virtual conference icip 2021

U-Noise: Learnable Noise Masks For Interpretable Image Segmentation

Get To The Point: Content Classification Of Animated Graphics Interchange Formats With Key-Frame Attention

Weight Reparametrization For Budget-Aware Network Pruning

Positional Encoding: Improving Class-Imbalanced Motorcycle Helmet Use Classification

Sparse And Structured Visual Attention

Perceptually-Weighted Cnn For 360-Degree Image Quality Assessment Using Visual Scan-Path And Jnd

Attend, Correct And Focus: A Bidirectional Correct Attention Network For Image-Text Matching

A Parameter Efficient Multi-Scale Capsule Network

Affine Non-Negative Collaborative Representation For Deep Metric Learning

Cross-Domain Recommendation Method Based On Multi-Layer Graph Analysis With Visual Information

Vvs: Action Recognition With Virtual View Synthesis

Task-Agnostic Continual Learning Using Base-Child Classifiers