Search Results for author:
Found 5 papers, 0 papers with code
TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model
Taking advantage of the fine-tuned language model on scene recognition benchmarks and the paradigm of text block detection, extensive experiments demonstrate the superior performance of our scene text spotter across multiple public benchmarks.
Heavy-Tailed Regularization of Weight Matrices in Deep Neural Networks
To capitalize on this discovery, we introduce a novel regularization technique, termed Heavy-Tailed Regularization, which explicitly promotes a more heavy-tailed spectrum in the weight matrix through regularization.
Spatially informed clustering, integration, and deconvolution of spatial transcriptomics with GraphST
Lastly, compared to other methods, GraphST’s cell type deconvolution achieved higher accuracy on simulated data and better captured spatial niches such as the germinal centers of the lymph node in experimentally acquired data.
Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation
This group-wise structural correlation can be explored to improve the accuracy and robustness of human pose estimation.
Ranked #1 on
Multi-Person Pose Estimation
on COCO test-dev
Provable More Data Hurt in High Dimensional Least Squares Estimator
Furthermore, the finite-sample distribution and the confidence interval of the prediction risk are provided.
