Finding visually identical images in large image collections is important for many applications such as intelligence propriety protection and search result presentation. Several a...
Blocking artifact is the most prevailing degradation caused by block-based DCT coding techniques under low bit-rate conditions. To alleviate blockings perceptually, it is desirabl...
Artists in new media arts explore the possibilities offered by digital technologies to create adaptive and interactive new media artworks integrating audio and video. In this pape...
Text-based search using video speech transcripts is a popular approach for granular video retrieval at the shot or story level. However, misalignment of speech and visual tracks, ...
In this paper a new approach for face clustering is developed. Mutual information and joint entropy are exploited in order to create a metric for the clustering process. The way t...
Nicholas Vretos, Vassilios Solachidis, Ioannis Pit...
In this paper, a new implementation method is proposed for Context-Adaptive Variable Length Coding (CAVLC) used in H.264 Baseline Profile. We analyze the correlation between bit p...
This paper presents a novel fuzzy stochastic Kalman filter for compression of digital images. In particular, it is shown that the state evolution of the synthesis coefficients of ...
The wireless networks are notoriously error prone and all errors cannot be prevented in real-time communications. The problem of error correction becomes even more challenging in ...
Semantic scene classification is a useful, yet challenging problem in image understanding. Most existing systems are based on low-level features, such as color or texture, and suc...
Matthew R. Boutell, Anustup Choudhury, Jiebo Luo, ...
We present VideoPot, a desktop video search system designed for digital video files stored on personal computers. The core metric of this system is based on video-indexing techno...
Hidenobu Nagata, Dan Mikami, Shozo Azuma, Masashi ...