International Conference on Image Processing

I SAW: A Self-Attention Weighted Method For Explanation of Visual Transformers

Clustering-Based Psychometric No-Reference Quality Model For Point Cloud Video

Channel-Wise Bit Allocation For Deep Visual Feature Quantization

Deep Learning Classification of Large-Scale Point Clouds: A Case Study On Cuneiform Tablets

Relational Future Captioning Model For Explaining Likely Collisions in Daily Tasks

UCF-CAP, Video Captioning in The Wild

Panoptic-Deeplab-Dva: Improving Panoptic Deeplab With Dual Value Attention and instance Boundary Aware Regression

Subspace Modeling For Fast Out-of-Distribution and Anomaly Detection

Moving Object Detection in Noisy Video Sequences Using Deep Convolutional Disentangled Representations

Measurably Stronger Explanation Reliability Via Model Canonization

Subjective Quality Evaluation of Point Clouds With 3D Stereoscopic Visualization

Learning-Based Lossless Point Cloud Geometry Coding Using Sparse Tensors