揭秘 CVPR 2024 Workshop 新兴技术与研究方向（下）

关注公众号，发现CV技术之美

美国华盛顿州西雅图

本文汇总了 CVPR 2024 所有的研讨会（下篇），会议中既有延续举办的经典研讨会，也有首次举办的全新研讨会。大部分研讨会的论文征稿已经截止，部分接收的论文也已经公布，欢迎感兴趣的伙伴先行查阅。

另外，CVPR 2024 收录论文已更新在 Github 库，欢迎 star ⭐。

• Github：https://github.com/52CV/CVPR-2024-Papers

1.Generative Models

2nd Workshop on Generative Models for Computer Vision

• 项目主页：https://generative-vision.github.io/workshop-CVPR-24/

研讨会聚焦于图像合成和计算机视觉交叉领域所面临的挑战和机遇，探讨相关技术和应用问题。

接收长篇论文：TBD

接收短篇论文：

• As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion Priors
• Generative AI in Vision: A Survey on Models, Metrics and Applications
• Robustness of Generative Models using Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation
• Intrinsic LoRA: A Generalist Approach for Discovering Knowledge in Generative Models
• GL-NeRF: Gauss-Laguerre Quadrature for Volume Rendering
• Synthesizing Image with High-Quality Segmentation Mask by Prompting Large Vision Model
• Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Data
• Posterior Distillation Sampling
• Learning Compositional Language-based Object Detection with Diffusion-based Synthetic Data
• KOALA: Fast and Memory-Efficient Latent Diffusion Models via Self-Attention Distillation
• Turns Out I'm Not Real: Towards Robust Detection of AI-Generated Videos
• Diffusion Models for Open-Vocabulary Segmentation
• ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models
• Do Counterfactual Examples Complicate Adversarial Training?
• CAT: Contrastive Adapter Training for Personalized Image Generation
• ZoomLDM: Latent Diffusion Model for multi-scale conditional histopathology image generation
• Causal Diffusion Autoencoders: Toward Representation-Enabled Counterfactual Generation via Diffusion Probabilistic Models
• Spatially Composable Diffusion
• Learning Multimodal Latent Space with EBM Prior and MCMC Inference

📍First Workshop on Efficient and On-Device Generation (EDGE)

• 项目主页：https://cvpr24-edge.github.io/

研讨会聚焦于生成式 AI 在计算机视觉领域的最新进展，探讨相关技术和应用问题。

论文征稿已截止

GenAI Media Generation Challenge for Computer Vision Workshop

• 项目主页：https://gamgc.github.io/

研讨会聚焦于生成模型发展中缺乏全面、大规模的评估数据集、标准化的评估协议以及当前自动度量标准的问题，提出相关挑战赛，探讨相关技术和解决方案。

论文征稿已截止

📍ReGenAI: First Workshop on Responsible Generative AI

• 项目主页：https://sites.google.com/view/cvpr-responsible-genai

研讨会聚焦于负责任的生成式 AI 所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

The First Workshop on the Evaluation of Generative Foundation Models

• 项目主页：https://evgenfm.github.io/

研讨会聚焦于生成基础模型（GenFMs）所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

2.Human Understanding

New Challenges in 3D Human Understanding

• 项目主页：https://sites.google.com/view/3d-humans-cvpr2024

研讨会聚焦于3D人类理解（多人互动分析、细粒度动作捕捉、穿着衣物的身体重建、虚拟试衣等）所面临的挑战和机遇，探讨相关技术和应用问题。

是否征稿：否

📍New Trends in Multimodal Human Action Perception, Understanding and Generation

• 项目主页：https://mango-workshop.github.io/2024.html

研讨会聚焦于多模态人体动作感知、理解、生成所面临的挑战和机遇，探讨相关技术和应用问题。

是否征稿：否

Rhobin 2024: The second Rhobin challenge on Reconstruction of Human-Object Interaction

• 项目主页：https://rhobin-challenge.github.io/index.html

研讨会聚焦于超越基于图像的交互重建，扩展到随时间变化的交互跟踪，寻求与相关主题（如自我中心视觉和动态场景交互）的联系的研究。

论文征稿已截止

Workshop on Human Motion Generation

• 项目主页：https://humogen.github.io/

研讨会聚焦于人体运动生成所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

3.Medical Vision

9th Workshop on Computer Vision for Microscopy Image Analysis

• 项目主页：https://cvmi-workshop.github.io/index.html

研讨会聚焦于计算机视觉和机器学习技术在显微镜图像分析中的应用所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

