Yuhang He (Henry)

3D_point_organization. 3D LiDAR Point Cloud Organized as Depth Map, Height Map and Surface Normal Map

RiTTA. Event Relation in Text-to-Audio (TTA) Generation

ResNet_with_IdentityMapping. python script implementation of residual network of identity mapping

Sound3DVDet. Code for WACV24 work for multiview acoustic-visual detection

arrow_road_marking_detection. C++

OpenSound. Various Audio Process Baselines

caffe_triplet_multiple_inputs. Caffe Framework for Triplet Network Ranking

HiFANet. HiFANet for Point Cloud Semantic Segmentation by Aggregating 2D Images

data_augmentation_caffe. common data augmentation methods, implemented in caffe.

image_batch_test_caffe. C++ interface for image batch test in Caffe deep learning platform

Aurelius. Relation aware Text-to-Audio Generation - ICLR26

AwesomeWorldModel. Keep Track of the Advancement of World Model

XShapeEnc. Training-free 2D Shape Encoding

caffe_incremental_add_data. C++ script for incrementally adding new image data to existing leveldb/lmdb database

TensorFlow-MultiGPU-ObjectDetection. TensorFlow Multi-GPU based Object Detection

OpenClustering.

SoundSynp. Sound Source Detection with Multi-Scale Synperiodic Filterbanks

MSRA_residual_net. python implementation of MSRA 18/34/152 layers