Towards Auto-Documentary: Tracking the Evolution of News Stories
Download:
unknown authors
http://www.cs.bilkent.edu.tr/%7Eduygulu/papers/MM2004.pdf
Add To MetaCart
Abstract:
News videos constitute an important source of information for tracking and documenting important events. In these videos, news stories are often accompanied by short video shots that tend to be repeated during the course of the event. Automatic detection of such repetitions is essential for creating auto-documentaries, for alleviating the limitation of traditional textual topic detection methods. In this paper, we propose novel methods for detecting and tracking the evolution of news over time. The proposed method exploits both visual cues and textual information to summarize evolving news stories. Experiments are carried on the TREC-VID data set consisting of 120 hours of news videos from two different channels.
Citations
| 117 | Co-Clustering Documents and Words Using Bipartite Spectral Graph Partitioning – Dhillon - 2001 |
| 42 | On the detection and recognition of television commercials – Lienhart, Kuhmunch, et al. - 1997 |
| 12 | Story Segmentation and Detection of Commercials – Hauptmann, Witbrock - 1998 |
| 10 | Discovering recurrent events in video using unsupervised methods – Naphade, Huang - 2002 |
| 8 | Object Detection Using the Statistics – Schneiderman, Kanade - 2002 |
| 3 | Identical Video Segment Detection for Large-Scale Broadcast Video – Yamagishi, Satoh, et al. |
| 2 | Evolvable visual commercial detector”, CVPR – Agnihotri, Dimitrova, et al. - 2003 |
