顶会论文速递！2023.11.7

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：

CVPR 2023

Updated on : 7 Nov 2023

total number : 1

Non-Hierarchical Transformers for Pedestrian Segmentation

• 论文/Paper: http://arxiv.org/pdf/2311.02506

• 代码/Code: None

ICCV 2023

Updated on : 7 Nov 2023

total number : 0

Efficient, Self-Supervised Human Pose Estimation with Inductive Prior Tuning

• 论文/Paper: http://arxiv.org/pdf/2311.02815

• 代码/Code: https://github.com/princetonvisualai/hpe-inductive-prior-tuning

Benchmarking a Benchmark: How Reliable is MS-COCO?

• 论文/Paper: http://arxiv.org/pdf/2311.02709

• 代码/Code: None

An Empirical Study of Uncertainty in Polygon Annotation and the Impact of Quality Assurance

• 论文/Paper: http://arxiv.org/pdf/2311.02707

• 代码/Code: None

Neural Collage Transfer: Artistic Reconstruction via Material Manipulation

• 论文/Paper: http://arxiv.org/pdf/2311.02202

• 代码/Code: https://github.com/northadventure/collagerl

WACV 2024

Updated on : 7 Nov 2023

total number : 14

TAMPAR: Visual Tampering Detection for Parcel Logistics in Postal Supply Chains

• 论文/Paper: http://arxiv.org/pdf/2311.03124

• 代码/Code: None

GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation

• 论文/Paper: http://arxiv.org/pdf/2311.03035

• 代码/Code: https://github.com/ackesnal/gtp-vit

Attention Modules Improve Image-Level Anomaly Detection for Industrial Inspection: A DifferNet Case Study

• 论文/Paper: http://arxiv.org/pdf/2311.02747

• 代码/Code: https://github.com/andreluizbvs/insplad

ISAR: A Benchmark for Single- and Few-Shot Object Instance Segmentation and Re-Identification

• 论文/Paper: http://arxiv.org/pdf/2311.02734

• 代码/Code: None

A Generative Multi-Resolution Pyramid and Normal-Conditioning 3D Cloth Draping

• 论文/Paper: http://arxiv.org/pdf/2311.02700

• 代码/Code: https://github.com/hunorlaczko/pyramid-drape

CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoning

• 论文/Paper: http://arxiv.org/pdf/2311.02661

• 代码/Code: https://github.com/cv-stuttgart

The Background Also Matters: Background-Aware Motion-Guided Objects Discovery

• 论文/Paper: http://arxiv.org/pdf/2311.02633

• 代码/Code: None

Learning Class and Domain Augmentations for Single-Source Open-Domain Generalization

• 论文/Paper: http://arxiv.org/pdf/2311.02599

• 代码/Code: None

3D-Aware Talking-Head Video Motion Transfer

• 论文/Paper: http://arxiv.org/pdf/2311.02549

• 代码/Code: None

Augment the Pairs: Semantics-Preserving Image-Caption Pair Augmentation for Grounding-Based Vision and Language Models

• 论文/Paper: http://arxiv.org/pdf/2311.02536

• 代码/Code: https://github.com/amzn/augment-the-pairs-wacv2024

Continual Learning of Unsupervised Monocular Depth from Videos

• 论文/Paper: http://arxiv.org/pdf/2311.02393

• 代码/Code: https://github.com/neurai-lab/cude-monodepthcl

Complex Organ Mask Guided Radiology Report Generation

• 论文/Paper: http://arxiv.org/pdf/2311.02329

• 代码/Code: None

Lost Your Style? Navigating with Semantic-Level Approach for Text-to-Outfit Retrieval

• 论文/Paper: http://arxiv.org/pdf/2311.02122

• 代码/Code: None

FATE: Feature-Agnostic Transformer-based Encoder for learning generalized embedding spaces in flow cytometry data

• 论文/Paper: http://arxiv.org/pdf/2311.03314

• 代码/Code: https://github.com/lisaweijler/fate

NeurIPS 2023

Updated on : 7 Nov 2023

total number : 7

A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation

• 论文/Paper: http://arxiv.org/pdf/2311.03312

• 代码/Code: None

LDM3D-VR: Latent Diffusion Model for 3D VR

• 论文/Paper: http://arxiv.org/pdf/2311.03226

• 代码/Code: None

Digital Typhoon: Long-term Satellite Image Dataset for the Spatio-Temporal Modeling of Tropical Cyclones

• 论文/Paper: http://arxiv.org/pdf/2311.02665

• 代码/Code: https://github.com/kitamoto-lab/digital-typhoon

Dynamic Neural Fields for Learning Atlases of 4D Fetal MRI Time-series

• 论文/Paper: http://arxiv.org/pdf/2311.02874

• 代码/Code: https://github.com/kidrauh/neural-atlasing

Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion

• 论文/Paper: http://arxiv.org/pdf/2311.02738

• 代码/Code: None

Synthetic Tumor Manipulation: With Radiomics Features

• 论文/Paper: http://arxiv.org/pdf/2311.02586

• 代码/Code: None

Multi-task Learning for Optical Coherence Tomography Angiography (OCTA) Vessel Segmentation

• 论文/Paper: http://arxiv.org/pdf/2311.02266

• 代码/Code: None

•