It is well known that incremental learning can often be difficult for traditional neural network systems, due to newly learned information interfering with previously learned infor...
Scoring sentences in documents given abstract summaries created by humans is important in extractive multi-document summarization. In this paper, we formulate extractive summariza...
The paper shows the outlines of the SLAM system and how its design is suitable for automating rapid prototyping. The system includes a very expressive object oriented specificati...
In this paper, we present a new incremental learning strategy for handwritten character recognition systems. This learning strategy enables the recognition system to learn “rapi...
This paper proposes a motion-focusing method to extract key frames and generate summarization synchronously for surveillance videos. Within each pre-segmented video shot, the prop...