This paper study temporal curve patterns associated with BBS information and how the information’s popularity grows and fades over time. We develop the Temporal-Peak clustering algorithm that accurately finds the curve pattern in BBS. According to the characteristics of BBS platform and applying sudden and durative describes temporal variation curve of information. The article demonstrates our ...

Abstract. In this paper, we investigate order-preserving sparse coding for classifying multi-dimensional sequence data. Such a problem is often tackled by first decomposing the input sequence into individual frames and extracting features, then performing sparse coding or other processing for each frame based feature vector independently, and finally aggregating individual responses to classify...

As a fine-grained video understanding task, dense video captioning involves first localizing events in a video and then generating captions for the identified events. We present the Joint Event Detection and Description Network (JEDDi-Net) that solves the dense captioning task in an end-to-end fashion. Our model continuously encodes the input video stream with three-dimensional convolutional la...

The real transactional databases often exhibit temporal characteristic and time varying behavior. Temporal association rule has thus become an active area of research.A calendar unit such as months and days, clock units such as hours and seconds and specialized units such as business days and academic years, play a major role in a wide range of information system applications. The calendar-base...

This paper presents a model of the temporal structure of repeating events. This model allows for the representation of quantitative temporal constraints for repeating events, viz., those dealing with their part-whole structure. The temporal structure of repeating events is viewed as being composed of ve properties: number, sub-interval duration, gap duration, period and extent. A set of constra...

This paper describes a model for temporal reasoning that handles both quantitative and qualitative information affected by vagueness and uncertainty. Starting from two existing models, namely the Meiri’s system [9] and IA fuz [2, 3], the proposed approach generalizes the first to a fuzzy framework and extends the second in order to handle qualitative constraints. The system uses the Fuzzy Const...

Temporal coordination of services, as a crucial aspect of integration in public transport systems, has always been a big concern for transit planners and schedulers. One of the major issues in the way of coordinating transit services is the lack of a robust measure of effectiveness for assessing the quality of temporal coordination in public transport systems. Even though the network-wide summa...

We show quantitative evidence that a full relational model of the body performs better at upper body parsing than the standard tree model, despite the need to adopt approximate inference and learning procedures. Our method uses an approximate search for inference, and an approximate structure learning method to learn. We compare our method to state of the art methods on our dataset (which depic...

English. We describe an experiment designed to measure the lexical coverage of some resources over the Italian cooking recipes genre. First, we have built a small cooking recipe dataset; second, we have done a qualitative morpho-syntactic analysis of the dataset and third we have done a quantitative analysis of the lexical coverage of the dataset. Italian. Descriviamo un esperimento per valutar...