Search results

Micro-video platforms have gained attention in recent years and have also become an important new channel for merchants to advertise their products. Since little research has studied micro-video advertising, this paper aims to fill the research gap by exploring the determinants of micro-video advertising clicks. We form a micro-video advertising click prediction model and demonstrate the effectiveness of the multimodal information extracted from the advertisement producers, commodities being sold and micro-video contents in the prediction task.

A multimodal analysis framework was conducted based on real-world micro-video advertisement datasets. To better capture the relations between different modalities, we adopt a cooperative learning model to predict the advertising clicks.

The experimental results show that the features extracted from different data sources can improve the prediction performance. Furthermore, the combination of different modal features (visual, acoustic, textual and numerical) is also worth studying. Compared to classical baseline models, the proposed cooperative learning model significantly outperforms the prediction results, which demonstrates that the relations between modalities are also important in advertising micro-video generation.

To the best of our knowledge, this is the first study analysing micro-video advertising effects. With the help of our advertising click prediction model, advertisement producers (merchants or their partners) can benefit from generating more effective micro-video advertisements. Furthermore, micro-video platforms can apply our prediction results to optimise their advertisement allocation algorithm and better manage network traffic. This research can be of great help for more effective development of the micro-video advertisement industry.

The objective of this paper is to quantitatively assess shear band evolution by using two-dimensional discrete element method (DEM).

The DEM model was first calibrated by retrospectively modelling existing triaxial tests. A series of DEM analyses was then conducted with the focus on the particle rotation during loading. An approach based on particle rotation was developed to precisely identify the shear band region from the surrounding. In this approach, a threshold rotation angle ω₀ was defined to distinguish the potential particles inside and outside the shear band and an index g(ω₀) was introduced to assess the discrepancy between the rotation response inside and outside shear band. The most distinct shear band region can be determined by the ω₀ corresponding to the peak g(ω₀). By using the proposed approach, the shear band development of two computational cases with different typical localised failure patterns were successfully examined by quantitatively measuring the inclination angle and thickness of shear band, as well as the microscopic quantities.

The results show that the shear band formation is stress-dependent, transiting from conjugated double shear bands to single shear band with confining stress increasing. The shear band evolution of two typical localised failure modes exhibits opposite trends with increasing strain level, both in inclination angle and thickness. Shear band featured a larger volumetric dilatancy and a lower coordination number than the surrounding. The shear band also significantly disturbs the induced anisotropy of soil.

This paper proposed an approach to quantitatively assess shear band evolution based on the result of two-dimensional DEM modelling.