Use Of Low-level Visual Features Research Articles

Influence of visual background complexity and task difficulty on action video game players’ performance

The purpose of this study was to investigate the influence of visual background complexity and task difficulty on players’ performance in a typical video game task, as a function of their expertise. Challenge in a video game is usually defined by the difficulty level of the main task. The use of low-level visual features of game interfaces to modulate the challenge has only been evaluated by a few studies. Two experiments were designed in which action video game players (AVGPs) and non-players of action video games (NVGPs) were engaged in a target-shooting task. The difficulty level of task as well as the complexity of visual background were manipulated. The enhanced attentional abilities of AVGPs allowed them to perform the task better than NVGPs. Both task difficulty and background complexity impaired task performance. However, this impairment was not modulated by player expertise. Recommendations are proposed to game designers to design the challenge around the low-level visual features of game interfaces.

Sketch-Based 3D Model Retrieval Using Attributes

With the rapid growth of available 3D models on the Internet, how to retrieve 3D models based on hand-drawn sketch retrieval are becoming increasingly important. This article proposes a new sketch-based 3D model retrieval approach. This approach is different from current methods that make use of low-level visual features to capture the search intention of users. The proposed method uses two kinds of semantic attributes, including pre-defined attributes and latent attributes. Specifically, pre-defined attributes are defined manually which can provide prior knowledge about different sketch categories and latent-attributes are more discriminative which can differentiate sketch categories at a finer level. Therefore, these semantic attributes can provide a more descriptive and discriminative meaningful representation than low-level feature descriptors. The experiment results demonstrate that this proposed method can achieve superior performance over previously proposed sketch-based 3D model retrieval methods.