Extracting moods from pictures and sounds: towards truly personalized TV

High-Dimensional Indexing for Video Retrieval

“…However, such detectors are available only for a small number of concepts and often provide low accuracy rates. If concepts such as 'water', 'sky', 'cars', 'faces' or 'outdoors' are relatively well-detected, concepts such as 'entertainment' or aspects such as preferences or moods Hanjalic (2006) are far from being correctly identified. To cope with the automatic concept detection challenges, the multimedia communities are currently establishing concept lexicons Naphade et al (2006); Snoek, Worring, van Gemert, Geusebroek & Smeulders (2006), focusing on the concepts that are feasible for automatic detection Hauptmann et al (2007);Snoek, Worring, Geusebroek, Koelma, Seinstra & Smeulders (2006); Yang & Hauptmann (2006 Deselaers et al (2004);Jiang et al (2007)?…”

“…Such an answer is difficult to obtain, because the retrieval quality is a problem that surpasses the choice of descriptors. However, we can say that retrieval based on low-level features is already mature Flickner et al (1995); Rehatschek et al (2004); Smith & Chang (1996); Wactlar et al (1996), but inferring high-level features is still a challenging task Gevers & Smeulders (2004);Hanjalic (2006); Huijbregts et al (2007); Smeulders et al (2000); Xiong et al (2006). As the high-level feature extraction depends, up to some extent, on the low-level features, we expect that the use of low-level features will still grow Burghouts & Geusebroek (2009).…”

“…The features that can be checked for relevance range from low-level ones such as color or shape, to high-level and subjective ones such as a feelings or moods Dimitrova (2004);Hanjalic (2006). In the sequel, the most common similarity models are presented.…”

Analyzing Emotional Semantics of Abstract Art Using Low-Level Image Features

“…While the CBIR systems are conventionally designed for recognizing object and scene such as plants, animals, people etc., an Emotional Semantic Image Retrieval (ESIR) [17] system aims at incorporating the emotional reflections to enable queries like "beautiful flowers", "lovely dogs", "happy faces" etc. In analogy to the concept of semantic gap implying the limitations of image recognition, the emotional gap can be defined as "the lack of coincidence between the measurable signal properties, commonly referred to as features, and the expected affective state in which the user is brought by perceiving the signal" [6].…”

Video Affective Content Recognition Based on Genetic Algorithm Combined HMM

“…Intensive research efforts in the field of multimedia content analysis in the past 15 years have resulted in an abundance of theoretical and algorithmic solutions for extracting the content-related information from audiovisual information [1]. However, due to the inscrutable nature of human emotions and seemingly broad affective gap from low-level features, the video affective content analysis is seldom addressed [2].…”