论文信息 - Visual-based transmedia events detection

Visual-based transmedia events detection

This paper presents a visual-based media event detection system based on the automatic discovery of the most circulated images across the main news media (news websites, press agencies, TV news and newspapers). Its main originality is to rely on the transmedia contextual information to denoise the raw visual detections and consequently focus on the most salient transmedia events.

[1] S. Dongen. A cluster algorithm for graphs , 2000 .

[2] Olivier Buisson,et al. Logo retrieval with a contrario visual query expansion , 2009, ACM Multimedia.

[3] Olivier Buisson,et al. A posteriori multi-probe locality sensitive hashing , 2008, ACM Multimedia.

[4] Olivier Buisson,et al. Content-Based Copy Retrieval Using Distortion-Based Probabilistic Similarity Search , 2007, IEEE Transactions on Multimedia.

[5] Olivier Buisson,et al. Random maximum margin hashing , 2011, CVPR 2011.

[6] Michael Isard,et al. Lost in quantization: Improving particular object retrieval in large scale image databases , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.