arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.11998cs.CV
收藏

有效的以角色为中心的人-物交互检测

Effective Actor-centric Human-object Interaction Detection

School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(华中科技大学人工智能与自动化学院)

Kunlun Xu, Zhimin Li, Zhijun Zhang, Leizhen Dong, Wenhui Xu, Luxin Yan, Sheng Zhong, Xu Zou

摘要:

虽然人-物交互(HOI)检测近年来取得了巨大的进展,但由于图像中存在多个人和物体的复杂交互,这将不可避免地导致歧义,因此仍然具有挑战性。大多数现有的方法要么生成所有的人-物体对候选人,并推断他们的关系,连续裁剪的局部特征,在两个阶段的方式,或直接预测的交互点在一个阶段的过程。然而,两阶段或一阶段方法分别缺乏空间配置或推理步骤,限制了它们在此类复杂场景中的性能。为了避免这种歧义,我们提出了一个新的演员为中心的框架。其主要思想是在交互推断时:1)根据角色位置获取整幅图像的非局部特征,建立角色与上下文之间的关系模型; 2)使用对象分支生成像素级交互区域预测,交互区域表示对象中心区域。此外,我们还使用一个演员分支来获得演员的交互预测,并提出了一种新的组合策略的基础上中心点索引,以产生最终的HOI预测。由于使用的非本地功能和部分耦合属性的人-物体组成策略,我们提出的框架可以更准确地检测HOI,特别是对于复杂的图像。大量的实验结果表明,我们的方法达到了最先进的具有挑战性的V-COCO和HICO-DET基准,特别是在多个人和/或物体的场景更强大。

英文摘要:

While Human-Object Interaction(HOI) Detection has achieved tremendous advances in recent, it still remains challenging due to complex interactions with multiple humans and objects occurring in images, which would inevitably lead to ambiguities. Most existing methods either generate all human-object pair candidates and infer their relationships by cropped local features successively in a two-stage manner, or directly predict interaction points in a one-stage procedure. However, the lack of spatial configurations or reasoning steps of two- or one- stage methods respectively limits their performance in such complex scenes. To avoid this ambiguity, we propose a novel actor-centric framework. The main ideas are that when inferring interactions: 1) the non-local features of the entire image guided by actor position are obtained to model the relationship between the actor and context, and then 2) we use an object branch to generate pixel-wise interaction area prediction, where the interaction area denotes the object central area. Moreover, we also use an actor branch to get interaction prediction of the actor and propose a novel composition strategy based on center-point indexing to generate the final HOI prediction. Thanks to the usage of the non-local features and the partly-coupled property of the human-objects composition strategy, our proposed framework can detect HOI more accurately especially for complex images. Extensive experimental results show that our method achieves the state-of-the-art on the challenging V-COCO and HICO-DET benchmarks and is more robust especially in multiple persons and/or objects scenes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