Artificial intelligence (AI) coupled with promising machine learning (ML) techniques well known from computer science is broadly affecting many aspects of various fields including …
K Zheng, W Liu, L He, T Mei, J Luo… - Proceedings of the …, 2021 - openaccess.thecvf.com
Abstract Unsupervised Domain Adaptive (UDA) person re-identification (ReID) aims at adapting the model trained on a labeled source-domain dataset to a target-domain dataset …
Road segmentation from remote-sensing images is a challenging task with wide ranges of application potentials. Deep neural networks have advanced this field by leveraging the …
K Zhu, Y Cao, W Zhai, J Cheng… - Proceedings of the …, 2021 - openaccess.thecvf.com
Few-shot class-incremental learning is to recognize the new classes given few samples and not forget the old classes. It is a challenging task since representation optimization and …
With the prevalence of smart appliances, smart meters, and Internet of Things (IoT) devices in smart grids, artificial intelligence (AI) built on the rich IoT big data enables various energy …
J Yu, H Zhou, Y Zhan, D Tao - Proceedings of the AAAI Conference on …, 2021 - ojs.aaai.org
Unsupervised cross-modal hashing (UCMH) has become a hot topic recently. Current UCMH focuses on exploring data similarities. However, current UCMH methods calculate …
End-to-end text spotting aims to integrate scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in …
Scene graph generation (SGG) aims to detect objects and predict the relationships between each pair of objects. Existing SGG methods usually suffer from several issues, including 1) …
Although point-based networks are demonstrated to be accurate for 3D point cloud modeling, they are still falling behind their voxel-based competitors in 3D detection. We …