Qian Zhang

Affiliations

Horizon Robotics

papers

3,851

total citations

papers (29)

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

ICML 2024arXiv

1,457

citations

Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentation

CVPR 2022arXiv

citations

MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition

ECCV 2022arXiv

citations

BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation

CVPR 2023arXiv

citations

Learning Where to Focus for Efficient Video Object Detection

ECCV 2020arXiv

citations

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

ECCV 2024arXiv

citations

GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving

CVPR 2025arXiv

citations

RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

NEURIPS 2025arXiv

citations

Epona: Autoregressive Diffusion World Model for Autonomous Driving

ICCV 2025arXiv

citations

Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery

AAAI 2024arXiv

citations

Enhancing RAW-to-sRGB with Decoupled Style Structure in Fourier Domain

AAAI 2024arXiv

citations

Multi-Granularity Archaeological Dating of Chinese Bronze Dings Based on a Knowledge-Guided Relation Graph

CVPR 2023arXiv

citations

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

AAAI 2025arXiv

citations

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

CVPR 2022arXiv

citations

Circuit as Set of Points

NEURIPS 2023arXiv

citations

Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration

ICCV 2025arXiv

citations

MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation

ICCV 2025arXiv

citations

Temporal-Context Enhanced Detection of Heavily Occluded Pedestrians

CVPR 2020

citations

SU-RGS: Relightable 3D Gaussian Splatting from Sparse Views under Unconstrained Illuminations

ICCV 2025

citations

Pseudo Facial Generation With Extreme Poses for Face Recognition

CVPR 2021

citations

Stacked Homography Transformations for Multi-View Pedestrian Detection

ICCV 2021

citations

BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation

CVPR 2023

citations

Qian Zhang

Affiliations

papers (29)

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

VAD: Vectorized Scene Representation for Efficient Autonomous Driving

AugFPN: Improving Multi-Scale Feature Learning for Object Detection

Cross-Image Relational Knowledge Distillation for Semantic Segmentation

Hierarchical Aggregation for 3D Instance Segmentation

Sparse Instance Activation for Real-Time Instance Segmentation

DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving

Densely Connected Search Space for More Flexible Neural Architecture Search

Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentation

MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition

BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation

Learning Where to Focus for Efficient Video Object Detection

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

GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving

RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

Epona: Autoregressive Diffusion World Model for Autonomous Driving

Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery

Enhancing RAW-to-sRGB with Decoupled Style Structure in Fourier Domain

Multi-Granularity Archaeological Dating of Chinese Bronze Dings Based on a Knowledge-Guided Relation Graph

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

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

Circuit as Set of Points

Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration

MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation

Temporal-Context Enhanced Detection of Heavily Occluded Pedestrians

SU-RGS: Relightable 3D Gaussian Splatting from Sparse Views under Unconstrained Illuminations

Pseudo Facial Generation With Extreme Poses for Face Recognition

Stacked Homography Transformations for Multi-View Pedestrian Detection

BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation

papers (29)

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

VAD: Vectorized Scene Representation for Efficient Autonomous Driving

AugFPN: Improving Multi-Scale Feature Learning for Object Detection

Cross-Image Relational Knowledge Distillation for Semantic Segmentation

Hierarchical Aggregation for 3D Instance Segmentation

Sparse Instance Activation for Real-Time Instance Segmentation

DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving

Densely Connected Search Space for More Flexible Neural Architecture Search

Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentation

MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition

BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation

Learning Where to Focus for Efficient Video Object Detection

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

GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving

RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

Epona: Autoregressive Diffusion World Model for Autonomous Driving

Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery

Enhancing RAW-to-sRGB with Decoupled Style Structure in Fourier Domain

Multi-Granularity Archaeological Dating of Chinese Bronze Dings Based on a Knowledge-Guided Relation Graph

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

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

Circuit as Set of Points

Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration

MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation

Temporal-Context Enhanced Detection of Heavily Occluded Pedestrians

SU-RGS: Relightable 3D Gaussian Splatting from Sparse Views under Unconstrained Illuminations

Pseudo Facial Generation With Extreme Poses for Face Recognition

Stacked Homography Transformations for Multi-View Pedestrian Detection

BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation