International Conference on Image Processing

3D Clues Guided Convolution For Depth Completion

D-CBRS: Accounting For intra-Class Diversity in Continual Learning

Truncated Lottery Ticket For Deep Pruning

CYEDA: Cycle-Object Edge Consistency Domain Adaptation

Dynamic Template Update For Visual Object Tracking

Geometry Partitioning With Motion Vector Difference For Video Coding

Soli Radar Image-Based Target Localization

NCTR: Neighborhood Consensus Transformer For Feature Matching

Clustering By Directly Disentangling Latent Space

Improving Generalization of Reinforcement Learning Using A Bilinear Policy Network

CONMW Transformer: A General Vision Transformer Backbone With Merged-Window Attention

MAANU-NET: Multi-Level Attention and Atrous Pyramid Nested U-Net For Wrecked Objects Segmentation in Forward-Looking Sonar Images