Picture for Hong-Yuan Mark Liao

Hong-Yuan Mark Liao

YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary

Add code
Oct 20, 2024
Figure 1 for YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary
Figure 2 for YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary
Figure 3 for YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary
Figure 4 for YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary
Viaarxiv icon

YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems

Add code
Aug 18, 2024
Viaarxiv icon

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

Add code
Feb 29, 2024
Viaarxiv icon

YOLOR-Based Multi-Task Learning

Add code
Sep 29, 2023
Figure 1 for YOLOR-Based Multi-Task Learning
Figure 2 for YOLOR-Based Multi-Task Learning
Figure 3 for YOLOR-Based Multi-Task Learning
Figure 4 for YOLOR-Based Multi-Task Learning
Viaarxiv icon

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

Add code
Nov 12, 2022
Viaarxiv icon

Designing Network Design Strategies Through Gradient Path Analysis

Add code
Nov 09, 2022
Viaarxiv icon

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

Add code
Jul 06, 2022
Figure 1 for YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
Figure 2 for YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
Figure 3 for YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
Figure 4 for YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
Viaarxiv icon

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

Add code
Mar 16, 2022
Figure 1 for Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video
Figure 2 for Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video
Figure 3 for Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video
Figure 4 for Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video
Viaarxiv icon

You Only Learn One Representation: Unified Network for Multiple Tasks

Add code
May 10, 2021
Figure 1 for You Only Learn One Representation: Unified Network for Multiple Tasks
Figure 2 for You Only Learn One Representation: Unified Network for Multiple Tasks
Figure 3 for You Only Learn One Representation: Unified Network for Multiple Tasks
Figure 4 for You Only Learn One Representation: Unified Network for Multiple Tasks
Viaarxiv icon

Scaled-YOLOv4: Scaling Cross Stage Partial Network

Add code
Nov 16, 2020
Figure 1 for Scaled-YOLOv4: Scaling Cross Stage Partial Network
Figure 2 for Scaled-YOLOv4: Scaling Cross Stage Partial Network
Figure 3 for Scaled-YOLOv4: Scaling Cross Stage Partial Network
Figure 4 for Scaled-YOLOv4: Scaling Cross Stage Partial Network
Viaarxiv icon