Human Pose Driven Object Effects Recommendation

Abstract

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.

Everything2Motion: Synchronizing Diverse Inputs via a Unified Framework for Human Motion Synthesis

“…The task of synthesizing realistic human motions -a cornerstone in the animation of robots (Khatib et al 2009) and digital avatars (Lee et al 2002) -is an imperative at the crossroads of various disciplines such as film making (Huang et al 2019), video game development (Menache 2000), and live broadcasting (Fan et al 2022). The pursuit of authenticity in digital human movements, particularly those that exhibit a nuanced response to environmental stimuli, has traditionally been under the purview of action directors and artists, facilitated by sophisticated equipment.…”