Deep vision multimodal learning aims at combining deep visual representation learning with other modalities, such as text, sound, and data collected from other sensors. With the fast development of deep learning, vision multimodal learning has gained much interest from the community. This paper reviews the types of architectures used in multimodal learning, including feature extraction, modality aggregation, and multimodal loss functions. Then, we discuss several learning paradigms such as supervised, semi-supervised, self-supervised, and transfer learning. We also introduce several practical challenges such as missing modalities and noisy modalities. Several applications and benchmarks on vision tasks are listed to help researchers gain a deeper understanding of progress in the field. Finally, we indicate that pretraining paradigm, unified multitask framework, missing and noisy modality, and multimodal task diversity could be the future trends and challenges in the deep vision multimodal learning field. Compared with existing surveys, this paper focuses on the most recent works and provides a thorough discussion of methodology, benchmarks, and future trends.