Search Results for author:
Found 15 papers, 3 papers with code
Learning to Detect Vehicles by Clustering Appearance Patterns
This paper studies efficient means for dealing with intra-category diversity in object detection.
Multi-scale Volumes for Deep Object Detection and Localization
This study aims to analyze the benefits of improved multi-scale reasoning for object detection and localization with deep convolutional neural networks.
To Boost or Not to Boost? On the Limits of Boosted Trees for Object Detection
We aim to study the modeling limitations of the commonly employed boosted decision trees classifier.
Ranked #33 on
Face Detection
on WIDER Face (Medium)
Driver Hand Localization and Grasp Analysis: A Vision-based Real-time Approach
This work addresses the task of accurately localizing driver hands and classifying the grasp state of each hand.
Personalized Dynamics Models for Adaptive Assistive Navigation Systems
Consider an assistive system that guides visually impaired users through speech and haptic feedback to their destination.
Human-Interactive Subgoal Supervision for Efficient Inverse Reinforcement Learning
The learning process is interactive, with a human expert first providing input in the form of full demonstrations along with some subgoal states.
Future Near-Collision Prediction from Monocular Video: Feasibility, Dataset, and Challenges
Our results show that our proposed multi-stream CNN is the best model for predicting time to near-collision.
Robotics
Label Efficient Visual Abstractions for Autonomous Driving
Beyond label efficiency, we find several additional training benefits when leveraging visual abstractions, such as a significant reduction in the variance of the learned policy when compared to state-of-the-art end-to-end driving models.
Learning Situational Driving
Motivated by this observation, we develop a framework for learning a situational driving policy that effectively captures reasoning under varying types of scenarios.
X-World: Accessibility, Vision, and Autonomy Meet
We tackle inherent data scarcity by leveraging a simulation environment to spawn dynamic agents with various mobility aids.
Learning by Watching
When in a new situation or geographical location, human drivers have an extraordinary ability to watch others and learn maneuvers that they themselves may have never performed.
SelfD: Self-Learning Large-Scale Driving Policies From the Web
However, it is difficult to directly leverage such large amounts of unlabeled and highly diverse data for complex 3D reasoning and planning tasks.
Coaching a Teachable Student
We propose a novel knowledge distillation framework for effectively teaching a sensorimotor student agent to drive from the supervision of a privileged teacher agent.
Ranked #6 on
CARLA longest6
on CARLA
Learning to Drive Anywhere
Human drivers can seamlessly adapt their driving decisions across geographical locations with diverse conditions and rules of the road, e. g., left vs. right-hand traffic.
XVO: Generalized Visual Odometry via Cross-Modal Self-Training
We propose XVO, a semi-supervised learning method for training generalized monocular Visual Odometry (VO) models with robust off-the-self operation across diverse datasets and settings.
