Human-object interaction(HOI) detection is an important task for understanding human activity. Graph structure is appropriate to denote the HOIs in the scene. Since there is an subordination between human and object---human play subjective role and object play objective role in HOI, the relations between homogeneous entities and heterogeneous entities in the scene should also not be equally the same. However, previous graph models regard human and object as the same kind of nodes and do not consider that the messages are not equally the same between different entities. In this work, we address such a problem for HOI task by proposing a heterogeneous graph network that models humans and objects as different kinds of nodes and incorporates intra-class messages between homogeneous nodes and inter-class messages between heterogeneous nodes. In addition, a graph attention mechanism based on the intra-class context and inter-class context is exploited to improve the learning. Extensive experiments on the benchmark datasets V-COCO and HICO-DET demonstrate that the intra-class and inter-class messages are very important in HOI detection and verify the effectiveness of our method.
Human Pose Regression by Combining Indirect Part Detection and Contextual Information
在本文中,我们提出了一种端到端的可训练回归方法,用于从静止图像中估计人体姿态。我们使用建议的Soft-argmax函数将特征映射直接转换为关节坐标,从而形成完全可微的框架。我们的方法能够间接地学习热图表示,而无需额外的人工地面真实生成步骤。因此,可以以无缝的方式将上下文信息包括到姿态预测中。我们在两个非常具有挑战性的数据集上评估了我们的方法,即Leeds Sports Poses(LSP)和MPII Human Pose数据集,在所有现有的回归方法中达到了最佳性能,并且与最先进的基于检测的方法具有可比性。
Human Pose Estimation with Spatial Contextual Information
Baidu Research, Baidu Inc.(百度研究部,百度公司);Hong Kong University of Science and Technology(香港科技大学);YouTu Lab, Tencent(优图实验室,腾讯);The Chinese University of Hong Kong(香港中文大学);University of Kentucky(肯塔基大学)
Contextual Guided Segmentation Framework for Semi-supervised Video Instance Segmentation
National Institute of Informatics(国立信息学研究所);University of Dayton(代顿大学);University of Science and Vietnam National University, Ho Chi Minh(胡志明市越南国家大学科学大学)
Learning to See the Elephant in the Room: Self-Supervised Context Reasoning in Humans and AI
College of Computing and Data Science, Nanyang Technological University(计算与数据科学学院,南洋理工大学);CFAR and I2R, Agency for Science, Technology and Research(CFAR和I2R,科技研究局);Boston Children’s Hospital, Harvard Medical School(哈佛医学院儿童医院)
KARAMEL: Knowledge-Aware Ranking for Multimodal Entity Linking in the Arts via Heterogeneous Graphs
University of Bari Aldo Moro(巴里大学阿尔多·莫罗分校);Hasso Plattner Institute(哈索·普拉特纳研究所);University of Potsdam(波茨坦大学);ZBW - Leibniz Information Centre for Economics(ZBW - 莱布尼茨经济信息中心);University of Kiel(基尔大学)
When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenes
ETH Zürich(苏黎世联邦理工学院);Children’s Hospital, Harvard Medical School(哈佛医学院儿童医院);Center for Brains, Minds and Machines(脑、心智与机器中心);Harvard College, Harvard University(哈佛大学哈佛学院);School of Engineering and Applied Sciences, Harvard University(哈佛大学工程与应用科学学院)
Lift-the-flap: what, where and when for context reasoning
Boston Children’s Hospital, Harvard Medical School(波士顿儿童医院,哈佛医学院);Harvard College(哈佛大学学院);Mayo Clinic Graduate School of Biomedical Sciences(梅奥诊所生物医学研究生院);Yale University(耶鲁大学)