Search Results for author: Henrik I. Christensen

Found 16 papers, 6 papers with code

Occlusion-Aware 2D and 3D Centerline Detection for Urban Driving via Automatic Label Generation

no code implementations3 Nov 2023 David Paz, Narayanan E. Ranganatha, Srinidhi K. Srinivas, Yunchao Yao, Henrik I. Christensen

This research work seeks to explore and identify strategies that can determine road topology information in 2D and 3D under highly dynamic urban driving scenarios.

Occlusion Handling

FashionNTM: Multi-turn Fashion Image Retrieval via Cascaded Memory

no code implementations ICCV 2023 Anwesan Pal, Sahil Wadhwa, Ayush Jaiswal, Xu Zhang, Yue Wu, Rakesh Chada, Pradeep Natarajan, Henrik I. Christensen

Extensive evaluation results show that our proposed method outperforms the previous state-of-the-art algorithm by 50. 5%, on Multi-turn FashionIQ -- the only existing multi-turn fashion dataset currently, in addition to having a relative improvement of 12. 6% on Multi-turn Shoes -- an extension of the single-turn Shoes dataset that we created in this work.

Image Retrieval Retrieval

3D Scene Graph Prediction on Point Clouds Using Knowledge Graphs

no code implementations13 Aug 2023 Yiding Qiu, Henrik I. Christensen

3D scene graph prediction is a task that aims to concurrently predict object classes and their relationships within a 3D environment.

Graph Generation Knowledge Graphs +1

CLiNet: Joint Detection of Road Network Centerlines in 2D and 3D

no code implementations4 Feb 2023 David Paz, Srinidhi Kalgundi Srinivas, Yunchao Yao, Henrik I. Christensen

This work introduces a new approach for joint detection of centerlines based on image data by localizing the features jointly in 2D and 3D.

3D Depth Estimation

Robust Human Identity Anonymization using Pose Estimation

1 code implementation10 Jan 2023 Hengyuan Zhang, Jing-Yan Liao, David Paz, Henrik I. Christensen

Many outdoor autonomous mobile platforms require more human identity anonymized data to power their data-driven algorithms.

Face Detection Pose Estimation

Meta-Modeling of Assembly Contingencies and Planning for Repair

no code implementations12 Mar 2021 Priyam Parashar, Aayush Naik, Jiaming Hu, Henrik I. Christensen

The World Robotics Challenge (2018 & 2020) was designed to challenge teams to design systems that are easy to adapt to new tasks and to ensure robust operation in a semi-structured environment.

Looking at the right stuff: Guided semantic-gaze for autonomous driving

no code implementations24 Nov 2019 Anwesan Pal, Sayan Mondal, Henrik I. Christensen

In recent years, predicting driver's focus of attention has been a very active area of research in the autonomous driving community.

Autonomous Driving Saliency Prediction

DEDUCE: Diverse scEne Detection methods in Unseen Challenging Environments

1 code implementation1 Aug 2019 Anwesan Pal, Carlos Nieto-Granda, Henrik I. Christensen

In recent years, there has been a rapid increase in the number of service robots deployed for aiding people in their daily activities.

Scene Recognition Visual Place Recognition

How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?

1 code implementation28 Mar 2019 Quan Vuong, Sharad Vikram, Hao Su, Sicun Gao, Henrik I. Christensen

A human-specified design choice in domain randomization is the form and parameters of the distribution of simulated environments.

Reinforcement Learning (RL)

Purely Geometric Scene Association and Retrieval - A Case for Macro Scale 3D Geometry

no code implementations3 Aug 2018 Rahul Sawhney, Fuxin Li, Henrik I. Christensen, Charles L. Isbell

We show how it can be employed to select a diverse set of data frames which have structurally similar content, and how to validate whether views with similar geometric content are from the same scene.

Retrieval

Distributed Mapping with Privacy and Communication Constraints: Lightweight Algorithms and Object-based Models

1 code implementation11 Feb 2017 Siddharth Choudhary, Luca Carlone, Carlos Nieto, John Rogers, Henrik I. Christensen, Frank Dellaert

Our field tests show that the combined use of our distributed algorithms and object-based models reduces the communication requirements by several orders of magnitude and enables distributed mapping with large teams of robots in real-world problems.

Sensor Fusion

StuffNet: Using 'Stuff' to Improve Object Detection

1 code implementation19 Oct 2016 Samarth Brahmbhatt, Henrik I. Christensen, James Hays

Through experiments on Pascal VOC 2007 and 2012, we demonstrate the effectiveness of this method and show that StuffNet also significantly improves object detection performance on such datasets.

Object object-detection +3

GASP : Geometric Association with Surface Patches

no code implementations15 Nov 2014 Rahul Sawhney, Fuxin Li, Henrik I. Christensen

A fundamental challenge to sensory processing tasks in perception and robotics is the problem of obtaining data associations across views.

Cannot find the paper you are looking for? You can Submit a new open access paper.