Tasks Integrated Networks: Joint Detection and Retrieval for Image Search
作者： Xinbo Gao , Liang Wang , Yi Yang , Lei Zhang , Zhenwei He
DOI:
关键词: Computer science 、 Artificial intelligence 、 Softmax function 、 Machine learning 、 Annotation 、 Robustness (computer science) 、 Discriminative model
摘要: The traditional object (person) retrieval (re-identification) task aims to learn a discriminative feature representation with intra-similarity and inter-dissimilarity, which supposes that the objects in an image are manually or automatically pre-cropped exactly. However, in many real-world searching scenarios (eg, video surveillance), the objects (eg, persons, vehicles, etc.) are seldom accurately detected or annotated. Therefore, object-level retrieval becomes intractable without bounding-box annotation, which leads to a new but challenging topic, ie …
arxiv.org
harvard.edu参考文章(67)
Bin Yang, Junjie Yan, Zhen Lei, Stan Z. Li, Convolutional Channel Features international conference on computer vision. pp. 82- 90 ,(2015) , 10.1109/ICCV.2015.18
Douglas Gray, Hai Tao, Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features european conference on computer vision. pp. 262- 275 ,(2008) , 10.1007/978-3-540-88682-2_21
Ross Girshick, Fast R-CNN international conference on computer vision. pp. 1440- 1448 ,(2015) , 10.1109/ICCV.2015.169
Wei Li, Rui Zhao, Xiaogang Wang, Human reidentification with transferred metric learning asian conference on computer vision. pp. 31- 44 ,(2012) , 10.1007/978-3-642-37331-2_3
Karen Simonyan, Andrew Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition computer vision and pattern recognition. ,(2014)
Yonglong Tian, Ping Luo, Xiaogang Wang, Xiaoou Tang, Pedestrian detection aided by deep learning semantic tasks computer vision and pattern recognition. pp. 5079- 5087 ,(2015) , 10.1109/CVPR.2015.7299143
Ejaz Ahmed, Michael Jones, Tim K Marks, None, An improved deep learning architecture for person re-identification computer vision and pattern recognition. pp. 3908- 3916 ,(2015) , 10.1109/CVPR.2015.7299016
Shengcai Liao, Yang Hu, Xiangyu Zhu, Stan Z Li, None, Person re-identification by Local Maximal Occurrence representation and metric learning computer vision and pattern recognition. pp. 2197- 2206 ,(2015) , 10.1109/CVPR.2015.7298832
Shengyong Ding, Liang Lin, Guangrun Wang, Hongyang Chao, Deep feature learning with relative distance comparison for person re-identification Pattern Recognition. ,vol. 48, pp. 2993- 3003 ,(2015) , 10.1016/J.PATCOG.2015.04.005
Xiaogang Wang, Intelligent multi-camera video surveillance: A review Pattern Recognition Letters. ,vol. 34, pp. 3- 19 ,(2013) , 10.1016/J.PATREC.2012.07.005