Dancing to music is one of human's innate abilities since ancient times. In artificial intelligence research, however, synthesizing dance movements (complex human motion) from music is a challenging problem, which suffers from the high spatial-temporal complexity in human motion dynamics modeling. Besides, the consistency of dance and music in terms of style, rhythm and beat also needs to be taken into account. Existing works focus on the short-term dance generation with music, e.g. less than 30 seconds. In this paper, we propose a novel seq2seq architecture for long sequence dance generation with music, which consists of a transformer based music encoder and a recurrent structure based dance decoder. By restricting the receptive field of self-attention, our encoder can efficiently process long musical sequences by reducing its quadratic memory requirements to the linear in the sequence length. To further alleviate the error accumulation in human motion synthesis, we introduce a dynamic auto-condition training strategy as a new curriculum learning method to facilitate the long-term dance generation. Extensive experiments demonstrate that our proposed approach significantly outperforms existing methods on both automatic metrics and human evaluation. Additionally, we also make a demo video to exhibit that our approach can generate minute-length dance sequences that are smooth, natural-looking, diverse, styleconsistent and beat-matching with the music. The demo video is now available at https://www.youtube.com/watch?v=P6yhfv3vpDI. * Equal contribution. † Work done during the internship at Microsoft. Preprint. Under review.

Abstract-UI is an important part of software product. Considering the complexity of web UI, generating the web page from a mockup proposes requirements for rich experience of developer. Extracting visible elements and their relationship, selecting proper tags, generating source code are time-consuming and error-prone task. In this paper, we propose a method to automate the transforming of the mockup to the web page. Our approach starts from the mockup designed by the art designers, and extracts the elements based on the color features of the edges. Then a bottom-up tag generating method based on the Random Forest is proposed to select the tags for elements. Finally the web page is generated by the definition of the elements. The generating tags can achieve an average accuracy of more than 84%, which can meet the basic requirements of the developers.