Modality-Agnostic Debiasing for Single Domain Generalization
Comments To appear in CVPR-2023
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
Upcycling Models under Domain and Category Shift
Comments To appear in CVPR 2023. The code has been made public
Prototype-based Embedding Network for Scene Graph Generation
Comments Accepted by CVPR 2023
Twin Contrastive Learning with Noisy Labels
Comments CVPR 2023
SCPNet: Semantic Scene Completion on Point Cloud
Comments CVPR 2023
Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Images
Comments Accepted by CVPR 2023; Code at https://github.com/HHHedo/IBMIL
Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning
Comments Accepted to CVPR 2023
Dynamic Neural Network for Multi-Task Learning Searching across Diverse Network Topologies
Comments Accepted at CVPR 2023, 13 pages, 10 encapsulated postscript figures
Turning Strengths into Weaknesses: A Certified Robustness Inspired Attack Framework against Graph Neural Networks
Comments Accepted by CVPR 2023
Context-Based Trit-Plane Coding for Progressive Image Compression
Comments Accepted to CVPR 2023
Referring Multi-Object Tracking
Comments Accpeted by CVPR 2023. The dataset and code will be available at https://github.com/wudongming97/RMOT
Perception-Oriented Single Image Super-Resolution using Optimal Objective Estimation
Comments CVPR 2023 accepted. Code and trained models will be available at https://github.com/seungho-snu/SROOE
SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
Comments Accepted by CVPR 2023, Project page: https://sadtalker.github.io, Code: https://github.com/Winfredy/SadTalker
Learning Transferable Spatiotemporal Representations from Natural Script Knowledge
Comments Accepted by CVPR 2023; camera-ready version
Practical Network Acceleration with Tiny Sets
Comments CVPR 2023
CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability
Comments Accepted at the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 (CVPR2023)
Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning
Comments 14 pages, 8 figure, CVPR 2023 accepted
ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction
Comments Accepted by CVPR 2023; Code at https://github.com/ZhengdiYu/Arbitrary-Hands-3D-Reconstruction
Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection
Comments Accepted by CVPR 2023
3D Cinemagraphy from a Single Image
Comments Accepted by CVPR 2023. Project page: https://xingyi-li.github.io/3d-cinemagraphy/
Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation from 2D Supervision
Comments accepted by CVPR 2023
Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detection
Comments Accepted to CVPR 2023, 10 pages, 4 figures
Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization
Comments Accepted by CVPR 2023
Occlusion-Aware Instance Segmentation via BiLayer Network Architectures
Comments Extended version of "Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers", CVPR 2021 (arXiv:2103.12340)
Masked Image Modeling with Local Multi-Scale Reconstruction
Comments CVPR 2023
Diversity-Measurable Anomaly Detection
Comments Accepted by CVPR 2023
CoralStyleCLIP: Co-optimized Region and Layer Selection for Image Editing
Comments CVPR 2023
NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging
Comments Accepted at CVPR 2023
Multimodal Prompting with Missing Modalities for Visual Recognition
Comments Accepted by CVPR 2023. Codes are available at https://github.com/YiLunLee/Missing_aware_prompts
MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices
Comments To be appeared at CVPR 2023
