Detecting and Recognizing Human-Object Interactions
作者： Georgia Gkioxari , Piotr Dollár , Kaiming He , Ross Girshick
DOI:
关键词: Action (philosophy) 、 Task (project management) 、 Object (computer science) 、 Computer science 、 Machine learning 、 Artificial intelligence
摘要: … , action – is a powerful cue for localizing the objects they are interacting with. To exploit this cue, our model learns to predict an action-… , and by fusing these predictions it efficiently infers …
arxiv.org
harvard.edu
128.84.21.199参考文章(28)
Varun Ramakrishna, Takeo Kanade, Yaser Sheikh, Shih-En Wei, Convolutional Pose Machines arXiv: Computer Vision and Pattern Recognition. ,(2016)
Arun Mallya, Svetlana Lazebnik, Learning Models for Actions and Person-Object Interactions with Transfer to Question Answering european conference on computer vision. pp. 414- 428 ,(2016) , 10.1007/978-3-319-46448-0_25
Chao-Yeh Chen, Kristen Grauman, Predicting the Location of “interactees” in Novel Human-Object Interactions asian conference on computer vision. pp. 351- 367 ,(2014) , 10.1007/978-3-319-16865-4_23
Mark Yatskar, Luke Zettlemoyer, Ali Farhadi, Situation Recognition: Visual Semantic Role Labeling for Image Understanding computer vision and pattern recognition. pp. 5534- 5542 ,(2016) , 10.1109/CVPR.2016.597
Yu-Wei Chao, Huayi Zeng, Xieyang Liu, Yunfan Liu, Jia Deng, Learning to Detect Human-Object Interactions arXiv: Computer Vision and Pattern Recognition. ,(2017)
Serge Belongie, Piotr Dollár, Bharath Hariharan, Kaiming He, Ross Girshick, Tsung-Yi Lin, Feature Pyramid Networks for Object Detection arXiv: Computer Vision and Pattern Recognition. ,(2016)
Shaoqing Ren, Kaiming He, Jian Sun, Xiangyu Zhang, Deep Residual Learning for Image Recognition arXiv: Computer Vision and Pattern Recognition. ,(2015)
Pierre Sermanet, Christian Szegedy, Vincent Vanhoucke, Dragomir Anguelov, Yangqing Jia, Andrew Rabinovich, Dumitru Erhan, Scott Reed, Wei Liu, Going Deeper with Convolutions arXiv: Computer Vision and Pattern Recognition. ,(2014)
Georgia Gkioxari, Jitendra Malik, Ross Girshick, Contextual Action Recognition with R*CNN arXiv: Computer Vision and Pattern Recognition. ,(2015)
Ross Girshick, Fast R-CNN arXiv: Computer Vision and Pattern Recognition. ,(2015)