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 2209.08353cs.CVcs.AI
收藏

人体姿势驱动物体效果推荐

Human Pose Driven Object Effects Recommendation

Renmin university of china(中国人民大学);Tinghua university(清华大学)

Zhaoxin Fan, Fengxin Li, Hongyan Liu, Jun He, Xiaoyong Du

摘要:

本文研究微视频平台中的物体效果推荐这一新课题,这对于广告插播等实际应用来说是一个具有挑战性的重要课题。为了避免直接从图像帧中学习视频内容所引起的背景偏差问题,我们提出利用隐藏在3D人体姿势中的有意义的肢体语言进行推荐。为此,在这项工作中,介绍了一种新的人类姿势驱动的对象效果推荐网络PoseRec。PoseRec利用3D人体姿势检测的优势,从多帧3D人体姿势中学习信息,用于视频项目注册,从而获得高质量的对象效果推荐性能。此外,为了解决对象效果推荐中存在的固有模糊性和稀疏性问题,我们进一步提出了一种新的项目感知隐式原型学习模块和一种新的姿势感知直推式硬否定挖掘模块,以更好地学习姿势-项目关系。此外,为了对新的研究主题的方法进行基准测试,我们建立了一个新的对象效果推荐数据集Pose-OBE。Pose-OBE上的大量实验表明,我们的方法可以实现优于强基线的性能。

英文摘要:

In this paper, we research the new topic of object effects recommendation in micro-video platforms, which is a challenging but important task for many practical applications such as advertisement insertion. To avoid the problem of introducing background bias caused by directly learning video content from image frames, we propose to utilize the meaningful body language hidden in 3D human pose for recommendation. To this end, in this work, a novel human pose driven object effects recommendation network termed PoseRec is introduced. PoseRec leverages the advantages of 3D human pose detection and learns information from multi-frame 3D human pose for video-item registration, resulting in high quality object effects recommendation performance. Moreover, to solve the inherent ambiguity and sparsity issues that exist in object effects recommendation, we further propose a novel item-aware implicit prototype learning module and a novel pose-aware transductive hard-negative mining module to better learn pose-item relationships. What's more, to benchmark methods for the new research topic, we build a new dataset for object effects recommendation named Pose-OBE. Extensive experiments on Pose-OBE demonstrate that our method can achieve superior performance than strong baselines.

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。

↑