In this chapter we first describe some HVS-based approaches which try to model the visual processing stream described above, since these approaches were originally used to predict visual quality. We then describe recently proposed structural and information-theoretic approaches and feature-based approaches which are commonly used. Further, we describe recent motion-modeling based approaches, and detail performance evaluation and validation techniques for VQA algorithms. Finally, we touch upon some possible future directions for research on VQA and conclude the chapter.