T Zhang, D Chang, Z Ma, J Guo - … International Conference on …, 2021 - ieeexplore.ieee.org
Fine-grained visual classification aims to recognize images belonging to multiple sub- categories within a same category. It is a challenging task due to the inherently subtle …
W Xu, D Liang, Y Zheng, J Xie… - IEEE Signal Processing …, 2021 - ieeexplore.ieee.org
Object counting aims to estimate the number of objects in images. The leading counting approaches focus on single-category counting tasks and achieve impressive performance …
B Mao, F Tang, K Yuichi, N Kato - arXiv preprint arXiv:2101.01588, 2021 - arxiv.org
Green communications have always been a target for the information industry to alleviate energy overhead and reduce fossil fuel usage. In current 5G and future 6G era, there is no …
Learning representation carrying rich local information is essential for recognizing fine- grained objects. Existing methods to this task resort to multi-stage frameworks to capture fine …
W Gao, M Wu, SK Lam, Q Xia, J Zou - Knowledge-Based Systems, 2022 - Elsevier
Self-supervised label augmentation has emerged as an effective means to overcome the data scarcity problem for supervised vision tasks. Existing rotation-based self-supervised …
X Li, S Wei, J Wang, Y Du, M Ge - Remote Sensing, 2022 - mdpi.com
With the development of remote sensing technology, content-based remote sensing image retrieval has become a research hotspot. Remote sensing image datasets not only contain …
J Wang, Y Zhao, X Ma, Q Gao, M Pan… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Device-free activity recognition (DFAR) is an emerging technique which could infer human activities by analyzing his/her influence on surrounding wireless signals. It may empower …
X Zhu, Y Li, H Fu, X Fan, Y Shi, J Lei - Neurocomputing, 2021 - Elsevier
RGB-D salient object detection aims at identifying attractive objects in a scene by combining the color image and depth map. However, due to the differences between RGB-D image …
K Liu, K Chen, K Jia - IEEE Transactions on Image Processing, 2022 - ieeexplore.ieee.org
Fine-grained visual classification can be addressed by deep representation learning under supervision of manually pre-defined targets (eg, one-hot or the Hadamard codes). Such …