论文信息 - CMU Informedia's TRECVID 2005 Skirmishes

CMU Informedia's TRECVID 2005 Skirmishes

Runid: Bashful: probabilistic camera motion with conservative threshold 1 for high precision Runid: Doc: probabilistic camera motion with conservative threshold 2 for high precision Runid: Dopey: probabilistic camera motion with relaxed constraints (threshold 1) for high recall Runid: Grumpy: probabilistic camera motion with relaxed constraints (threshold 2) for high recall Runid: Happy: optical flow with weighting 1 Runid: Sleepy: optical flow with weighting 2 Runid: Sneezy: a more sensitive algorithm based on optical flow in order to improve recall

[1] Robert Spence,et al. Rapid, Serial and Visual: A Presentation Technique with Potential , 2002, Inf. Vis..

[2] Sara Shatford. Describing a Picture: A Thousand Words are Seldom Cost Effective , 1984 .

[3] Milind R. Naphade,et al. A probabilistic framework for semantic video indexing, filtering, and retrieval , 2001, IEEE Trans. Multim..

[4] Robert T. Collins,et al. Articulated Motion Modeling for Activity Analysis , 2004, CVPR 2004.

[5] Marcel Worring,et al. The MediaMill TRECVID 2004 Semantic Viedo Search Engine , 2004, TRECVID.

[6] Mark Derthick. Interfaces for palmtop image search , 2002, JCDL '02.

[7] Andrew McCallum,et al. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[8] Wei-Hao Lin,et al. Confounded Expectations: Informedia at TRECVID 2004 , 2004, TRECVID.

[9] Michael G. Christel,et al. Finding the right shots: assessing usability and performance of a digital video library interface , 2004, MULTIMEDIA '04.

[10] Michael G. Christel,et al. Addressing the challenge of visual information access from digital image and video libraries , 2005, Proceedings of the 5th ACM/IEEE-CS Joint Conference on Digital Libraries (JCDL '05).