Hierarchical Contrastive Learning for Pattern-Generalizable Image Corruption Detection
Comments ICCV 2023
期刊&会议
ICCV
International Conference on Computer Vision · 会议 · Computer Vision
Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation
Comments ICCV 2023. Project page: http://val.cds.iisc.ac.in/DSiT-SFDA
LDL: Line Distance Functions for Panoramic Localization
Comments Accepted to ICCV 2023
Prior-guided Source-free Domain Adaptation for Human Pose Estimation
Comments Accepted at ICCV 2023
Disjoint Pose and Shape for 3D Face Reconstruction
Comments ICCV workshops 2023
Late Stopping: Avoiding Confidently Learning from Mislabeled Examples
Comments Accepted by ICCV 2023
Beyond One-to-One: Rethinking the Referring Image Segmentation
Comments ICCV 2023
Point-Query Quadtree for Crowd Counting, Localization, and More
Comments Accepted by ICCV 2023
Generalized Lightness Adaptation with Channel Selective Normalization
Comments Accepted to ICCV 2023. Code: https://github.com/mdyao/CSNorm/
MST-compression: Compressing and Accelerating Binary Neural Networks with Minimum Spanning Tree
Comments 11 pages, 9 figures, ICCV 2023
VQA Therapy: Exploring Answer Differences by Visually Grounding Answers
Comments IEEE/CVF International Conference on Computer Vision
DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving
Comments Accepted by ICCV 2023 (Oral). Code url: https://github.com/OpenDriveLab/DriveAdapter
Handwritten and Printed Text Segmentation: A Signature Case Study
Comments Accepted for publication in ICCV 2023. Updated version with 17 pages including main text and appendecies
Bayesian Optimization Meets Self-Distillation
Comments ICCV 2023 accepted
The Devil is in the Upsampling: Architectural Decisions Made Simpler for Denoising with Deep Image Prior
Comments Accepted to ICCV 2023
Pretrained Language Models as Visual Planners for Human Assistance
Comments Accepted at ICCV 2023
No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier
Comments Accepted by ICCV 2023
SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving
Comments Accepted to ICCV 2023. Code is available at https://github.com/weiyithu/SurroundOcc
EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries
Comments ICCV 2023
Local Context-Aware Active Domain Adaptation
Comments Accepted by ICCV 2023
Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning
Comments Published in ICCV 2023. The code is available at https://github.com/SimingYan/IAE
Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers
Comments ICCV 2023
Harvard Glaucoma Detection and Progression: A Multimodal Multitask Dataset and Generalization-Reinforced Semi-Supervised Learning
Comments ICCV 2023
ConSlide: Asynchronous Hierarchical Interaction Transformer with Breakup-Reorganize Rehearsal for Continual Whole Slide Image Analysis
Comments To be appeared in ICCV 2023
GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Clouds
Comments 13pages,14figures. Accepted by ICCV 2023
IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization
Comments Accepted by ICCV 2023, selected for an Oral presentation
Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Model
Comments Accepted by ICCV 2023
Benchmarking Data Efficiency and Computational Efficiency of Temporal Action Localization Models
Comments Accepted to the CVEU workshop at ICCV 2023
Preserving Modality Structure Improves Multi-Modal Learning
Comments Accepted at ICCV 2023
Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training
Comments 10 pages, 6 figures. Accepted in ICCV 2023
