1 code implementation • 12 Nov 2022 • Yu-Hsi Chen, Chien-Yao Wang, Cheng-Yun Yang, Hung-Shuo Chang, Youn-Long Lin, Yung-Yu Chuang, Hong-Yuan Mark Liao
We propose a post-processor, called NeighborTrack, that leverages neighbor information of the tracking target to validate and improve single-object tracking (SOT) results.
Ranked #1 on Visual Object Tracking on UAV123
no code implementations • 9 Nov 2022 • Chien-Yao Wang, Hong-Yuan Mark Liao, I-Hau Yeh
This paper proposes a new network design strategy, i. e., to design the network architecture based on gradient path analysis.
9 code implementations • 6 Jul 2022 • Chien-Yao Wang, Alexey Bochkovskiy, Hong-Yuan Mark Liao
YOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS and has the highest accuracy 56. 8% AP among all known real-time object detectors with 30 FPS or higher on GPU V100.
Ranked #3 on Real-Time Object Detection on COCO (using extra training data)
no code implementations • CVPR 2022 • Wen-Li Wei, Jen-Chun Lin, Tyng-Luh Liu, Hong-Yuan Mark Liao
To address this problem, we propose a motion pose and shape network (MPS-Net) to effectively capture humans in motion to estimate accurate and temporally coherent 3D human pose and shape from a video.
Ranked #4 on 3D Human Pose Estimation on MPI-INF-3DHP (Acceleration Error metric)
8 code implementations • 10 May 2021 • Chien-Yao Wang, I-Hau Yeh, Hong-Yuan Mark Liao
In this paper, we propose a unified network to encode implicit knowledge and explicit knowledge together, just like the human brain can learn knowledge from normal learning as well as subconsciousness learning.
Ranked #1 on Real-Time Object Detection on COCO test-dev
41 code implementations • CVPR 2021 • Chien-Yao Wang, Alexey Bochkovskiy, Hong-Yuan Mark Liao
We show that the YOLOv4 object detection neural network based on the CSP approach, scales both up and down and is applicable to small and large networks while maintaining optimal speed and accuracy.
Ranked #9 on Object Detection on COCO test-dev
no code implementations • 19 May 2020 • Yueh-Hua Wu, I-Hau Yeh, David Hu, Hong-Yuan Mark Liao
Specifically, we are required to provide a solution that is able to (1) handle the traffic signal control when certain surveillance cameras that retrieve information for reinforcement learning are down, (2) learn from batch data without a traffic simulator, and (3) make control decisions without shared information across intersections.
Multi-agent Reinforcement Learning reinforcement-learning +1
224 code implementations • 23 Apr 2020 • Alexey Bochkovskiy, Chien-Yao Wang, Hong-Yuan Mark Liao
There are a huge number of features which are said to improve Convolutional Neural Network (CNN) accuracy.
Ranked #30 on Object Detection on COCO test-dev
no code implementations • 27 Nov 2019 • Ping-Yang Chen, Jun-Wei Hsieh, Chien-Yao Wang, Hong-Yuan Mark Liao, Munkhjargal Gochoo
A new structure "residual feature pyramid" is proposed in this paper.
126 code implementations • 27 Nov 2019 • Chien-Yao Wang, Hong-Yuan Mark Liao, I-Hau Yeh, Yueh-Hua Wu, Ping-Yang Chen, Jun-Wei Hsieh
Neural networks have enabled state-of-the-art approaches to achieve incredible results on computer vision tasks such as object detection.
Ranked #591 on Image Classification on ImageNet
no code implementations • 27 Mar 2018 • Guanjun Guo, Hanzi Wang, Yan Yan, Hong-Yuan Mark Liao, Bo Li
Then, we apply the proposed TOPG method to the task of visual tracking and propose a TOPG-based tracker (called as TOPGT), where TOPG is used as a sample selection strategy to select a small number of high-quality target candidates from the generated object proposals.
no code implementations • 25 Dec 2017 • Guanjun Guo, Hanzi Wang, Chunhua Shen, Yan Yan, Hong-Yuan Mark Liao
The deep CNN model is then designed to extract features from several image cropping datasets, upon which the cropping bounding boxes are predicted by the proposed CCR method.
no code implementations • 19 Dec 2017 • Huan-Cheng Hsu, Ching-Hang Chen, Hsiao-Rong Tyan, Hong-Yuan Mark Liao
With the hierarchical cross feature maps, an HCN can effectively uncover additional semantic features which could not be discovered by a conventional CNN.
no code implementations • CVPR 2014 • Yen-Yu Lin, Ju-Hsuan Hua, Nick C. Tang, Min-Hung Chen, Hong-Yuan Mark Liao
Our approach aims to enhance action recognition in RGB videos by leveraging the extra database.