Overlapping object detection with adaptive Gaussian sample division and asymmetric weighted loss
Y Xue, Y Zhang, Y Liu, X Qian - Knowledge-Based Systems, 2024 - Elsevier
Existing deep learning based detectors are mostly designed for scenes with sparsely
distributed objects. However, in certain scenarios such as dense crowds, objects often …
distributed objects. However, in certain scenarios such as dense crowds, objects often …
Can using a pre-trained deep learning model as the feature extractor in the bag-of-deep-visual-words model always improve image classification accuracy?
Y Xu, X Zhang, C Huang, X Qiu - Plos one, 2024 - journals.plos.org
This article investigates whether higher classification accuracy can always be achieved by
utilizing a pre-trained deep learning model as the feature extractor in the Bag-of-Deep …
utilizing a pre-trained deep learning model as the feature extractor in the Bag-of-Deep …
Cross-domain pedestrian detection via feature alignment and image quality assessment
J Yao, Z Guo, JJ Yu, N Yan, Q Wang, W Yu - Iscience, 2024 - cell.com
Datasets collected under different sensors, viewpoints, or weather conditions cause different
domains. Models trained on domain A applied to tasks of domain B result in low …
domains. Models trained on domain A applied to tasks of domain B result in low …
Context feature fusion and enhanced non-maximum suppression for pedestrian detection in crowded scenes
Y Shao, J Hu, L Hu, J Zhang, X Wang - Multimedia Tools and Applications, 2024 - Springer
Pedestrian detection has a wide range of applications in the field of multimedia, and
significant progress has been made. However, in densely populated scenes, there are two …
significant progress has been made. However, in densely populated scenes, there are two …
Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completion
S Zhang, M Ji, Y Li, J Yang - arXiv preprint arXiv:2405.01311, 2024 - arxiv.org
Pedestrian detection has significantly progressed in recent years, thanks to the development
of DNNs. However, detection performance at occluded scenes is still far from satisfactory, as …
of DNNs. However, detection performance at occluded scenes is still far from satisfactory, as …
An improved multi-scale and knowledge distillation method for efficient pedestrian detection in dense scenes
Y Xu, M Wen, W He, H Wang, Y Xue - Journal of Real-Time Image …, 2024 - Springer
Pedestrian detection in densely populated scenes, particularly in the presence of
occlusions, remains a challenging issue in computer vision. Existing approaches often …
occlusions, remains a challenging issue in computer vision. Existing approaches often …
Research, Applications and Prospects of Event-Based Pedestrian Detection: A Survey
H Wang, Y Nie, Y Li, H Liu, M Liu, W Cheng… - arXiv preprint arXiv …, 2024 - arxiv.org
Event-based cameras, inspired by the biological retina, have evolved into cutting-edge
sensors distinguished by their minimal power requirements, negligible latency, superior …
sensors distinguished by their minimal power requirements, negligible latency, superior …
Addressing uncertainty challenges for autonomous driving in real-world environments
Despite ongoing beta tests and research, significant challenges still need to be addressed
before fully autonomous driving can be commercialized. At levels 3 or higher, the …
before fully autonomous driving can be commercialized. At levels 3 or higher, the …
AOPPI: An adaptive obstruction perception pedestrian identifier for complex environments
Y Zhang, K He, J Ge - Journal of Intelligent & Fuzzy Systems, 2024 - content.iospress.com
Pedestrian detection plays a crucial role in ensuring traffic safety within the domain of
computer vision. However, accurately detecting pedestrians in complex environments …
computer vision. However, accurately detecting pedestrians in complex environments …
[图书][B] Artificial Intelligence and Machine Learning for Open-world Novelty
Advances in Computers, Volume presents innovations in computer hardware, software,
theory, design and applications, with this updated volume including new chapters on …
theory, design and applications, with this updated volume including new chapters on …