The impact of culture in visual emotion perception has recently captured the attention of multimedia research. In this study, we provide powerful computational linguistics tools to explore, retrieve and browse a dataset of 16K multilingual affective visual concepts and 7.3M Flickr images.
EventNet - A Large Scale Structured Concept Library
EventNet is a large scale structured concept library, which includes automatic detection models for the video events and constituent concepts using deep learning with around 95K training videos from YouTube. The system allows users to explore rich hierarchical structures among video events, relations between concepts and events, and automatic detection of events and concepts embedded in user-uploaded videos in a live fashion.
Recent years have witnessed the rapid enhancement of video quality towards higher definition. To achieve better compression performance, the Human Visual System (HVS) is carefully studied and then incorporated into video codec. Just-noticeable-difference (JND) models have been developed for measuring the maximum distortion that is imperceptible to the HVS. In this work, we focus on the exploration of HVS characteristics and its application in image/video compression fields.