Data Curation and Augmentation in Enhancing Medical Imaging Applications

• 项目主页：https://dca-in-mi.github.io/

研讨会聚焦于基于数据驱动的计算机视觉和人工智能在医学成像应用中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

Domain adaptation, Explainability and Fairness in AI for Medical Image Analysis (DEF-AI-MIA)

• 项目主页：https://ai-medical-image-analysis.github.io/4th/

研讨会聚焦于AI辅助医学图像分析中域适应、公平性和可解释性所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

Foundation Models for Medical Vision

• 项目主页：https://fmv-cvpr24workshop.github.io/

研讨会聚焦于基础模型在医学成像领域所面临的挑战和机遇，探讨相关技术和应用问题。

是否征稿：否

4.Mobile and Embedded Vision

4th Mobile AI Workshop and Challenges

• 项目主页：https://ai-benchmark.com/workshops/mai/2024/

研讨会聚焦于基于人工智能的移动应用中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

Embedded Vision Workshop

• 项目主页：https://embeddedvisionworkshop.wordpress.com/

研讨会聚焦于嵌入式视觉所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

Third Workshop of Mobile Intelligent Photography & Imaging

• 项目主页：https://mipi-challenge.org/MIPI2024/

研讨会聚焦于图像传感器的最新算法在照相系统应用中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

5.Multimodal Learning

7th MUltimodal Learning and Applications

• 项目主页：https://mula-workshop.github.io/

研讨会聚焦于多模态学习在计算机视觉、多媒体、遥感和机器人应用中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

Multimodal Algorithmic Reasoning Workshop

• 项目主页：https://marworkshop.github.io/cvpr24/index.html

研讨会聚焦于多模态算法推理中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

Sight and Sound

• 项目主页：https://sightsound.org/

研讨会聚焦于视觉和声音所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

6.Neural Rendering

📍1st Workshop on Neural Volumetric Video

• 项目主页：https://nvvw.github.io/

研讨会聚焦于动态视图合成所面临的挑战和机遇，探讨相关技术和应用问题。

是否征稿：否

Neural Rendering Intelligence

• 项目主页：https://neural-rendering.com/

研讨会聚焦于神经渲染和新兴渲染智能所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

XRNeRF: Second Workshop on Advances in Radiance Fields for the Metaverse

• 项目主页：https://sites.google.com/view/xrnerf/

研讨会聚焦于对元宇宙具有影响的三个方面：规模、效率和保真度研究中所面临的挑战和机遇，探讨相关技术和应用问题。

是否征稿：否

7.Open World Learning

VAND 2.0: Visual Anomaly and Novelty Detection

• 项目主页：https://sites.google.com/view/vand-2-0-cvpr-2024/home

研讨会聚焦于异常检测和新颖性检测在医疗诊断、机场安检、工业检测或人群控制等应用中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

Visual Perception via Learning in an Open World

• 项目主页：https://vplow.github.io/vplow_4th.html

研讨会聚焦于开放世界中开发视觉感知算法所面临的挑战和机遇，探讨相关技术和应用问题。

是否征稿：否

8.Physics, Graphics, Geometry, AR/VR/MR

4th Workshop on Physics Based Vision meets Deep Learning (PBDL2024)

• 项目主页：https://pbdl-ws.github.io/pbdl2024/index.html

研讨会聚焦于基于物理的视觉与深度学习所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

Computer Vision for Mixed Reality

• 项目主页：https://cv4mr.github.io/

研讨会聚焦于混合现实在计算机视觉应用中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

Social Presence with Codec Avatars

• 项目主页：https://codec-avatars.github.io/cvpr24/

研讨会聚焦于生成和操控逼真的人体表示研究中所面临的挑战和机遇，探讨相关技术和应用问题。

在生成方面，重点关注面部、手部和身体的高效3D表示学习，以及每种模态的特殊挑战。

在操控方面，重点讨论使用头戴式设备驱动面部和手部，以及使用外部摄像头进行全身跟踪。

是否征稿：否

The Sixth Workshop on Deep Learning for Geometric Computing (DLGC 2024)

• 项目主页：https://sites.google.com/view/dlgc-workshop-cvpr2024/home

研讨会聚焦于深度学习在几何计算中的应用中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

9.Responsible and Explainable AI

2nd Workshop on Multimodal Content Moderation

• 项目主页：https://multimodal-content-moderation.github.io/

研讨会聚焦于多模态在内容管理应用中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

Ethical Considerations in Creative Applications of Computer Vision

• 项目主页：https://sites.google.com/view/cvpr-2024-ec3v

研讨会聚焦于计算机视觉在艺术创意应用中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

Safe Artificial Intelligence for All Domains (SAIAD)

