ApVideor: a video automaker for apparels
Video plays a great important role in online apparel sales, which is a vital tool for publicity and to provide consumers with space of imagination. However, as the apparel market rapidly updates in large amounts every day, creating videos for fast increasing clothes can be challenging and labor-consuming. Considering this, we present ApVideor, a musicdriven video generation system customized for displaying clothes. This system consists of two main modules: music recommendation module and audio-visual synthesis module. The former assists users in searching background music that matches the apparel style, while the latter combines the audio and visuals into a video by music-driven approaches. Our user study suggests that this system makes the video creation process significantly easier and faster than manual creation. Meanwhile, the viewer test suggests that apparel-displaying videos created using our system are of comparable quality to those created manually by people who have worked with video editing.
SWA dataset
SWA is a brand new dataset which contains 14257 background soundtracks of women apparel and seller-annotated style information from TaoBao.com. This dataset aims to support research on music recommendation for apparel.
Click here to get the SWA dataset for task of music recommendation.
Project codes
Click here to get the code from github.
Results of various transition detection algrithoms
Apvideor
Cut-to-beat
Agglomerative Clustering
Videos created by ApVideor and human users
We list 2 demo sets to show the result.
Note: In each set below, the left video is maded by our Apvideor and the right video is maded by video editors manually.
Contact us
If you have any problem, please contact us (huiz@zju.edu.cn).