no code implementations • 4 Dec 2023 • Shima Rezasoltani, Faisal Z. Qureshi
Hyperspectral images, which record the electromagnetic spectrum for a pixel in the image of a scene, often store hundreds of channels per pixel and contain an order of magnitude more information than a similarly-sized RBG color image.
no code implementations • 17 Nov 2023 • Soham Chitnis, Kiran Mantripragada, Faisal Z. Qureshi
The hyperspectral pixel unmixing aims to find the underlying materials (endmembers) and their proportions (abundances) in pixels of a hyperspectral image.
1 code implementation • 26 May 2023 • Hamoon Jafarian, Faisal Z. Qureshi
Human pose and shape estimation methods continue to suffer in situations where one or more parts of the body are occluded.
no code implementations • 8 Feb 2023 • Shima Rezasoltani, Faisal Z. Qureshi
Hyperspectral images, which record the electromagnetic spectrum for a pixel in the image of a scene, often store hundreds of channels per pixel and contain an order of magnitude more information than a typical similarly-sized color image.
no code implementations • 5 Mar 2022 • Kiran Mantripragada, Faisal Z. Qureshi
The results demonstrate the potential of our method to find objects in a Hyperspectral Image while bypassing the burden of manual search of the optimal parameters.
no code implementations • 2 Mar 2022 • Kiran Mantripragada, Faisal Z. Qureshi
We present a method for hyperspectral pixel {\it unmixing}.
no code implementations • 1 Apr 2021 • Kiran Mantripragada, Phuong D. Dao, Yuhong He, Faisal Z. Qureshi
We use five dimensionality reduction methods -- PCA, KPCA, ICA, AE, and DAE -- to compress 301-dimensional hyperspectral pixels.
no code implementations • 26 Jan 2019 • Wesley Taylor, Faisal Z. Qureshi
Our method on average is able to generate a video summary in time that is shorter than the duration of the video.
no code implementations • 16 Jan 2019 • Tony Joseph, Konstantinos G. Derpanis, Faisal Z. Qureshi
In this paper, we propose a novel approach that learns to sequentially attend to different Convolutional Neural Networks (CNN) layers (i. e., ``what'' feature abstraction to attend to) and different spatial locations of the selected feature map (i. e., ``where'') to perform the task at hand.
20 code implementations • 1 Jan 2019 • Kamyar Nazeri, Eric Ng, Tony Joseph, Faisal Z. Qureshi, Mehran Ebrahimi
The edge generator hallucinates edges of the missing region (both regular and irregular) of the image, and the image completion network fills in the missing regions using hallucinated edges as a priori.
Ranked #10 on Image Inpainting on Places2
no code implementations • NIPS Workshop CDNNRIA 2018 • Martin Magill, Faisal Z. Qureshi, Hendrick W. de Haan
We explore the use of neural networks to solve the Laplace equation in a two-dimensional geometry.
no code implementations • 13 Mar 2018 • Jordan Stadler, Faisal Z. Qureshi
We present a framework for video-driven crowd synthesis.