Special issue on deep learning in image and video retrieval

An overview of the state of the art of deep learning applied to video understanding is given by the paper “A Study on Deep Learning Spatiotemporal Models and Feature Extraction Techniques for Video Understanding” by M. Suresha, S. Kuppa and D.S. Raghukumar. The paper “Learning Visual Features for Relational CBIR” by N. Messina, G. Amato, F. Carrara, F. Falchi and C. Gennaro defines Relational Content-Based Image Retrieval as the task of finding images containing similar inter-object relationships. Evaluation on the ImageNet dataset and four well-known CNNs showed that their system achieves state-of-the-art performance.