6 accepted papers
Learning to retrieve dance poses from music, a cross-modal retrieval task, has gained prominence in assisting choreographers in creating dances that harmonize with music. The recent predominant approach is to map music into 3D pose and shape space, and then match it with dance poses [1]. However, we…
Choreography is an artful blend of technique and creativity, requiring the meticulous design of movement sequences in harmony with music. To support choreographers in this intricate task, this work proposes a "music-to-dance pose retrieval" system that uses music snippets to retrieve dance poses, pr…
Learning to capture human motion is essential to 3D human pose and shape estimation from monocular video. However, the existing methods mainly rely on recurrent or convolutional operation to model such temporal information, which limits the ability to capture non-local context relations of human mot…
Recently, a non-local (NL) operation has been designed as the central building block for deep-net models to capture long-range dependencies (Wang et al. 2018). Despite its excellent performance, it does not consider the interaction between positions across channels and layers, which is crucial in fi…
Varying types of shots is a fundamental element in the language of film, commonly used by a visual storytelling director to convey the emotion, ideas, and art. To classify such types of shots from images, we present a new framework that facilitates the intriguing task by addressing two key issues. W…
This paper presents a deep similarity matching-based emotion-oriented music video (MV) generation system, called DEMV-matchmaker, which utilizes an emotion-oriented deep similarity matching (EDSM) metric as a bridge to connect music and video. Specifically, we adopt an emotional temporal course mode…