Search Results for author:
Found 3 papers, 0 papers with code
Shape-centered Representation Learning for Visible-Infrared Person Re-identification
One pertains to the dependence on auxiliary models for shape feature extraction in the inference phase, along with the errors in generated infrared shapes due to the intrinsic modality disparity.
Ranking-based Adaptive Query Generation for DETRs in Crowded Pedestrian Detection
Moreover, to train the rank prediction head better, we propose Soft Gradient L1 Loss.
Characters as Graphs: Recognizing Online Handwritten Chinese Characters via Spatial Graph Convolutional Network
Chinese is one of the most widely used languages in the world, yet online handwritten Chinese character recognition (OLHCCR) remains challenging.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
