Results 31 to 40 of about 59,151 (296)

Few-shot activity recognition with cross-modal memory network

, 2023
Deep learning based action recognition methods require large amount of labelled training data. However, labelling large-scale video data is time consuming and tedious.
Liu, J, Chang, X, Luo, M, Zhang, L, Hauptmann, AG, Prakash, M   +5 more
core   +1 more source

MetaView: Few-shot Active Object Recognition

CoRR, 2021
In robot sensing scenarios, instead of passively utilizing human captured views, an agent should be able to actively choose informative viewpoints of a 3D object as discriminative evidence to boost the recognition accuracy. This task is referred to as active object recognition.
Wei Wei, Haonan Yu, Haichao Zhang 0001, Wei Xu 0017, Ying Wu 0001   +4 more
openaire   +2 more sources

Temporal-Viewpoint Transportation Plan for Skeletal Few-Shot Action Recognition

, 2023
We propose a Few-shot Learning pipeline for 3D skeleton-based action recognition by Joint tEmporal and cAmera viewpoiNt alIgnmEnt (JEANIE). To factor out misalignment between query and support sequences of 3D body joints, we propose an advanced variant ...
Koniusz, Piotr, Wang, Lei
core   +1 more source

A Few-shot Learning Approach for Historical Ciphered Manuscript Recognition

, 2021
Encoded (or ciphered) manuscripts are a special type of historical documents that contain encrypted text. The automatic recognition of this kind of documents is challenging because: 1) the cipher alphabet changes from one document to another, 2) there is
Yousri Kessentini, Souibgui, Mohamed Ali,, Tudor, Crina,, Kessentini, Yousri,, Fornes, Alicia,, Alicia Fornes, Crina Tudor, Mohamed Ali Souibgui   +7 more
core   +1 more source

Continuous Gesture Sequences Recognition Based on Few-Shot Learning

International Journal of Aerospace Engineering, 2022
A large number of demands for space on-orbit services to ensure the on-orbit system completes its specified tasks are foreseeable, and the efficiency and the security are the most significant factors when we carry out an on-orbit mission.
Zhe Liu, Cao Pan, Hongyuan Wang
doaj   +1 more source

Few-Shot Action Recognition with Permutation-Invariant Attention [PDF]

, 2020
ECCV2020 ...
Hongguang Zhang, Li Zhang 0040, Xiaojuan Qi 0001, Hongdong Li, Philip H. S. Torr, Piotr Koniusz   +5 more
openaire   +3 more sources

Hippocampus-heuristic character recognition network for zero-shot learning in Chinese character recognition

, 2022
The recognition of Chinese characters has always been a challenging task due to their huge variety and complex structures. The current radical-based methods fail to recognize Chinese characters without learning all of their radicals in the training stage.
Huang, Guanjie, Su, Kaile, Luo, Xiangyu, Wang, Shaowei, Gu, Tianlong   +4 more
core   +1 more source

Replication Package - Illicit Content Recognition with Few-shot Learning

, 2023
Replication package and dataset for the paper: When the Few Outweigh the Many: Illicit Content Recognition with Few-shot ...
Cascavilla Giuseppe
core   +2 more sources

Few-shot classification in named entity recognition task [PDF]

Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing, 2019
In proceedings of the 34th ACM/SIGAPP Symposium on Applied ...
Alexander Fritzler, Varvara Logacheva, Maksim Kretov   +2 more
openaire   +2 more sources

Few-Shot SAR Target Recognition Based on Deep Kernel Learning

IEEE Access, 2022
Deep learning methods have achieved state-of-the-art performance on synthetic aperture radar (SAR) target recognition tasks in recent years. However, obtaining sufficient SAR images for training these deep learning methods is costly in time and labor ...
Ke Wang, Qi Qiao, Gong Zhang, Yihan Xu
doaj   +1 more source