Chang Huang

19

Papers

69

Total Citations

Papers (19)

Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction

ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention

Omnidirectional Multi-Object Tracking

Deep Multiple Instance Learning for Image Classification and Auto-Annotation

CNN-RNN: A Unified Framework for Multi-Label Image Classification

RENAS: Reinforced Evolutionary Neural Architecture Search

Mask Scoring R-CNN

Sparse Instance Activation for Real-Time Instance Segmentation

A Deep Visual Correspondence Embedding Model for Stereo Matching Costs

Conditional Random Fields as Recurrent Neural Networks

Look and Think Twice: Capturing Top-Down Visual Attention With Feedback Convolutional Neural Networks

Text Flow: A Unified Text Detection System in Natural Scene Images

CCNet: Criss-Cross Attention for Semantic Segmentation

VAD: Vectorized Scene Representation for Efficient Autonomous Driving

AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception

Learning From Massive Noisy Labeled Data for Image Classification

Multi-Objective Convolutional Learning for Face Labeling

Circuit as Set of Points

How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization