Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Lin (Yuanbo) Wu"'
Autor:
Deyin Liu, Lin (Yuanbo) Wu, Richang Hong, Zongyuan Ge, Jialie Shen, Farid Boussaid, Mohammed Bennamoun
The vulnerability of re-identification (re-ID) models under adversarial attacks is of significant concern as criminals may use adversarial perturbations to evade surveillance systems. Unlike a closed-world re-ID setting (i.e., a fixed number of train
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2e859bfbd13d11041cf903adbac08f06
https://cronfa.swan.ac.uk/Record/cronfa63558
https://cronfa.swan.ac.uk/Record/cronfa63558
Publikováno v:
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence.
Multi-scale representation learning aims to leverage diverse features from different layers of Convolutional Neural Networks (CNNs) for boosting the feature robustness to scale variance. For dense prediction tasks, two key properties should be satisf
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::061c7796e582c0a2da238467bd73c0fb
https://doi.org/10.24963/ijcai.2022/204
https://doi.org/10.24963/ijcai.2022/204
Text-based person search (TBPS) is of significant importance in intelligent surveillance, which aims to retrieve pedestrian images with high semantic relevance to a given text description. This retrieval task is characterized with both modal heteroge
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c11932d321133ea4b49279491fd7f7e4