A Visual Model Of Self-Attention: Transformers Work Differently Now

Early-2026 explainer reframes transformer attention: tokenized text becomes Q/K/V self-attention maps, not linear prediction.
IEEE

THT-Net: A Novel Object Tracking Model Based on Global-Local Transformer Hashing and Tensor Analysis

Abstract: The object point clouds acquired by the original LiDAR are inherently sparse and incomplete, resulting in suboptimal single object tracking (SOT) precision for 3D bounding boxes, especially ...
GitHub

[ICCV2025] CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillation

Official implementation of our CleanPose, the first solution to mitigate the confoundering effect in category-level pose estimation via causal learning and knowledge distillation. You can generate the ...
IEEE

DADSR: Degradation-Aware Diffusion Super-Resolution Model for Object-Level SAR Image

Abstract: Synthetic aperture radar (SAR) plays a vital role in remote sensing applications but suffers from coupled degradation problems, including resolution deterioration, speckle noise, and ...