Deep Learning Advances in Computer Vision with 3D Data

By Anastasia Ioannidou, Elisavet Chatzilari, S. Nikolopoulos, I. Kompatsiaris. ACM Computing Surveys, 2017

347 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Geology

View Paper: https://www.semanticscholar.org/paper/cc188b35108d089b31cc0cedcfed100e4e7ae8a1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Song Bai
2. Yulan Guo
3. Xiang Bai
4. Mohammed Bennamoun
5. Zhichao Zhou
6. Ashirbani Saha
7. Li Liu
8. Qingyong Hu

In Geology

1. Yulan Guo
2. Paul Patras
3. Xiang Bai
4. Mohammed Bennamoun
5. Shu‐Ching Chen
6. Hamed Haddadi
7. Hao Liu
8. Ying Li

Citations in the corpus

• Deep Learning vs. Traditional Computer Vision (2019, background): “This process is known as dataset augmentation and it involves the artificial generation of extra training data from the available ones, for example, by cropping, scaling, or rotating images [64].”
• Deep Learning for 3D Point Clouds: A Survey (2019, background): “2) As opposed to existing reviews [19], [20], we specifically focus on deep learning methods for 3D point clouds rather than all types of 3D data.”
• Triplet-Center Loss for Multi-view 3D Object Retrieval (2018, background): “We refer the readers to [34, 13] for a comprehensive survey of 3D shape retrieval.”
• Deep Learning in Mobile and Wireless Networking: A Survey (2018, background): “As the flagship of machine learning, deep learning has achieved remarkable performance in areas such as computer vision [13] and natural language processing (NLP) [14].”
• Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithm (2019, background): “Deep learning is a new field of machine learning that is recently revolutionizing the automated analysis of images [8, 9].”
• A Survey on Deep Learning (2018, background): “While some previous survey papers only focused on a certain scope in deep learning [36, 70], the novelty of this article is that it focuses on different aspects of deep learning by presenting a review of the top-level papers, the authors’ experience, and the breakthroughs in research on and…”
• Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review (2020, methodology): “Although DL in 3D data has been surveyed in [27–29], these 3D data are mainly 3D CAD models [30].”
• A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trends (2019, background): “Deep Learning for Computer Vision: A Brief Review [229] A Survey on Deep Learning Methods for Robot Vision [230] Deep learning for visual understanding: A review [228] Deep Learning Advances in Computer Vision with 3D Data: A Survey [231] Visualizations of Deep Neural Networks in Computer Vision: A ”
• A Survey on Vision--Language--Action Models for Embodied AI (2024, neutral): “…segmentation, zero-shot performance, and versatile architecture, further underlining the transformative impact of Vision Transformer models in various computer vision domains. c) Vision in 3D.: Aside from the most common RGB data, other types of visual inputs are widely used [254], [255].”