A survey of traditional and deep learning-based feature descriptors for high dimensional data in computer vision

T Georgiou, Y Liu, W Chen, M Lew - International Journal of Multimedia …, 2020 - Springer
Higher dimensional data such as video and 3D are the leading edge of multimedia retrieval
and computer vision research. In this survey, we give a comprehensive overview and key …

Three dimensional objects recognition & pattern recognition technique; related challenges: A review

S Rani, K Lakhwani, S Kumar - Multimedia Tools and Applications, 2022 - Springer
Abstract 3D object recognition and pattern recognition are active and fast-growing research
areas in the field of computer vision. It is mandatory to define the pattern class, feature …

Taskonomy: Disentangling task transfer learning

AR Zamir, A Sax, W Shen, LJ Guibas… - Proceedings of the …, 2018 - openaccess.thecvf.com
Do visual tasks have a relationship, or are they unrelated? For instance, could having
surface normals simplify estimating the depth of an image? Intuition answers these …

Gvcnn: Group-view convolutional neural networks for 3d shape recognition

Y Feng, Z Zhang, X Zhao, R Ji… - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
Abstract 3D shape recognition has attracted much attention recently. Its recent advances
advocate the usage of deep features and achieve the state-of-the-art performance. However …

Imvotenet: Boosting 3d object detection in point clouds with image votes

CR Qi, X Chen, O Litany… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
Abstract 3D object detection has seen quick progress thanks to advances in deep learning
on point clouds. A few recent works have even shown state-of-the-art performance with just …

Volumetric and multi-view cnns for object classification on 3d data

CR Qi, H Su, M Nießner, A Dai… - Proceedings of the …, 2016 - openaccess.thecvf.com
Abstract 3D shape models are becoming widely available and easier to capture, making
available 3D information crucial for progress in object classification. Current state-of-the-art …

Lcdnet: Deep loop closure detection and point cloud registration for lidar slam

D Cattaneo, M Vaghi, A Valada - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Loop closure detection is an essential component of simultaneous localization and mapping
(SLAM) systems, which reduces the drift accumulated over time. Over the years, several …

Multi-view convolutional neural networks for 3d shape recognition

H Su, S Maji, E Kalogerakis… - Proceedings of the IEEE …, 2015 - cv-foundation.org
A longstanding question in computer vision concerns the representation of 3D shapes for
recognition: should 3D shapes be represented with descriptors operating on their native 3D …

SHOT: Unique signatures of histograms for surface and texture description

S Salti, F Tombari, L Di Stefano - Computer Vision and Image …, 2014 - Elsevier
This paper presents a local 3D descriptor for surface matching dubbed SHOT. Our proposal
stems from a taxonomy of existing methods which highlights two major approaches, referred …

Learning relationships for multi-view 3D object recognition

Z Yang, L Wang - … of the IEEE/CVF international conference …, 2019 - openaccess.thecvf.com
Recognizing 3D object has attracted plenty of attention recently, and view-based methods
have achieved best results until now. However, previous view-based methods ignore the …