Search results

The purpose of this paper is to examine an auto‐assembled multimedia presentation from digital libraries, in which the retrieved media objects are dynamically composed to form a continuously played “TV‐like” presentation. This study seeks to propose techniques for ordering the media objects in such a presentation so as to reduce its total presentation lag in a high‐delay network environment.

Scheduling techniques adapted from conventional operational research for solving the proposed problem were applied. A number of computationally efficient heuristic algorithms that can obtain near‐optimal sequences are proposed. Numerical simulations and real‐life experiments for cases with different buffer constraints and bandwidth fluctuations were conducted to evaluate the proposed algorithms.

The result indicates that the proposed algorithms always significantly reduce the presentation lag of a given presentation, compared with a random sequence. Overall, for all the test cases, the average gaps between the idle rates of the heuristic sequences and random sequences range from 15 to 25 per cent. In particular, the RRB_3_2007 algorithm outperforms others in most of the cases involved in the experiment.

The study develops a sequence optimization technique for ordering the media objects and a framework for a prefetch‐enabled presentation system. The effectiveness and ease of implementation of the heuristic algorithms and the system framework make it feasible for practical digital library and meta‐search engine applications.

The purpose of this paper is to show how previous studies have demonstrated that non‐professional users prefer using event‐based conceptual descriptions, such as “a woman wearing a hat”, to describe and search images. In many art image archives, these conceptual descriptions are manually annotated in free‐text fields. This study aims to explore technologies to automate event‐based knowledge extractions from these free‐text image descriptions.

This study presents an approach based on semantic role labeling technologies for automatically extracting event‐based knowledge, including subject, verb, object, location and temporal information from free‐text image descriptions. A query expansion module is applied to further improve the retrieval recall. The effectiveness of the proposed approach is evaluated by measuring the retrieval precision and recall capabilities for experiments with real life art image collections in museums.

Evaluations results indicate that the proposed method can achieve a substantially higher retrieval precision than conventional keyword‐based approaches. The proposed methodology is highly applicable for large‐scale collections where the image retrieval precision is more critical than the recall.

The study provides the first attempt in literature for automating the extraction of event‐based knowledge from free‐text image descriptions. The effectiveness and ease of implementation of the proposed approach make it feasible for practical applications.