Journal Article10.11834/jig.230390
Multi-object tracking using adaptive-IoU loss and hierarchical association
Wen Guo,Qigui Liu,Xinmiao Ding +2 more
About: This article is published in Journal of image and graphics. The article was published on 01 Jan 2024. The article focuses on the topics: Association (psychology) & Tracking (education).
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
References
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TL;DR: This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
Feature Pyramid Networks for Object Detection
Tsung-Yi Lin,Piotr Dollár,Ross Girshick,Kaiming He,Bharath Hariharan,Serge Belongie +5 more
- 21 Jul 2017
TL;DR: This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.
Mask R-CNN
Kaiming He,Georgia Gkioxari,Piotr Dollár,Ross Girshick +3 more
- 20 Mar 2017
TL;DR: This work presents a conceptually simple, flexible, and general framework for object instance segmentation, which extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition.
Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression
Hamid Rezatofighi,Nathan Tsoi,JunYoung Gwak,Amir Sadeghian,Ian Reid,Silvio Savarese +5 more
- 01 Jun 2019
TL;DR: In this paper, a generalized IoU (GIoU) metric is proposed for non-overlapping bounding boxes, which can be directly used as a regression loss.
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
Zhaohui Zheng,Ping Wang,Wei Liu,Jinze Li,Rongguang Ye,Dongwei Ren +5 more
- 03 Apr 2020
TL;DR: A Distance-IoU (DIoU) loss is proposed by incorporating the normalized distance between the predicted box and the target box, which converges much faster in training than IoU and GIoU losses, thereby leading to faster convergence and better performance.