• 项目主页：https://sites.google.com/view/saiad-2024/home

研讨会聚焦于安全人工智能研究中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

接收长篇论文：

• Reliable Trajectory Prediction and Uncertainty Quantification with Conditioned Diffusion Models
• Hinge-Wasserstein: Estimating Multimodal Aleatoric Uncertainty in Regression Tasks
• Towards 100x faster Randomized Smoothing: exploring the trade-off between sample budget and Certified Radius
• The Penalized Inverse Probability Measure for Conformal Classification
• Run-time Monitoring of 3D Object Detection in Automated Driving Systems Using Early Layer Neural Activation Patterns

接收短篇论文：

• Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition
• Understanding ReLU Network Robustness Through Test Set Certification Performance
• AdvDenoise: Fast Generation Framework of Universal and Robust Adversarial Patches Using Denoise
• Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations
• Situation Monitor: Zero-Shot Out-of-Distribution Detection based on Diversity based Budding Ensemble Architecture for Object Detection
• Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression
• Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Study
• Towards Weakly-Supervised Domain Adaptation for Lane Detection
• Towards Engineered Safe AI with Modular Concept Models
• Conformal Semantic Image Segmentation: Post-hoc quantification of predictive uncertainty
• A Comprehensive Analysis of Factors Impacting Membership Inference
• Exploiting CLIP Self-Consistency to Automate Image Augmentation for Safety Critical Scenarios

The 3rd Explainable AI for Computer Vision (XAI4CV) Workshop

• 项目主页：https://xai4cv.github.io/

研讨会聚焦于可解释 AI 研究中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

The Fifth Workshop on Fair, Data-efficient, and Trusted Computer Vision

• 项目主页：https://fadetrcv.github.io/2024/

研讨会聚焦于计算机视觉和人工智能系统信任的四个关键问题：公平性、可解释性、对抗性和隐私安全性研究中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

Workshop on Responsible Data

• 项目主页：https://responsibledata.github.io/

研讨会聚焦于构建更包容性和多样性的数据集所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

10.Science Applications

4th Workshop on CV4Animals: Computer Vision for Animal Behavior Tracking and Modeling

• 项目主页：https://www.cv4animals.com/

研讨会聚焦于对基于计算机视觉的动物行为理解研究所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

接收论文：

• Benchmarking wild bird detection in complex forest scenes
• Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape
• Low-power, Continuous Remote Behavioral Localization with Event Cameras
• Learning Implicit Representation for Reconstructing Articulated Objects
• Three-dimensional surface motion capture of multiple freely moving pigs using MAMMAL
• UniAP: Towards Universal Animal Perception in Vision via Few-Shot Learning
• BioCLIP: A Vision Foundation Model for the Tree of Life
• Learning the 3D Fauna of the Web
• GART: Gaussian Articulated Template Models
• Putting the Object Back into Video Object Segmentation
• WildlifeDatasets: An Open-Source Toolkit for Animal Re-Identification
• Deep learning enables satellite-based monitoring of large populations of terrestrial mammals across heterogeneous landscape
• Using machine learning to count Antarctic shag (Leucocarbo bransfieldensis) nests on images captured by Remotely Piloted Aircraft Systems
• Deep Learning Methodology for Early Detection and Outbreak Prediction of Invasive Species Growth
• A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis
• Species-agnostic Patterned Animal Re-Identification by Aggregating Deep Local Features
• OmniMotionGPT: Animal Motion Generation with Limited Data

AI4Space 2024

• 项目主页：https://aiforspace.github.io/2024/

研讨会聚焦于人工智能、计算机视觉、机器学习在航空领域应用中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

接收论文：

• Robust Perspective-n-Crater for Crater-based Camera Pose Estimation
• Exploring AI-based satellite pose estimation: from novel synthetic dataset to in-depth performance evaluation
• Optimized Martian Dust Displacement Detection Using Explainable Machine Learning
• Mitigating Challenges of the Space Environment for Onboard Artificial Intelligence: Design Overview for a recently launched payload
• A Dual-Mode Approach for Vision-Based Navigation in a Lunar Landing Scenario
• Tackling the Satellite Downlink Bottleneck with Federated Onboard Learning of Image Compression
• Transformers for Orbit Determination Anomaly Detection and Classification
• Deploying Machine Learning Anomaly Detection Models to Flight Ready AI Boards
• Cross-Temporal Spectrogram Autoencoder (CTSAE): Unsupervised Dimensionality Reduction for Clustering Gravitational Wave Glitches
• Monocular 6-DoF Pose Estimation of Spacecrafts Utilizing Self-iterative Optimization and Motion Consistency
• CroSpace6D: Leveraging Geometric and Motion Cues for High-Precision Cross-Domain 6DoF Pose Estimation for Non-Cooperative Spacecrafts
• Revisiting the Domain Gap Issue in Non-cooperative Spacecraft Pose Tracking

