Qian Zhang

34

Papers

202

Total Citations

Papers (34)

Learning Where to Focus for Efficient Video Object Detection

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

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

Epona: Autoregressive Diffusion World Model for Autonomous Driving

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

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

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

6D Dynamic Camera Relocalization From Single Reference Image

RENAS: Reinforced Evolutionary Neural Architecture Search

Densely Connected Search Space for More Flexible Neural Architecture Search

AugFPN: Improving Multi-Scale Feature Learning for Object Detection

Temporal-Context Enhanced Detection of Heavily Occluded Pedestrians

Pseudo Facial Generation With Extreme Poses for Face Recognition

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

Sparse Instance Activation for Real-Time Instance Segmentation

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

Cross-Image Relational Knowledge Distillation for Semantic Segmentation

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

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

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

Fine-Grained Change Detection of Misaligned Scenes With Varied Illuminations

Progressive Sparse Local Attention for Video Object Detection

View-Consistent 4D Light Field Superpixel Segmentation

Stacked Homography Transformations for Multi-View Pedestrian Detection

Hierarchical Aggregation for 3D Instance Segmentation

VAD: Vectorized Scene Representation for Efficient Autonomous Driving

MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition

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

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

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

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

Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration

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

Circuit as Set of Points