C'est La VIE --- Visual Inference & Evaluation
VIE focuses on computer vision, image/video quality assessment and medical image processing.
News
- Ruohua and Zhaochen papers being accepted by AAAI 2024
- Yujia Liu and Chenxi Yang paper being accepted by CVPR 2024
- "ShapeMamba-EM: Fine-Tuning Foundation Model with Local Shape Descriptors and Mamba Blocks for 3D EM Image Segmentation" being accepted by MICCAI 2024
- "Amodal Segmentation for Laparoscopic Surgery Video Instruments" accepted by ICSI 2024 and getting the Best Paper Award
Recent Publications
- DiffAct++: Diffusion Action Segmentation
- Exploring Vulnerabilities of No-Reference Image Quality Assessment Models: A Query-Based Black-Box Method
- GIN: Generative INvariant Shape Prior for Amodal Instance Segmentation
- BLADE: Box-Level Supervised Amodal Segmentation through Directed Expansion
- Evidential Uncertainty-Guided Mitochondria Segmentation for 3D EM Images
- VIPNet: Combining Viewpoint Information and Shape Priors for Instant Multi-view 3D Reconstruction
- Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization
- Causal-IQA: Towards the Generalization of Image Quality Assessment Based on Causal Inference
- ShapeMamba-EM: Fine-Tuning Foundation Model with Local Shape Descriptors and Mamba Blocks for 3D EM Image Segmentation
- PS-Net: human perception-guided segmentation network for EM cell membrane