13 citations · 37 across the 18 of their papers we have counts for
15 papers · 1 filter
NavAble: A Large-Scale Dataset and Synthetic Data Generation Pipeline for Blind Navigation
Hochul Hwang, Jahir Sadik Monon, Soowan Yang +9
Reliable recognition of accessibility-critical objects (e.g., audible pedestrian signals, door-activation buttons, and handrails) is essential for assistive navigation technologies…
Time-Aware Assistive Navigation
Masaki Kuribayashi, Zhongkai Shangguan, Eshed Ohn-Bar
Can interactive vision-and-language agents learn not just what to say but also \textbf{\textit{when}} to say it? Current language models rarely plan over whether and when to realiz…
DriveQA: Passing the Driving Knowledge Test
Maolin Wei, Wanzhou Liu, Eshed Ohn-Bar
If a Large Language Model (LLM) were to take a driving knowledge test today, would it pass? Beyond standard spatial and visual question-answering (QA) tasks on current autonomous d…
ZeroVO: Visual Odometry with Minimal Assumptions
Lei Lai, Zekai Yin, Eshed Ohn-Bar
We introduce ZeroVO, a novel visual odometry (VO) algorithm that achieves zero-shot generalization across diverse cameras and environments, overcoming limitations in existing metho…
Text to Blind Motion
Hee Jae Kim, Kathakoli Sengupta, Masaki Kuribayashi +2
People who are blind perceive the world differently than those who are sighted, which can result in distinct motion characteristics. For instance, when crossing at an intersection,…
XVO: Generalized Visual Odometry via Cross-Modal Self-Training
Lei Lai, Zhongkai Shangguan, Jimuyang Zhang +1
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 sett…
Learning to Drive Anywhere
Ruizhao Zhu, Peng Huang, Eshed Ohn-Bar +1
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. In contra…
Coaching a Teachable Student
Jimuyang Zhang, Zanming Huang, Eshed Ohn-Bar
We propose a novel knowledge distillation framework for effectively teaching a sensorimotor student agent to drive from the supervision of a privileged teacher agent. Current disti…
SelfD: Self-Learning Large-Scale Driving Policies From the Web
Jimuyang Zhang, Ruizhao Zhu, Eshed Ohn-Bar
Effectively utilizing the vast amounts of ego-centric navigation data that is freely available on the internet can advance generalized intelligent systems, i.e., to robustly scale…
Learning by Watching
Jimuyang Zhang, Eshed Ohn-Bar
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. In…
Label Efficient Visual Abstractions for Autonomous Driving
Aseem Behl, Kashyap Chitta, Aditya Prakash +2
It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmen…
Driver Hand Localization and Grasp Analysis: A Vision-based Real-time Approach
Siddharth, Akshay Rangesh, Eshed Ohn-Bar +1
Extracting hand regions and their grasp information from images robustly in real-time is critical for occupants' safety and in-vehicular infotainment applications. It must however,…
To Boost or Not to Boost? On the Limits of Boosted Trees for Object Detection
Eshed Ohn-Bar, Mohan M. Trivedi
We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. d…
Multi-scale Volumes for Deep Object Detection and Localization
Eshed Ohn-Bar, M. M. Trivedi
This study aims to analyze the benefits of improved multi-scale reasoning for object detection and localization with deep convolutional neural networks. To that end, an efficient a…
Learning to Detect Vehicles by Clustering Appearance Patterns
Eshed Ohn-Bar, Mohan M. Trivedi
This paper studies efficient means for dealing with intra-category diversity in object detection. Strategies for occlusion and orientation handling are explored by learning an ense…