Multi-spectral SIFT for scene category recognition

By Matthew A. Brown, Sabine Süsstrunk. Computer Vision and Pattern Recognition, 2011

525 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/2133f14e239be65ad30de0f92b2469f9de0f2f5d

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. Jiayi Ma
2. Linfeng Tang
3. Yong Ma
4. Jun Huang
5. Xiaoguang Mei
6. Jinde Cao
7. Shishuang Yu
8. Xue Wang

In Media Technology

1. Jiayi Ma
2. Linfeng Tang
3. Yong Ma
4. Jun Huang
5. Jinde Cao
6. Shishuang Yu
7. Xue Wang
8. Zheng Guan

Citations in the corpus

• Convolutional Neural Network Based Automatic Object Detection on Aerial Images (2016, background): “Also, texture descriptor extraction is easily extended to color and multispectral images [11], [12].”
• Image Segmentation for Fruit Detection and Yield Estimation in Apple Orchards (2016, methodology): “A separate natural scene data set (Brown & Susstrunk, 2011) was used to initialize the first layer filters with a DAE.”
• Salient object detection: A survey (2014, unknown): “ ˘300 225 3 - ,, ASD [6,139] 2009 1000 ˘1 PW 400 300 1 - ,, SOD [13,156] 2010 300 ˘3 PW 481 321 7 - ,, iCoSeg [16] 2010 643 ˘1 PW ˘500 400 1 - ,, MSRA5K [86,139] 2011 5K ˘1 PW 400 300 1 - ,, Infrared [31,206] 2011 900 ˘5 PW 1024 768 2 15 ,, ImgSal [122] 2013 235 ˘2 PW 640 480 19 50 ,, CSSD [216] 201”
• Infrared and Visible Image Fusion via Decoupling Network (2022, methodology): “4) We have evaluated the proposed DNFusion on the TNO dataset [19], FLIR-test dataset [20], near-infrared (NIR) dataset [21], and multiscenario multimodality (M 3 FD) dataset [22].”
• SwinFusion: Cross-domain Long-range Learning for General Image Fusion via Swin Transformer (2022, methodology): “We build the training and test datasets based on the publicly available VIS-NIR Scene dataset [78]2 for VIS-NIR.”
• In Defense of Fully Connected Layers in Visual Representation Transfer (2017, methodology): “First, four image classification datasets are included (Caltech-101 [3], Indoor-67 [11], RGB-NIR scene [1] and CUB200-2011 [16]).”