International Conference on Image Processing

Multi-View 3D Reconstruction From Video With Transformer

Two Distillation Perspectives Based On Tanimoto Coefficient

Transformer Visual Tracker Based On Template Features Corresponding To Foreground Region

Multiclass-Sgcn: Sparse Graph-Based Trajectory Prediction With Agent Class Embedding

Hologram Super-Resolution Using Dual-Generator Gan

investigating Explainable Artificial intelligence For Mri-Based Classification of Dementia: A New Stability Criterion For Explainable Methods

Does Physical interpretability of Observation Map Improve Photometric Stereo Networks?

Exploring Occlusion-Sensitive Deep Network For Single-View 3D Face Reconstruction

Scanpath Prediction Via Semantic Representation of The Scene

Reduced Dependency Fast Unsupervised 3D Face Reconstruction

Font Watermarking Network For Text Images

Dekrv2: More Accurate or Fast Than Dekr