3 Hits in 4.2 sec

AFAT: Adaptive Failure-Aware Tracker for Robust Visual Object Tracking [article]

Tianyang Xu, Zhen-Hua Feng, Xiao-Jun Wu, Josef Kittler
2020 arXiv   pre-print
In addition, we further provide an Adaptive Failure-Aware Tracker (AFAT) by combing the state-of-the-art Siamese trackers with our system.  ...  Siamese approaches have achieved promising performance in visual object tracking recently.  ...  Adaptive failure-aware tracker We propose the Adaptive Failure-Aware Tracker (AFAT) based on the Siame-seRPN++ tracker [26] and the proposed QPN in Section 3.  ... 
arXiv:2005.13708v1 fatcat:zo55gjj5krcdth6gbbagdpksbq

RFN-Nest: An end-to-end residual fusion network for infrared and visible images [article]

Hui Li, Xiao-Jun Wu, Josef Kittler
2021 pre-print
The most difficult part of the design is to choose an appropriate strategy to generate the fused image for a specific task in hand.  ...  To address this problem, a novel end-to-end fusion network architecture (RFN-Nest) is developed for infrared and visible image fusion.  ...  In AFAT, a failure-aware system, realized by a Quality Prediction Network (QPN), based on convolutional and LSTM modules was proposed and obtained better tracking performance in many datasets.  ... 
doi:10.1016/j.inffus.2021.02.023 arXiv:2103.04286v1 fatcat:akla65qmunfrnpkbxglsbenq2m

Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective [article]

Wu Liu, Qian Bao, Yu Sun, Tao Mei
2021 arXiv   pre-print
Finally, we discuss the challenges and give deep thinking of promising directions for future research.  ...  Although there have been some works to summarize the different approaches, it still remains challenging for researchers to have an in-depth view of how these approaches work.  ...  : 0.95), AP M for medium objects, AP L for large objects, AR 0.5 , AR 0.75 , AR, AR M for medium objects, AR L for large objects.  ... 
arXiv:2104.11536v1 fatcat:tdag2jq2vjdrjekwukm5nu7l6a