Conventional multimedia understanding is usually built on top of handcrafted features, which are often much restrictive in capturing complex multimedia content. Recent progress on deep learning opens an exciting new era, placing multimedia understanding on a more rigorous foundation with automatically learned representations to model the multimodal data. This workshop is devoted to the publications of high quality papers on technical developments and practical applications around learning-based big multimedia understanding. It will serve as a forum for recent advances in the fields of multimedia content representation, analysis, mining, retrieval, etc.