CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model
Comments Accepted by CVPR 2023
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification
Comments CVPR 2023
Adversarially Robust Neural Architecture Search for Graph Neural Networks
Comments Accepted as a conference paper at CVPR 2023
Deep Prototypical-Parts Ease Morphological Kidney Stone Identification and are Competitively Robust to Photometric Perturbations
Comments This paper has been accepted at the LatinX in Computer Vision Research Workshop at CVPR2023 as a full paper and it will appear on the CVPR proceedings
RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors
Comments Acceptted by CVPR 2023
Benchmarking the Robustness of Quantized Models
Comments Workshop at IEEE Conference on Computer Vision and Pattern Recognition 2023
GANHead: Towards Generative Animatable Neural Head Avatars
Comments Camera-ready for CVPR 2023. Project page: https://wsj-sjtu.github.io/GANHead/
Delving into Discrete Normalizing Flows on SO(3) Manifold for Probabilistic Rotation Modeling
Comments CVPR 2023
Exploring Data Geometry for Continual Learning
Comments CVPR 2023
System-status-aware Adaptive Network for Online Streaming Video Understanding
Comments Accepted to CVPR 2023
Class-Incremental Exemplar Compression for Class-Incremental Learning
Comments Accepted to CVPR 2023
Intrinsic Physical Concepts Discovery with Object-Centric Predictive Models
Comments Accepted to Computer Vision and Pattern Recognition (CVPR)2023
Improving GAN Training via Feature Space Shrinkage
Comments Accepted by CVPR'2023. Code and Demo are available at https://github.com/WentianZhang-ML/AdaptiveMix
HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization
Comments Accepted to CVPR 2023
DiffPose: Toward More Reliable 3D Pose Estimation
Comments Accepted to CVPR 2023
CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion
Comments Accepted by CVPR 2023
SUPRA: Superpixel Guided Loss for Improved Multi-modal Segmentation in Endoscopy
Comments This work has been accepted at the LatinX in Computer Vision Research Workshop at CVPR 2023
Improving Data-Efficient Fossil Segmentation via Model Editing
Comments CVPR 2023 Workshop on Learning with Limited Labelled Data for Image and Video Understanding
MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining
Comments CVPR 2023, code is available at https://github.com/LightDXY/MaskCLIP
Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering
Comments CVPR 2023 Workshop L3D-IVU
Meta-causal Learning for Single Domain Generalization
Comments Accepted by CVPR 2023
DATE: Domain Adaptive Product Seeker for E-commerce
Comments This paper was accepted by CVPR 2023
A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image
Comments CVPR 2023. The code is avaliable at https://github.com/ChanglongJiangGit/A2J-Transformer
Asynchronous Federated Continual Learning
Comments CVPR 2023 FedVision Workshop (CVPRW)
Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution
Comments Accepted by CVPR 2023
Leveraging GANs for data scarcity of COVID-19: Beyond the hype
Comments submitted to 2023 CVPR workshop on Generative Models for Computer Vision
What Affects Learned Equivariance in Deep Image Recognition Models?
Comments Accepted at CVPR workshop L3D-IVU 2023
Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection
Comments Accepted to CVPR 2023
Large-scale Robustness Analysis of Video Action Recognition Models
Comments Accepted in 2023 Conference on Computer Vision and Pattern Recognition (CVPR)
UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection
Comments Accepted at CVPR 2022. Paper + supplementary (15 pages, 9 figures)
