MAS: Towards Resource-Efficient Federated Multiple-Task Learning
Comments ICCV'23. arXiv admin note: substantial text overlap with arXiv:2207.04202
期刊&会议
ICCV
International Conference on Computer Vision · 会议 · Computer Vision
StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces
Comments ICCV 2023. Code: https://github.com/williamyang1991/StyleGANEX Project page: https://www.mmlab-ntu.com/project/styleganex/
Cascade-DETR: Delving into High-Quality Universal Object Detection
Comments Accepted in ICCV 2023. Our code and models will be released at https://github.com/SysCV/cascade-detr
Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image
Comments Accepted to ICCV 2023. Won the championship in the 2nd Monocular Depth Estimation Challenge. The code is available at https://github.com/YvanYin/Metric3D
HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces
Comments Accepted for publication in ICCV 2023. Project page: https://stelabou.github.io/hyperreenact.github.io/ Code: https://github.com/StelaBou/HyperReenact
See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data
Comments Accepted by ICCV 2023
Lighting up NeRF via Unsupervised Decomposition and Enhancement
Comments ICCV 2023. Project website: https://whyy.site/paper/llnerf
Physics-Driven Turbulence Image Restoration with Stochastic Refinement
Comments Accepted by ICCV 2023
CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation
Comments Accepted by ICCV 2023
Towards Viewpoint-Invariant Visual Recognition via Adversarial Training
Comments Accepted by ICCV 2023
LA-Net: Landmark-Aware Learning for Reliable Facial Expression Recognition under Label Noise
Comments accepted by ICCV 2023
Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer
Comments Accepted to ICCV 2023
Chordal Averaging on Flag Manifolds and Its Applications
Comments Appears at ICCV 2023
Event Camera Data Pre-training
Comments Accepted by ICCV 2023
Unsupervised Accuracy Estimation of Deep Visual Models using Domain-Adaptive Adversarial Perturbation without Source Samples
Comments Accepted to ICCV 2023
MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions
Comments Accepted by ICCV 2023
Generative Prompt Model for Weakly Supervised Object Localization
Journal ref International Conference on Computer Vision Conference (ICCV2023)
Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentation
Comments Accepted to ICCV 2023
MagicFusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion Models
Comments Accepted by ICCV 2023
Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition
Comments Accepted by ICCV 2023
Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
Comments Accepted by ICCV 2023
GlobalMapper: Arbitrary-Shaped Urban Layout Generation
Comments Accepted by ICCV 2023
EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting
Comments Accepted at ICCV 2023
Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells
Comments Accepted by ICCV 2023
Learning Adaptive Neighborhoods for Graph Neural Networks
Comments ICCV 2023
Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond
Comments ICCV 2023
Local or Global: Selective Knowledge Assimilation for Federated Learning with Limited Labels
Comments To appear in the proceedings of ICCV 2023
Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer
Comments ICCV 2023
Multimodal Distillation for Egocentric Action Recognition
Comments Accepted at ICCV 2023; Codebase released at https://github.com/gorjanradevski/multimodal-distillation
Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learning
Comments Accepted in ICCV 2023
