Deep reinforcement learning in computer vision: a comprehensive survey

N Le, VS Rathour, K Yamazaki, K Luu… - Artificial Intelligence …, 2022 - Springer
Deep reinforcement learning augments the reinforcement learning framework and utilizes
the powerful representation of deep neural networks. Recent works have demonstrated the …

Computing systems for autonomous driving: State of the art and challenges

L Liu, S Lu, R Zhong, B Wu, Y Yao… - IEEE Internet of …, 2020 - ieeexplore.ieee.org
The recent proliferation of computing technologies (eg, sensors, computer vision, machine
learning, and hardware acceleration) and the broad deployment of communication …

Motchallenge: A benchmark for single-camera multiple target tracking

P Dendorfer, A Osep, A Milan, K Schindler… - International Journal of …, 2021 - Springer
Standardized benchmarks have been crucial in pushing the performance of computer vision
algorithms, especially since the advent of deep learning. Although leaderboards should not …

3d multi-object tracking: A baseline and new evaluation metrics

X Weng, J Wang, D Held, K Kitani - 2020 IEEE/RSJ …, 2020 - ieeexplore.ieee.org
3D multi-object tracking (MOT) is an essential component for many applications such as
autonomous driving and assistive robotics. Recent work on 3D MOT focuses on develo** …

Computer vision for autonomous vehicles: Problems, datasets and state of the art

J Janai, F Güney, A Behl, A Geiger - Foundations and Trends® …, 2020 - nowpublishers.com
Recent years have witnessed enormous progress in AI-related fields such as computer
vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it …

Deep affinity network for multiple object tracking

SJ Sun, N Akhtar, HS Song, A Mian… - IEEE transactions on …, 2019 - ieeexplore.ieee.org
Multiple Object Tracking (MOT) plays an important role in solving many fundamental
problems in video analysis and computer vision. Most MOT methods employ two steps …

Spatial-temporal relation networks for multi-object tracking

J Xu, Y Cao, Z Zhang, H Hu - Proceedings of the IEEE/CVF …, 2019 - openaccess.thecvf.com
Recent progress in multiple object tracking (MOT) has shown that a robust similarity score is
a key to the success of trackers. A good similarity score is expected to reflect multiple cues …

Online multi-object tracking using CNN-based single object tracker with spatial-temporal attention mechanism

Q Chu, W Ouyang, H Li, X Wang… - Proceedings of the …, 2017 - openaccess.thecvf.com
In this paper, we propose a CNN-based framework for online MOT. This framework utilizes
the merits of single object trackers in adapting appearance models and searching for target …

Online multi-target tracking using recurrent neural networks

A Milan, SH Rezatofighi, A Dick, I Reid… - Proceedings of the AAAI …, 2017 - ojs.aaai.org
We present a novel approach to online multi-target tracking based on recurrent neural
networks (RNNs). Tracking multiple objects in real-world scenes involves many challenges …

Multiple object tracking: A literature review

W Luo, J **ng, A Milan, X Zhang, W Liu, TK Kim - Artificial intelligence, 2021 - Elsevier
Abstract Multiple Object Tracking (MOT) has gained increasing attention due to its academic
and commercial potential. Although different approaches have been proposed to tackle this …