Exploiting the PANORAMA Representation for Convolutional Neural Network Classification and Retrieval

By Konstantinos Sfikas, Theoharis Theoharis, Ioannis Pratikakis. 2017

123 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 3D Vision & Pose

How researchers see this paper

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

In Artificial Intelligence

1. Ali K. Thabet
2. Bernard Ghanem
3. Karthik Ramani
4. Qi-Xing Huang
5. Bertrand Le Saux
6. Matthias Zwicker
7. Chi-Man Vong
8. Kyoung Mu Lee

In Computer Vision and Pattern Recognition

1. Junwei Han
2. Luc Van Gool
3. Ming-Hsuan Yang
4. Bernard Ghanem
5. Dacheng Tao
6. Trevor Darrell
7. Jiashi Feng
8. Lei Zhang

In 3D Vision & Pose

1. Karthik Ramani
2. Qi-Xing Huang
3. Bertrand Le Saux
4. Matthias Zwicker
5. Ali K. Thabet
6. Kyoung Mu Lee
7. Euyoung Kim
8. Alexandre Boulch

Citations in the corpus

• Learning Descriptor Networks for 3D Shape Synthesis and Analysis (2018, neutral): “PANORAMA-NN [19] 91.”
• 3D2SeqViews: Aggregating Sequential Views for 3D Global Feature Learning by CNN With Hierarchical Attention Aggregation (2019, methodology): “[22] used CNN to learn 3D global features from multiple panorama views which were stacked together in a consistent order.”
• 3D Object Classification via Spherical Projections (2017, methodology): “This is relevant to some recent works of classifying panoramas of 3D objects [22, 21].”
• SPNet: Deep 3D Object Classification and Retrieval using Stereographic Projection (2018, background): “We note that the stereographic representations of 3D object preserve more details about the shape of the 3D object compared to other approaches such as panorama [28,26,1], slice [12], and multi-view [31,15] representations.”
• MVTN: Multi-View Transformation Network for 3D Shape Recognition (2020, methodology): “…ShapeNets [34] Voxels 49.2 - PVNet[36] Points 89.5 - MVCNN [28] 12 Views 80.2 73.5 GIFT [1] 20 Views - 64.0 MVFusionNet [12] 12 Views - 62.2 ReVGG [27] 20 Views - 74.9 RotNet [14] 20 Views - 77.2 ViewGCN [32] 20 Views - 78.4 MLVCNN [13] 24 Views 92.2 - MVTN (ours) 12 Views 92.9 (92.4 ± 0.6) 82.9…”
• SnapNet: 3D point cloud semantic labeling with 2D deep segmentation networks (2017, background): “The PANORAMA representation [32] introduces another trick: projections on bounding cylinders oriented following the 3 principal directions of the volume.”
• RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints (2016, unknown): “80 PANORAMA-NN [30] 90.”
• General-Purpose Deep Point Cloud Feature Extractor (2018, unknown): “8% PANORAMA-NN [43] 91.”