Domain adaptation for visual applications: A comprehensive survey
G Csurka - arXiv preprint arXiv:1702.05374, 2017 - arxiv.org
The aim of this paper is to give an overview of domain adaptation and transfer learning with
a specific view on visual applications. After a general motivation, we first position domain …
a specific view on visual applications. After a general motivation, we first position domain …
Review and analysis of synthetic dataset generation methods and techniques for application in computer vision
G Paulin, M Ivasic‐Kos - Artificial intelligence review, 2023 - Springer
Synthetic datasets, for which we propose the term synthsets, are not a novelty but have
become a necessity. Although they have been used in computer vision since 1989, helping …
become a necessity. Although they have been used in computer vision since 1989, helping …
Virtual worlds as proxy for multi-object tracking analysis
Modern computer vision algorithms typically require expensive data acquisition and
accurate manual labeling. In this work, we instead leverage the recent progress in computer …
accurate manual labeling. In this work, we instead leverage the recent progress in computer …
Seeing 3d chairs: exemplar part-based 2d-3d alignment using a large dataset of cad models
This paper poses object category detection in images as a type of 2D-to-3D alignment
problem, utilizing the large quantities of 3D CAD models that have been made publicly …
problem, utilizing the large quantities of 3D CAD models that have been made publicly …
Single image 3d interpreter network
Understanding 3D object structure from a single image is an important but difficult task in
computer vision, mostly due to the lack of 3D object annotations in real images. Previous …
computer vision, mostly due to the lack of 3D object annotations in real images. Previous …
Semantic segmentation of point clouds of building interiors with deep learning: Augmenting training datasets with synthetic BIM-based point clouds
This paper investigates the viability of using synthetic point clouds generated from building
information models (BIMs) to train deep neural networks to perform semantic segmentation …
information models (BIMs) to train deep neural networks to perform semantic segmentation …
Panocontext: A whole-room 3d context model for panoramic scene understanding
The field-of-view of standard cameras is very small, which is one of the main reasons that
contextual information is not as useful as it should be for object detection. To overcome this …
contextual information is not as useful as it should be for object detection. To overcome this …
Parsing ikea objects: Fine pose estimation
We address the problem of localizing and estimating the fine-pose of objects in the image
with exact 3D models. Our main focus is to unify contributions from the 1970s with recent …
with exact 3D models. Our main focus is to unify contributions from the 1970s with recent …
Procedural generation of videos to train deep action recognition networks
C Roberto de Souza, A Gaidon… - Proceedings of the …, 2017 - openaccess.thecvf.com
Deep learning for human action recognition in videos is making significant progress, but is
slowed down by its dependency on expensive manual labeling of large video collections. In …
slowed down by its dependency on expensive manual labeling of large video collections. In …
Automatic scene inference for 3d object compositing
We present a user-friendly image editing system that supports a drag-and-drop object
insertion (where the user merely drags objects into the image, and the system automatically …
insertion (where the user merely drags objects into the image, and the system automatically …