The China-US Million Book Digital Library Project （Million Book Project） is an intemational cooperation program between China and the US. However, one million digitized books are considered not to be the ultimate go...The China-US Million Book Digital Library Project （Million Book Project） is an intemational cooperation program between China and the US. However, one million digitized books are considered not to be the ultimate goal of the project, but a first step towards universal access to human knowledge. In particular, there are four challenges about the new way to analyze, process, operate, visualize and interact with digital media resource in this library. To tackle these challenges, North China Centre of Million Book Project （in Chinese Academy of Sciences） has initiated several innovative research projects in areas such as multimedia content analysis and retrieval, bilingual services, multimodal information presentation, and knowledge-based organization and services. In this keynote speech, we simply review our work in these areas, and argue that by technological cooperation with these innovation research topics, the project will develop a top-level digital library platform for the million book library.展开更多
This paper presents a novel system for violent scenes detection, which is based on machine learning to handle visual and audio features. MKL （Multiple Kernel Learning） is applied so that multimodality of videos can ...This paper presents a novel system for violent scenes detection, which is based on machine learning to handle visual and audio features. MKL （Multiple Kernel Learning） is applied so that multimodality of videos can be maximized. The largest features of our system is that mid-level concepts clustering is proposed and implemented in order to learn mid-level concepts implicitly. By this algorithm, our system does not need manually tagged annotations. The whole system is trained on the dataset from MediaEval 2013 Affect Task and evaluated by its official metric. The obtained results outperformed its best score.展开更多
Although many existing movie recommender systems have investigated recommendation based on information such as clicks and tags, much less efforts have been made to explore the multimedia content of movies, which has p...Although many existing movie recommender systems have investigated recommendation based on information such as clicks and tags, much less efforts have been made to explore the multimedia content of movies, which has potential information for the elicitation of the user＇s visual and musical preferences. In this paper, we explore the content from three media types （image, text, audio） and propose a novel multi-view semi-supervised movie recommendation method, which represents each media type as a view space for movies. The three views of movies are integrated to predict the rating values under the multi-view framework. ~rthermore, our method considers the casual users who rate limited movies. The algorithm enriches the user profile with a semi-supervised way when there are only few rating histories. Experiments indicate that the multimedia content analysis reveals the user＇s profile in a more comprehensive way. Different media types can be a complement to each other for movie recommendation. And the experimental results validate that our semi-supervised method can effectively enrich the user profile for recommendation with limited rating history.展开更多
文摘The China-US Million Book Digital Library Project （Million Book Project） is an intemational cooperation program between China and the US. However, one million digitized books are considered not to be the ultimate goal of the project, but a first step towards universal access to human knowledge. In particular, there are four challenges about the new way to analyze, process, operate, visualize and interact with digital media resource in this library. To tackle these challenges, North China Centre of Million Book Project （in Chinese Academy of Sciences） has initiated several innovative research projects in areas such as multimedia content analysis and retrieval, bilingual services, multimodal information presentation, and knowledge-based organization and services. In this keynote speech, we simply review our work in these areas, and argue that by technological cooperation with these innovation research topics, the project will develop a top-level digital library platform for the million book library.
文摘This paper presents a novel system for violent scenes detection, which is based on machine learning to handle visual and audio features. MKL （Multiple Kernel Learning） is applied so that multimodality of videos can be maximized. The largest features of our system is that mid-level concepts clustering is proposed and implemented in order to learn mid-level concepts implicitly. By this algorithm, our system does not need manually tagged annotations. The whole system is trained on the dataset from MediaEval 2013 Affect Task and evaluated by its official metric. The obtained results outperformed its best score.
基金Supported by the National Basic Research 973 Program of China under Grant No. 2011CB302200-Gthe Key Program of National Natural Science Foundation of China under Grant No. 61033007+1 种基金the National Natural Science Foundation of China under Grant Nos.61100026, 60973019the Fundamental Research Funds for the Central Universities of China under Grant Nos. N110604003,N100704001, N100304004, N120404007
文摘Although many existing movie recommender systems have investigated recommendation based on information such as clicks and tags, much less efforts have been made to explore the multimedia content of movies, which has potential information for the elicitation of the user＇s visual and musical preferences. In this paper, we explore the content from three media types （image, text, audio） and propose a novel multi-view semi-supervised movie recommendation method, which represents each media type as a view space for movies. The three views of movies are integrated to predict the rating values under the multi-view framework. ~rthermore, our method considers the casual users who rate limited movies. The algorithm enriches the user profile with a semi-supervised way when there are only few rating histories. Experiments indicate that the multimedia content analysis reveals the user＇s profile in a more comprehensive way. Different media types can be a complement to each other for movie recommendation. And the experimental results validate that our semi-supervised method can effectively enrich the user profile for recommendation with limited rating history.
