Skip to main content

🏢 University of Arkansas

EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding
·2574 words·13 mins· loading · loading
AI Generated Computer Vision Image Segmentation 🏢 University of Arkansas
EAGLE: A novel unsupervised cross-view adaptation method for semantic segmentation achieves state-of-the-art performance by efficiently modeling geometric structural changes across different camera vi…
DINTR: Tracking via Diffusion-based Interpolation
·2223 words·11 mins· loading · loading
Computer Vision Object Detection 🏢 University of Arkansas
DINTR: A novel diffusion-based object tracker surpasses existing methods by using efficient interpolation, achieving superior performance across diverse benchmarks.
CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos
·2627 words·13 mins· loading · loading
Computer Vision Scene Understanding 🏢 University of Arkansas
CYCLO: A novel cyclic graph transformer excels at multi-object relationship modeling in aerial videos.