Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report

no code implementations • 7 Nov 2022 • Andrey Ignatov, Grigory Malivenko, Radu Timofte, Lukasz Treszczotko, Xin Chang, Piotr Ksiazek, Michal Lopuszynski, Maciej Pioro, Rafal Rudnicki, Maciej Smyl, Yujie Ma, Zhenyu Li, Zehui Chen, Jialei Xu, Xianming Liu, Junjun Jiang, XueChao Shi, Difan Xu, Yanan Li, Xiaotao Wang, Lei Lei, Ziyu Zhang, Yicheng Wang, Zilong Huang, Guozhong Luo, Gang Yu, Bin Fu, Jiaqi Li, Yiran Wang, Zihao Huang, Zhiguo Cao, Marcos V. Conde, Denis Sapozhnikov, Byeong Hyun Lee, Dongwon Park, Seongmin Hong, Joonhee Lee, Seunggyu Lee, Se Young Chun

Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks.

Bokeh Effect Rendering Depth Estimation +3

Multi-modal Residual Perceptron Network for Audio-Video Emotion Recognition

no code implementations • 21 Jul 2021 • Xin Chang, Władysław Skarbek

Audio-Video Emotion Recognition is now attacked with Deep Neural Network modeling tools.

Video Emotion Recognition

ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation

no code implementations • 7 Jul 2020 • Fan Yang, Xin Chang, Chenyu Dang, Ziqiang Zheng, Sakriani Sakti, Satoshi Nakamura, Yang Wu

We aim to improve the performance of Multiple Object Tracking and Segmentation (MOTS) by refinement.

Multi-Object Tracking Multi-Object Tracking and Segmentation +2

Multiple Object Tracking by Flowing and Fusing

no code implementations • 30 Jan 2020 • Jimuyang Zhang, Sanping Zhou, Xin Chang, Fangbin Wan, Jinjun Wang, Yang Wu, Dong Huang

Most of Multiple Object Tracking (MOT) approaches compute individual target features for two subtasks: estimating target-wise motions and conducting pair-wise Re-Identification (Re-ID).

Multiple Object Tracking Object +2

Human Face Expressions from Images - 2D Face Geometry and 3D Face Local Motion versus Deep Neural Features

no code implementations • 31 Jan 2019 • Rafal Pilarczyk, Xin Chang, Wladyslaw Skarbek

For geometric features, the success rate (accuracy) indicate nearly triple increase of performance of CNN with respect to SVM classifiers.