Search Results for author:
Found 9 papers, 6 papers with code
At Which Training Stage Does Code Data Help LLMs Reasoning?
Inspired by the great success of code data in training LLMs, we naturally wonder at which training stage introducing code data can really help LLMs reasoning.
GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer
They seek correspondences over downsampled superpoints, which are then propagated to dense points.
Ranked #5 on
Point Cloud Registration
on FP-O-H
Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registration
We first design a local spatial consistency measure over the deformation graph of the point cloud, which evaluates the spatial compatibility only between the correspondences in the vicinity of a graph node.
Wound Segmentation with Dynamic Illumination Correction and Dual-view Semantic Fusion
Wound image segmentation is a critical component for the clinical diagnosis and in-time treatment of wounds.
Trusted Multi-Scale Classification Framework for Whole Slide Image
Leveraging the Vision Transformer as the backbone for multi branches, our framework can jointly classification modeling, estimating the uncertainty of each magnification of a microscope and integrate the evidence from different magnification.
Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast
We present an approach to learn voice-face representations from the talking face videos, without any identity labels.
Geometric Transformer for Fast and Robust Point Cloud Registration
Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds.
Learning Environmental Sounds with Multi-scale Convolutional Neural Network
For leveraging the waveform-based features and spectrogram-based features in a single model, we introduce two-phase method to fuse the different features.
Sound Audio and Speech Processing
hi-RF: Incremental Learning Random Forest for large-scale multi-class Data Classification
Most traditional methods struggle to balance the precision and computational burden when data and its number of classes increased.
