Care about you: towards large-scale human-centric visual relationship detection.
作者： Ian D. Reid , Chunhua Shen , Anton van den Hengel , Bohan Zhuang , Qi Wu
DOI:
关键词:
摘要: Visual relationship detection aims to capture interactions between pairs of objects in images. Relationships and humans represent a particularly important subset this problem, with implications for challenges such as understanding human behaviour, identifying affordances, amongst others. In addressing problem we first construct large-scale human-centric visual dataset (HCVRD), which provides many more types annotation (nearly 10K categories) than the previous released datasets. This large label space better reflects reality human-object interactions, but gives rise long-tail distribution turn demands zero-shot approach labels appearing only test set. This is time issue has been addressed. We propose webly-supervised these problems demonstrate that proposed model strong baseline on our HCVRD dataset.
arxiv.org
harvard.edu参考文章(30)
Jitendra Malik, Saurabh Gupta, Visual Semantic Role Labeling arXiv: Computer Vision and Pattern Recognition. ,(2015)
Bangpeng Yao, Li Fei-Fei, Recognizing Human-Object Interactions in Still Images by Modeling the Mutual Context of Objects and Human Poses IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 34, pp. 1691- 1703 ,(2012) , 10.1109/TPAMI.2012.67
Bangpeng Yao, Xiaoye Jiang, Aditya Khosla, Andy Lai Lin, Leonidas Guibas, Li Fei-Fei, Human action recognition by learning bases of action attributes and parts international conference on computer vision. pp. 1331- 1338 ,(2011) , 10.1109/ICCV.2011.6126386
Bangpeng Yao, Li Fei-Fei, Modeling mutual context of object and human pose in human-object interaction activities computer vision and pattern recognition. pp. 17- 24 ,(2010) , 10.1109/CVPR.2010.5540235
Mohammad Amin Sadeghi, Ali Farhadi, Recognition using visual phrases CVPR 2011. pp. 1745- 1752 ,(2011) , 10.1109/CVPR.2011.5995711
Bangpeng Yao, Li Fei-Fei, Grouplet: A structured image representation for recognizing human and object interactions computer vision and pattern recognition. pp. 9- 16 ,(2010) , 10.1109/CVPR.2010.5540234
Mykhaylo Andriluka, Leonid Pishchulin, Peter Gehler, Bernt Schiele, 2D Human Pose Estimation: New Benchmark and State of the Art Analysis computer vision and pattern recognition. pp. 3686- 3693 ,(2014) , 10.1109/CVPR.2014.471
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei, ImageNet: A large-scale hierarchical image database computer vision and pattern recognition. pp. 248- 255 ,(2009) , 10.1109/CVPR.2009.5206848
Haibo He, E.A. Garcia, Learning from Imbalanced Data IEEE Transactions on Knowledge and Data Engineering. ,vol. 21, pp. 1263- 1284 ,(2009) , 10.1109/TKDE.2008.239
A. Prest, C. Schmid, V. Ferrari, Weakly Supervised Learning of Interactions between Humans and Objects IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 34, pp. 601- 614 ,(2012) , 10.1109/TPAMI.2011.158