Search Results for author: Hong-Yuan Mark Liao

Found 16 papers, 8 papers with code

YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

1 code implementation21 Feb 2024 Chien-Yao Wang, I-Hau Yeh, Hong-Yuan Mark Liao

It can be used to obtain complete information, so that train-from-scratch models can achieve better results than state-of-the-art models pre-trained using large datasets, the comparison results are shown in Figure 1.

object-detection Real-Time Object Detection

YOLOR-Based Multi-Task Learning

2 code implementations29 Sep 2023 Hung-Shuo Chang, Chien-Yao Wang, Richard Robert Wang, Gene Chou, Hong-Yuan Mark Liao

Multi-task learning (MTL) aims to learn multiple tasks using a single model and jointly improve all of them assuming generalization and shared semantics.

Image Captioning Instance Segmentation +5

NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets

1 code implementation12 Nov 2022 Yu-Hsi Chen, Chien-Yao Wang, Cheng-Yun Yang, Hung-Shuo Chang, Youn-Long Lin, Yung-Yu Chuang, Hong-Yuan Mark Liao

Our proposed NeighborTrack takes advantage of unoccluded neighbors' information to reconfirm the tracking target and reduces false tracking when the target is occluded.

Object Visual Object Tracking

Designing Network Design Strategies Through Gradient Path Analysis

no code implementations9 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.

YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

16 code implementations CVPR 2023 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.

Object Real-Time Object Detection +1

Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video

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.

3D human pose and shape estimation

You Only Learn One Representation: Unified Network for Multiple Tasks

9 code implementations10 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 #4 on Object Detection on COCO minival (APS metric)

Multi-Task Learning Real-Time Object Detection +1

Scaled-YOLOv4: Scaling Cross Stage Partial Network

42 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.

Real-Time Object Detection

Batch-Augmented Multi-Agent Reinforcement Learning for Efficient Traffic Signal Optimization

no code implementations19 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

CSPNet: A New Backbone that can Enhance Learning Capability of CNN

124 code implementations27 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.

Attribute Image Classification +1

A New Target-specific Object Proposal Generation Method for Visual Tracking

no code implementations27 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.

Object Object Proposal Generation +1

Automatic Image Cropping for Visual Aesthetic Enhancement Using Deep Neural Networks and Cascaded Regression

no code implementations25 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.

Image Cropping regression

Hierarchical Cross Network for Person Re-identification

no code implementations19 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.

Person Re-Identification Retrieval

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