Edge Detection Generalization

• 论文/Paper: http://arxiv.org/pdf/2308.06468

• 代码/Code: https://github.com/xavysp/TEED.

U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds

• 论文/Paper: http://arxiv.org/pdf/2308.06383

• 代码/Code: https://github.com/zhangcyg/u-red

Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning

• 论文/Paper: http://arxiv.org/pdf/2308.07209

• 代码/Code: None

CBA: Improving Online Continual Learning via Continual Bias Adaptor

• 论文/Paper: http://arxiv.org/pdf/2308.06925

• 代码/Code: https://github.com/wqza/cba-online-cl

Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches

• 论文/Paper: http://arxiv.org/pdf/2308.06776

• 代码/Code: https://github.com/linxin0/scpgabnet

Multi-Label Knowledge Distillation

• 论文/Paper: http://arxiv.org/pdf/2308.06453

• 代码/Code: https://github.com/penghui-yang/l2d

•