H Bangalath, M Maaz, MU Khattak… - Advances in …, 2022 - proceedings.neurips.cc
Existing open-vocabulary object detectors typically enlarge their vocabulary sizes by leveraging different forms of weak supervision. This helps generalize to novel objects at …
The goal of open-vocabulary detection is to identify novel objects based on arbitrary textual descriptions. In this paper, we address open-vocabulary 3D point-cloud detection by a …
Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training. However, major challenges …
Abstract Weakly Supervised Object Detection (WSOD) has emerged as an effective tool to train object detectors using only the image-level category labels. However, without object …
D Zhang, W Zeng, J Yao, J Han - IEEE Transactions on Pattern …, 2020 - ieeexplore.ieee.org
In recent years, weakly supervised object detection has attracted great attention in the computer vision community. Although numerous deep learning-based approaches have …
Weakly supervised object detection (WSOD) has received widespread attention since it requires only image-category annotations for detector training. Many advanced approaches …
X Xu, BG De Soto - … of the International Symposium on Automation …, 2020 - researchgate.net
The use of robotic systems on construction sites can efficiently reduce construction time and increase safety by replacing construction workers in monotonous or dangerous operations …
J Mai, M Yang, W Luo - … of the IEEE/CVF conference on …, 2020 - openaccess.thecvf.com
Weakly supervised object localization (WSOL) aims to localize object with only weak supervision like image-level labels. However, a long-standing problem for available …