AVVision

Gesture Recognition with Keypoint and Radar Stream Fusion for Automated Vehicles

[Keynote Talk by Wei Liu] Achievements and Open Questions for Autonomous Driving

Effectiveness of Function Matching in Driving Scene Recognition

Number-Adaptive Prototype Learning for 3D Point Cloud Semantic Segmentation

SIM2E: Benchmarking the Group Equivariant Capability of Correspondence Matching Algorithms

Learning 3D Semantics from Pose-Noisy 2D Images with Hierarchical Full Attention Network

RPR-Net: A Point Cloud-based Rotation-awareLarge Scale Place Recognition Network

Ego-Motion Compensation of Range-Beam-Doppler Radar Data for Object Detection

SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking

MCIP: Multi-Stream Network for Pedestrian Crossing Intention Prediction

Human-vehicle Cooperative Visual Perception for Autonomous Driving under Complex Traffic Environment

Leveraging Geometric Structure for Label-efficient Semi-supervised Scene Segmentation

Joint Prediction of Amodal and Visible Semantic Segmentation for Automated Driving

Lane Change Classification and Prediction with Action Recognition Networks

Plausibility Verification For 3D Object Detectors Using Energy-Based Optimization

An improved lightweight network based on YOLOv5s for object detection in autonomous driving

BlindSpotNet: Seeing Where We Cannot See

Panoptic Segmentation of 4D LiDAR Using Spatio-Temporal Object Proposal Generation and Aggregation

SDVTracker: Real-Time Multi-Sensor Association and Tracking for Self-Driving Vehicles

SA-Det3D: Self-Attention Based Context-Aware 3D Object Detection

Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous Environments

Frustum-PointPillars: A Multi-Stage Approach for 3D Object Detection Using RGB Camera and LiDAR

RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes

Monocular 3D Localization of Vehicles in Road Scenes

DriPE: A Dataset for Human Pose Estimation in Real-World Driving Settings

SCARF: A Semantic Constrained Attention Refinement Network for Semantic Segmentation

CDAda: A Curriculum Domain Adaptation for Nighttime Semantic Segmentation

Graph Convolutional Networks for 3D Object Detection on Radar Data

CenterPoly: Real-Time Instance Segmentation Using Bounding Polygons

Few-Shot Batch Incremental Road Object Detection via Detector Fusion