Picture for Heiko Neumann

Heiko Neumann

Cycle-Correspondence Loss: Learning Dense View-Invariant Visual Features from Unlabeled and Unordered RGB Images

Add code
Jun 18, 2024
Viaarxiv icon

Learning Dense Visual Descriptors using Image Augmentations for Robot Manipulation Tasks

Add code
Sep 12, 2022
Figure 1 for Learning Dense Visual Descriptors using Image Augmentations for Robot Manipulation Tasks
Figure 2 for Learning Dense Visual Descriptors using Image Augmentations for Robot Manipulation Tasks
Figure 3 for Learning Dense Visual Descriptors using Image Augmentations for Robot Manipulation Tasks
Figure 4 for Learning Dense Visual Descriptors using Image Augmentations for Robot Manipulation Tasks
Viaarxiv icon

Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression

Add code
Aug 01, 2022
Figure 1 for Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression
Figure 2 for Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression
Figure 3 for Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression
Figure 4 for Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression
Viaarxiv icon

Efficient and Robust Training of Dense Object Nets for Multi-Object Robot Manipulation

Add code
Jun 24, 2022
Figure 1 for Efficient and Robust Training of Dense Object Nets for Multi-Object Robot Manipulation
Figure 2 for Efficient and Robust Training of Dense Object Nets for Multi-Object Robot Manipulation
Figure 3 for Efficient and Robust Training of Dense Object Nets for Multi-Object Robot Manipulation
Figure 4 for Efficient and Robust Training of Dense Object Nets for Multi-Object Robot Manipulation
Viaarxiv icon

Generating 3D People in Scenes without People

Add code
Dec 12, 2019
Figure 1 for Generating 3D People in Scenes without People
Figure 2 for Generating 3D People in Scenes without People
Figure 3 for Generating 3D People in Scenes without People
Figure 4 for Generating 3D People in Scenes without People
Viaarxiv icon

Low-rank Random Tensor for Bilinear Pooling

Add code
Jun 03, 2019
Figure 1 for Low-rank Random Tensor for Bilinear Pooling
Figure 2 for Low-rank Random Tensor for Bilinear Pooling
Figure 3 for Low-rank Random Tensor for Bilinear Pooling
Figure 4 for Low-rank Random Tensor for Bilinear Pooling
Viaarxiv icon

Local Temporal Bilinear Pooling for Fine-grained Action Parsing

Add code
Jan 10, 2019
Figure 1 for Local Temporal Bilinear Pooling for Fine-grained Action Parsing
Figure 2 for Local Temporal Bilinear Pooling for Fine-grained Action Parsing
Figure 3 for Local Temporal Bilinear Pooling for Fine-grained Action Parsing
Figure 4 for Local Temporal Bilinear Pooling for Fine-grained Action Parsing
Viaarxiv icon

An Empirical Study towards Understanding How Deep Convolutional Nets Recognize Falls

Add code
Dec 05, 2018
Figure 1 for An Empirical Study towards Understanding How Deep Convolutional Nets Recognize Falls
Figure 2 for An Empirical Study towards Understanding How Deep Convolutional Nets Recognize Falls
Figure 3 for An Empirical Study towards Understanding How Deep Convolutional Nets Recognize Falls
Figure 4 for An Empirical Study towards Understanding How Deep Convolutional Nets Recognize Falls
Viaarxiv icon

Training De-Confusion: An Interactive, Network-Supported Visual Analysis System for Resolving Errors in Image Classification Training Data

Add code
Aug 09, 2018
Figure 1 for Training De-Confusion: An Interactive, Network-Supported Visual Analysis System for Resolving Errors in Image Classification Training Data
Figure 2 for Training De-Confusion: An Interactive, Network-Supported Visual Analysis System for Resolving Errors in Image Classification Training Data
Figure 3 for Training De-Confusion: An Interactive, Network-Supported Visual Analysis System for Resolving Errors in Image Classification Training Data
Figure 4 for Training De-Confusion: An Interactive, Network-Supported Visual Analysis System for Resolving Errors in Image Classification Training Data
Viaarxiv icon

Temporal Human Action Segmentation via Dynamic Clustering

Add code
Mar 18, 2018
Figure 1 for Temporal Human Action Segmentation via Dynamic Clustering
Figure 2 for Temporal Human Action Segmentation via Dynamic Clustering
Figure 3 for Temporal Human Action Segmentation via Dynamic Clustering
Figure 4 for Temporal Human Action Segmentation via Dynamic Clustering
Viaarxiv icon