GeoAI for large-scale image analysis and machine vision: recent progress of artificial intelligence in geography

W Li, CY Hsu - ISPRS International Journal of Geo-Information, 2022 - mdpi.com
GeoAI, or geospatial artificial intelligence, has become a trending topic and the frontier for
spatial analytics in Geography. Although much progress has been made in exploring the …

Region proposal by guided anchoring

J Wang, K Chen, S Yang, CC Loy… - Proceedings of the …, 2019 - openaccess.thecvf.com
Region anchors are the cornerstone of modern object detection techniques. State-of-the-art
detectors mostly rely on a dense anchoring scheme, where anchors are sampled uniformly …

Co-occurrence feature learning from skeleton data for action recognition and detection with hierarchical aggregation

C Li, Q Zhong, D **e, S Pu - arxiv preprint arxiv:1804.06055, 2018 - arxiv.org
Skeleton-based human action recognition has recently drawn increasing attentions with the
availability of large-scale skeleton datasets. The most crucial factors for this task lie in two …

Detection in crowded scenes: One proposal, multiple predictions

X Chu, A Zheng, X Zhang, J Sun - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
We propose a simple yet effective proposal-based object detector, aiming at detecting highly-
overlapped instances in crowded scenes. The key of our approach is to let each proposal …

Swapmix: Diagnosing and regularizing the over-reliance on visual context in visual question answering

V Gupta, Z Li, A Kortylewski, C Zhang… - Proceedings of the …, 2022 - openaccess.thecvf.com
Abstract While Visual Question Answering (VQA) has progressed rapidly, previous works
raise concerns about robustness of current VQA models. In this work, we study the …

Cascade rpn: Delving into high-quality region proposal network with adaptive convolution

T Vu, H Jang, TX Pham, C Yoo - Advances in neural …, 2019 - proceedings.neurips.cc
This paper considers an architecture referred to as Cascade Region Proposal Network
(Cascade RPN) for improving the region-proposal quality and detection performance by …

Cascade object detection and remote sensing object detection method based on trainable activation function

SN Shivappriya, MJP Priyadarsini, A Stateczny… - Remote Sensing, 2021 - mdpi.com
Object detection is an important process in surveillance system to locate objects and it is
considered as major application in computer vision. The Convolution Neural Network (CNN) …

STDnet: Exploiting high resolution feature maps for small object detection

B Bosquet, M Mucientes, VM Brea - Engineering Applications of Artificial …, 2020 - Elsevier
The accuracy of small object detection with convolutional neural networks (ConvNets) lags
behind that of larger objects. This can be observed in popular contests like MS COCO. This …

Generalizing state-of-the-art object detectors for autonomous vehicles in unseen environments

A Khosravian, A Amirkhani, H Kashiani… - Expert Systems with …, 2021 - Elsevier
In scene understanding for autonomous vehicles (AVs), models trained on the available
datasets fail to generalize well to the complex, real-world scenarios with higher dynamics. In …

Cascade RetinaNet: Maintaining consistency for single-stage object detection

H Zhang, H Chang, B Ma, S Shan, X Chen - arxiv preprint arxiv …, 2019 - arxiv.org
Recent researches attempt to improve the detection performance by adopting the idea of
cascade for single-stage detectors. In this paper, we analyze and discover that inconsistency …