Visual Question Answering aims to answer the free-form natural language question based
on the visual clues in a given image. It is a difficult problem as it requires understanding the …

Illustrating a multi-sentence story with visual content is a significant challenge in multimedia
research. While previous works have focused on sequential story-to-visual representations …

Talking face generation is a demanding task to synthesize a high quality video with accurate
lip synchronization and rhythmic head motion. However, existing methods always suffer from …

In this paper, we propose a novel approach to video object segmentation where dual
streams consisting of a shared network and a special network are designed to constitute the …

Person clustering with multi-modal clues, including faces, bodies, and voices, is critical for
various tasks, such as movie parsing and identity-based movie editing. Related methods …

The objective of this work is to manipulate visual timelines (eg a video) through natural
language instructions, making complex timeline editing tasks accessible to non-expert or …

Video description methods aim to produce the most relevant description of a video. This
could be description based on full video, frame based or based on important events of the …

Video editing is a high-required job, for it requires skilled artists or workers equipped with
plentiful physical strength and multidisciplinary knowledge, such as cinematography …

As vlog has become increasingly popular on videosharing platforms, more amateurs have
participated in vlog creation. One critical step of attractive vlog creation is multi-shot …

Video editing is a high-required job, for it requires skilled artists or workers equipped with
plentiful physical strength and multidisciplinary knowledge, such as cinematography …