POSTER: A Pyramid Cross-Fusion Transformer Network for Facial Expression Recognition
Comments ICCV Workshop (AMFG) 2023
期刊&会议
ICCV
International Conference on Computer Vision · 会议 · Computer Vision
Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning
Comments Accepted by ICCV 2023
Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches
Comments Accepted to ICCV 2023
Dual Meta-Learning with Longitudinally Generalized Regularization for One-Shot Brain Tissue Segmentation Across the Human Lifespan
Comments ICCV 2023
AerialVLN: Vision-and-Language Navigation for UAVs
Comments Accepted by ICCV 2023
On the Interplay of Convolutional Padding and Adversarial Robustness
Comments Accepted as full paper at ICCV-W 2023 BRAVO
Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction
Comments Published at ICCV 2023, 16 pages including the supplementary material
Revisiting Vision Transformer from the View of Path Ensemble
Comments Accepted by ICCV 2023, oral presentation
SegPrompt: Boosting Open-world Segmentation via Category-level Prompt Learning
Comments Accepted to Proc. Int. Conf. Computer Vision (ICCV) 2023. Code is at: https://github.com/aim-uofa/SegPrompt
BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation
Comments Accepted by ICCV 2023
Tiny and Efficient Model for the Edge Detection Generalization
Comments To Appear in ICCV 2023
Bird's-Eye-View Scene Graph for Vision-Language Navigation
Comments Accepted at ICCV 2023; Project page: https://github.com/DefaultRui/BEV-Scene-Graph
LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment
Comments Accepted as ICCV 2023 paper
SVDFormer: Complementing Point Cloud via Self-view Augmentation and Self-structure Dual-generator
Comments Accepted by ICCV 2023
Dynamic Perceiver for Efficient Visual Recognition
Comments Accepted at ICCV 2023
Efficient 3D Semantic Segmentation with Superpoint Transformer
Comments Accepted at ICCV 2023. Camera-ready version with Appendix. Code available at github.com/drprojects/superpoint_transformer
Neural LiDAR Fields for Novel View Synthesis
Comments ICCV 2023 - camera ready. Project page: https://research.nvidia.com/labs/toronto-ai/nfl/
Diffusion Action Segmentation
Comments ICCV 2023
SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis
Comments Accepted by ICCV 2023, Project page: https://sparsenerf.github.io/
Localizing Object-level Shape Variations with Text-to-Image Diffusion Models
Comments ICCV 2023. Project page at https://orpatashnik.github.io/local-prompt-mixing/
Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images
Comments Accepted to ICCV 2023. Website: whoops-benchmark.github.io
GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving
Comments 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Transparent Shape from a Single View Polarization Image
Comments Proceedings of the IEEE International Conference on Computer Vision, ICCV, 2023
FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods
Comments Accepted at ICCV 2023. Code: https://github.com/visinf/funnybirds
Out-of-Distribution Detection for Monocular Depth Estimation
Comments Accepted to ICCV 2023
Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection
Comments Accepted by ICCV 2023
TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models
Comments ICCV 2023 version
Generalizing Event-Based Motion Deblurring in Real-World Scenarios
Comments Accepted by ICCV 2023
SegDA: Maximum Separable Segment Mask with Pseudo Labels for Domain Adaptive Semantic Segmentation
Comments 11 pages, 4 Tables, 3 Figures, accepted at ICCVW 2023 (ICCV 2023: 4th Workshop on Visual Perception for Navigation in Human Environments)
Dual Aggregation Transformer for Image Super-Resolution
Comments Accepted to ICCV 2023. Code is available at https://github.com/zhengchen1999/DAT
