ISO/IEC 14496-2:2004提供了与视觉信息编码表示相关的以下元素: -视频编码工具、对象类型和配置文件的规范，包括对基于矩形和任意形状的视频对象进行编码的能力、定义可伸缩比特流的能力和容错编码工具； -用于将静态纹理映射到视觉场景的编码工具、对象类型和配置文件的规范； -基于人脸/身体模型和附加语义参数的人脸和身体动画编码工具、对象类型和配置文件规范；和 -具有均匀和不规则拓扑的二维扭曲网格动画的编码工具、对象类型和轮廓规范。 可视化规范包含比特流语法、比特流语义和相关解码过程的定义。 它没有指定编码器，可以在不同的实现中进行优化。

ISO/IEC 14496-2:2004 provides the following elements related to the encoded representation of visual information: - Specification of video coding tools, object types and profiles, including capability to encode rectangular-based and arbitrary-shaped video objects, capability to define scalable bitstreams and error-resilient encoding tools; - Specification of coding tools, object types and profiles for mapping of still textures into visual scenes; - Specification of coding tools, object types and profiles for human face and body animation based on face/body models and additional semantic parameters; and - Specification of coding tools, object types and profiles for animation of 2D warping grids with uniform and irregular topology. The Visual specification contains definitions of the bitstream syntax, bitstream semantics and the related decoding process. It does not specify the encoders, which can be optimized in different implementations.