Area of research
Computer Vision and Pattern Recognition · Automotive Engineering
Research interest
Research interests include Video Surveillance and Tracking Methods, Autonomous Vehicle Technology and Safety, Advanced Vision and Imaging, and Advanced Neural Network Applications.
A New Perspective on AI Safety Through Control Theory Methodologies
Transfer Learning from Simulated to Real Scenes for Monocular 3D Object Detection
Lights as Points: Learning to Look at Vehicle Substructures With Anchor-Free Object Detection
Gaze Preserving CycleGANs for Eyeglass Removal and Persistent Gaze Estimation
LaneAF: Robust Multi-Lane Detection With Affinity Fields
Trajectory Prediction in Autonomous Driving With a Lane Heading Auxiliary Loss
Looking at the Driver/Rider in Autonomous Vehicles to Predict Take-Over Readiness
Scene Compliant Trajectory Forecast With Agent-Centric Spatio-Temporal Grids
Looking at Hands in Autonomous Vehicles: A ConvNet Approach Using Part Affinity Fields
Ground Plane Polling for 6DoF Pose Estimation of Objects on the Road
No Blind Spots: Full-Surround Multi-Object Tracking for Autonomous Vehicles Using Cameras and LiDARs
No Blind Spots: Full-Surround Multi-Object Tracking for Autonomous Vehicles Using Cameras and LiDARs
Looking at Vehicles in the Night: Detection and Dynamics of Rear Lights
How Would Surround Vehicles Move? A Unified Framework for Maneuver Classification and Motion Prediction
Dynamics of Driver's Gaze: Explorations in Behavior Modeling and Maneuver Prediction
Convolutional Social Pooling for Vehicle Trajectory Prediction
On generalizing driver gaze zone estimation using convolutional neural networks
Vision for Looking at Traffic Lights: Issues, Survey, and Perspectives
Computer vision for assistive technologies
To boost or not to boost? On the limits of boosted trees for object detection
Surround vehicles trajectory analysis with recurrent neural networks
Looking at Vehicles in the Night: Detection and Dynamics of Rear Lights
RefineNet: Refining Object Detectors for Autonomous Driving
Learning to Detect Vehicles by Clustering Appearance Patterns
On Performance Evaluation of Driver Hand Detection Algorithms: Challenges, Dataset, and Metrics
Traffic Light Detection: A Learning Algorithm and Evaluations on Challenging Dataset
Trajectory analysis and prediction for improved pedestrian safety: Integrated framework and evaluations
On surveillance for safety critical events: In-vehicle video networks for predictive driver assistance systems
Multipart Vehicle Detection Using Symmetry-Derived Analysis and Active Learning