Team seminar

PhD student Van Hao Le will give a talk on his work entitled “Performance characterization of 2D CNN features for partial video copy detection”

Abstract: 2D CNN are main components for Partial Video Copy Detection (PVCD). 2D CNN features serve for the retrieval and matching of videos. Robustness is a key property of these features. It is a well-known problem in the computer vision field but little investigated for PVCD. In this talk, we first introduce briefly the PCVD and CNN approaches in the literature. Next, we report (i) large-scale experiments with 700 B of comparisons of 4.4 M feature vectors, and (ii) a method for the characterization of key-frames with 2D CNN features. It provides a fine categorization of key-frames and allows a deeper characterization of a PVCD problem with 2D CNN features.