Search Results for author: Jason Gu

Found 6 papers, 0 papers with code

End-To-End Audiovisual Feature Fusion for Active Speaker Detection

no code implementations27 Jul 2022 Fiseha B. Tesema, Zheyuan Lin, Shiqiang Zhu, Wei Song, Jason Gu, Hong Wu

After fusion, one BiGRU layer is attached to model the joint temporal dynamics.

BCOT: A Markerless High-Precision 3D Object Tracking Benchmark

no code implementations CVPR 2022 Jiachen Li, Bin Wang, Shiqiang Zhu, Xin Cao, Fan Zhong, Wenxuan Chen, Te Li, Jason Gu, Xueying Qin

Our new benchmark dataset contains 20 textureless objects, 22 scenes, 404 video sequences and 126K images captured in real scenes.

3D Object Tracking Object Tracking

RSI-Net: Two-Stream Deep Neural Network for Remote Sensing Imagesbased Semantic Segmentation

no code implementations19 Sep 2021 Shuang He, Xia Lu, Jason Gu, Haitong Tang, Qin Yu, Kaiyue Liu, Haozhou Ding, Chunqi Chang, Nizhuan Wang

For semantic segmentation of remote sensing images (RSI), trade-off between representation power and location accuracy is quite important.

Semantic Segmentation

Deep Learning Training with Simulated Approximate Multipliers

no code implementations26 Dec 2019 Issam Hammad, Kamal El-Sankary, Jason Gu

The paper demonstrates that using approximate multipliers for CNN training can significantly enhance the performance in terms of speed, power, and area at the cost of a small negative impact on the achieved accuracy.

A Comparative Study on Machine Learning Algorithms for the Control of a Wall Following Robot

no code implementations26 Dec 2019 Issam Hammad, Kamal El-Sankary, Jason Gu

A comparison of the performance of various machine learning models to predict the direction of a wall following robot is presented in this paper.

BIG-bench Machine Learning

Edge-Semantic Learning Strategy for Layout Estimation in Indoor Environment

no code implementations3 Jan 2019 Weidong Zhang, Wei zhang, Jason Gu

More specifically, we present an encoder-decoder network with shared encoder and two separate decoders, which are composed of multiple deconvolution (transposed convolution) layers, to jointly learn the edge maps and semantic labels of a room image.

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