Best Multimodal Paper Award to Nikolaos Pappas and co-authors at ICMR 2016

The paper "Multilingual Visual Sentiment Concept Matching" by Nikolaos Pappas, Mercan Topkara, Miriam Redi, Brendan Jou, Tao Chen, Hongyi Liu, Shih-Fu Chang has received the Best Multimodal Paper Award at the Annual ACM International Conference on Multimedia Retrieval (ICMR), held on June 6-9 in New York.

The impact of culture in visual emotion perception has recently captured the attention of multimedia research. Focusing on the language dimension of culture, this paper proposes a clustering method for multilingual affective visual concepts based on distributed representations, which enables their analysis and comparison across languages. The discovered clusters which were evaluated in terms of semantic and sentiment consistency provide interesting cultural insights such as lexical, affective, and visual variation, as well as, uniqueness and expressivity.

The research was conducted in collaboration with Columbia University (DVMM lab), Yahoo! Research and JW Player.

The article is available at: Multilingual Visual Sentiment Concept Matching