Search Results for author: Hamid Reza Vaezi Joze

Found 8 papers, 2 papers with code

Adaptive Token Sampling For Efficient Vision Transformers

no code implementations30 Nov 2021 Mohsen Fayyaz, Soroush Abbasi Koohpayegani, Farnoush Rezaei Jafari, Sunando Sengupta, Hamid Reza Vaezi Joze, Eric Sommerlade, Hamed Pirsiavash, Juergen Gall

Since ATS is a parameter-free module, it can be added to the off-the-shelf pre-trained vision transformers as a plug and play module, thus reducing their GFLOPs without any additional training.

Image Classification Video Classification

Network Architecture Search for Face Enhancement

no code implementations13 May 2021 Rajeev Yasarla, Hamid Reza Vaezi Joze, Vishal M Patel

Poor quality face images often reduce the performance of face analysis and recognition systems.

MMTM: Multimodal Transfer Module for CNN Fusion

1 code implementation CVPR 2020 Hamid Reza Vaezi Joze, Amirreza Shaban, Michael L. Iuzzolino, Kazuhito Koishida

In late fusion, each modality is processed in a separate unimodal Convolutional Neural Network (CNN) stream and the scores of each modality are fused at the end.

Action Recognition Action Recognition In Videos +3

Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training

1 code implementation CVPR 2019 Mahdi Abavisani, Hamid Reza Vaezi Joze, Vishal M. Patel

We present an efficient approach for leveraging the knowledge from multiple modalities in training unimodal 3D convolutional neural networks (3D-CNNs) for the task of dynamic hand gesture recognition.

Action Recognition Hand Gesture Recognition +2

MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Language

no code implementations3 Dec 2018 Hamid Reza Vaezi Joze, Oscar Koller

Sign language recognition is a challenging and often underestimated problem comprising multi-modal articulators (handshape, orientation, movement, upper body and face) that integrate asynchronously on multiple streams.

Action Recognition Sign Language Recognition

DIY Human Action Data Set Generation

no code implementations29 Mar 2018 Mehran Khodabandeh, Hamid Reza Vaezi Joze, Ilya Zharkov, Vivek Pradeep

Therefore, the ability to generate de novo data or expand an existing data set, however small, in order to satisfy data requirement of current networks may be invaluable.

Action Recognition Video Generation

Camera Calibration for Daylight Specular-Point Locus

no code implementations12 Dec 2017 Mark S. Drew, Hamid Reza Vaezi Joze, Graham D. Finlayson

First we prove theoretically that any candidate specular points, for an image that is generated by a specific camera and taken under a daylight, must lie on a straight line in log-chromaticity space, for a chromaticity that is generated using a geometric-mean denominator.

Camera Calibration

Cannot find the paper you are looking for? You can Submit a new open access paper.