In this paper, we introduce the DEEP-SEE FACE framework, an assistive device designed to improve cognition, interaction, and communication of visually impaired (VI) people in social encounters. The proposed approach jointly exploits computer vision algorithms (region proposal networks, ATLAS tracking and global, and low-level image descriptors) and deep convolutional neural networks in order to detect, track, and recognize, in real-time, various persons existent in the video streams. The major contribution of the paper concerns a global, fixed-size face representation that takes into the account of various video frames while remaining independent of the length of the image sequence. To this purpose, we introduce an effective weight adaptation scheme that is able to determine the relevance assigned to each face instance, depending on the frame degree of motion/camera blur, scale variation, and compression artifacts. Another relevant contribution involves a hard negative mining stage that helps us differentiating between known and unknown face identities. The experimental results, carried out on a large-scale data set, validate the proposed methodology with an average accuracy and recognition rates superior to 92%. When tested in real life, indoor/outdoor scenarios, the DEEP-SEE FACE prototype proves to be effective and easy to use, allowing the VI people to access visual information during social events