|URNet||0.6604||Oct. 17, 2019, 9:08 p.m.||Tianfei Zhou, Wenguan Wang, Jianbing Shen, Zhijie Zhang (Inception Institute of Artificial Intelligence)||We propose a Unified Relationship detection Network (URNet) in this contest. We jointly train entity detection/segmentation and relationship inference in an end-to-end way. Our URNet is built on Cascade (Mask)RCNN, which is further extended to add a new branch for relationship recognition for each human-object pair. The relationship recognition branch operates on rich multi-modal features for accurate inference.|
|GMVM||0.6026||Oct. 17, 2019, 5:11 a.m.||Zanhui Fan, Han Wang, Peng Chen, Yusen Qin, Shengjin Wang, Zichong Chen (Segway Robotics, Tsinghua University, Dalian Neusoft University of Information)||The interactions in HOI-W challenge are highly correlated with object categories and location information is critical to determining whether an interaction between a person and an object exists. We propose a human-object-interaction detection scheme consisting of three parts…|
|Faster Interaction Net||0.5693||Oct. 17, 2019, 5:01 a.m.||Haoliang Tan, Yu Zhu, Guodong Guo (Institute of Deep Learning, Baidu Research, Xi’an Jiaotong University, Xi’an, China, National Engineering Laboratory for Deep Learning Technology and Application, Beijing China)||We decompose the problem into two steps: 1) Human and Object bounding-boxes detection and 2) human-object Interaction recognition…|
|F2INet||0.4913||Oct. 17, 2019, 5:06 a.m.||Shuchang Lyu, Lingyun Zeng (Beihang University)||We propose a two-stage architecture named Faster Fusion Interaction Network (F2INet) for the human-object interaction (HOI) task…|
|test||0.4871||Oct. 17, 2019, 8:43 p.m.||test||test|
|m15_9||0.4477||Oct. 17, 2019, 9:53 p.m.||9||9|
|6_post||0.4268||Oct. 17, 2019, 9:24 p.m.||6||6|
|Hierarchical joint training model||0.4114||Oct. 17, 2019, 5:08 a.m.||Xijie Huang, Yong-Lu Li, Xinpeng Liu (Shanghai Jiao Tong University)||We apply a hierarchical joint training scheme…|
|FNet||0.3965||Oct. 17, 2019, 2:18 p.m.||changge||fusion model|
|geometry embedding baseline||0.3292||Oct. 17, 2019, 5:09 a.m.||Rongjie Li, Haozhe Wang (ShanghaiaTech University, China)||We resampled the detection boxes while training and added a module which embedding the relvant position of subject and object for encoded the geometry information.|
|zsp||0.204||Oct. 17, 2019, 5:26 a.m.||–||–|
AI is evolving. Don't get left behind.
AI insights delivered straight to your inbox.