arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1802.06459cs.CV
收藏

用于视觉理解的结构化标签推理

Structured Label Inference for Visual Understanding

Nelson Nauata, Hexiang Hu, Guang-Tong Zhou, Zhiwei Deng, Zicheng Liao, Greg Mori

摘要:

图像和视频等视觉数据包含丰富的结构化语义标签源以及广泛的交互组件。视觉内容可以被分配有描述主要组件的细粒度标签、描述高级抽象的粗粒度标签或揭示属性的一组标签。这种分类在不同的,相互作用的标签层显示了潜在的基于图形的编码的标签信息。在本文中,我们利用这种丰富的结构,在标签空间中执行基于图的推理,用于许多任务:多标签图像和视频分类以及未修剪视频中的动作检测。我们考虑使用双向推理神经网络(BINN)和结构化推理神经网络(SINN)在标签空间中执行基于图的推理,并提出了一种基于长短期记忆(LSTM)的扩展,用于利用未修剪视频上的活动进展。这些方法在以下数据集上进行了评估:(i)用于多标签图像分类的动物属性(AwA),场景理解(SUN)和NUS-WIDE数据集,(ii)用于多标签视频分类的YouTube-8 M大规模数据集的前两个版本,以及(iii)用于动作检测的THUMOS'14和MultiTHUMOS视频数据集。我们的研究结果证明了结构化标签推理在这些具有挑战性的任务中的有效性,实现了对基线的显着改进。

英文摘要:

Visual data such as images and videos contain a rich source of structured semantic labels as well as a wide range of interacting components. Visual content could be assigned with fine-grained labels describing major components, coarse-grained labels depicting high level abstractions, or a set of labels revealing attributes. Such categorization over different, interacting layers of labels evinces the potential for a graph-based encoding of label information. In this paper, we exploit this rich structure for performing graph-based inference in label space for a number of tasks: multi-label image and video classification and action detection in untrimmed videos. We consider the use of the Bidirectional Inference Neural Network (BINN) and Structured Inference Neural Network (SINN) for performing graph-based inference in label space and propose a Long Short-Term Memory (LSTM) based extension for exploiting activity progression on untrimmed videos. The methods were evaluated on (i) the Animal with Attributes (AwA), Scene Understanding (SUN) and NUS-WIDE datasets for multi-label image classification, (ii) the first two releases of the YouTube-8M large scale dataset for multi-label video classification, and (iii) the THUMOS'14 and MultiTHUMOS video datasets for action detection. Our results demonstrate the effectiveness of structured label inference in these challenging tasks, achieving significant improvements against baselines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