Computer Vision for Materials Science Workshop

• 项目主页：https://sites.google.com/view/cv4ms-cvpr-2024

研讨会聚焦于机器学习、计算机视觉和材料显微镜研究中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

CV4Science

• 项目主页：https://sites.google.com/nyu.edu/computervisionforscience/

研讨会聚焦于计算机视觉与科学交叉领域研究中所面临的挑战和机遇，探讨相关技术和应用问题。

是否征稿：否

The Seventh International Workshop on Computer Vision for Physiological Measurement (CVPM)

• 项目主页：https://www.es.ele.tue.nl/cvpm24/

研讨会聚焦于计算摄影中的技术与视觉识别领域所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

11.Synthetic Data

3rd Workshop on Vision Datasets Understanding and DataCV Challenge

• 项目主页：https://sites.google.com/view/vdu-cvpr24/

研讨会聚焦于对各种类型的视觉数据集的理解、应用和评估中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

SyntaGen: Harnessing Generative Models for Synthetic Visual Datasets

• 项目主页：https://syntagen.github.io/

研讨会聚焦于生成模型和计算机视觉应用领域所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

Synthetic Data for Computer Vision

• 项目主页：https://syndata4cv.github.io/

研讨会聚焦于合成数据在计算机视觉模型的训练和评估中所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

12.Urban Environments

📍1st Workshop on Urban Scene Modeling: Where Vision Meets Photogrammetry and Graphics

• 项目主页：https://usm3d.github.io/

研讨会聚焦于城市场景建模所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

4th Workshop and Challenge on Computer Vision in the Built Environment for the Design, Construction, and Operation of Buildings

• 项目主页：https://cv4aec.github.io/

研讨会聚焦于计算机视觉在建筑环境中的最新研究进展和应用，重点关注平面图重建和三维建筑模型重建的任务。

论文征稿已截止

接收论文：

• Automatic Defurnishing of Indoor Panoramas
• A Two-Stage Masked Autoencoder Based Network for Indoor Depth Completion
• ARCH2S: Dataset, Benchmark and Challenges for Learning Exterior Architectural Structures from Point Clouds
• Towards Automating the Retrospective Generation of BIM Models: A Unified Framework for 3D Semantic Reconstruction of the Built Environment
• Enhancing Polygonal Building Segmentation via Oriented Corners
• Window to Wall Ratio Detection using SegFormer
• An Expeditious Spatial Mean Radiant Temperature Mapping Framework using Visual SLAM and Semantic Segmentation
• Zero-Shot Construction Object Detection through Knowledge-based Feature Integrator
• Real-time Ergonomic Risk Assessment in Construction Sites through Spatiotemporal Graph Convolution Network
• BIM-Module for deep learning-based parametric IFC reconstruction

8th AI City Challenge

• 项目主页：https://www.aicitychallenge.org/

研讨会聚焦于人工智能城市的两大潜力研究领域：the brick and mortar retail business（实体零售业务）和Intelligent Traffic Systems（智能交通系统）所面临的挑战和机遇，探讨相关技术和应用问题。

是否征稿：否

13.Video Understanding

4th International Workshop on Long-form Video Understanding: Towards Multimodal AI Assistant and Copilot

• 项目主页：https://sites.google.com/view/loveucvpr24

研讨会聚焦于长视频理解所面临的挑战和机遇，探讨相关技术和应用问题。

是否征稿：否

5th International Workshop on Large Scale Holistic Video Understanding

• 项目主页：https://holistic-video-understanding.github.io/workshops/cvpr2024.html

研讨会聚焦于整体视频理解（HVU）所面临的挑战和机遇，探讨相关技术和应用问题。

是否征稿：否

Learning from Procedural Videos and Language: What is Next?

• 项目主页：https://sites.google.com/view/lpvl-cvpr2024

研讨会聚焦于基于语言的程序视频理解所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

Pixel-level Video Understanding in the Wild Challenge

• 项目主页：https://www.vspwdataset.com/Workshop2024

研讨会聚焦于像素级场景理解所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止

What is Next in Video Understanding?

• 项目主页：https://winvu.github.io/cvpr-24/

研讨会聚焦于视频理解所面临的挑战和机遇，探讨相关技术和应用问题。

论文征稿已截止