arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.11721cs.CV
收藏

基于语言对象约束的暹罗跟踪

Siamese Tracking with Lingual Object Constraints

University of Amsterdam(阿姆斯特丹大学)

Maximilian Filtenborg, Efstratios Gavves, Deepak Gupta

摘要:

传统上,视觉对象跟踪涉及在给定视频中跟踪目标对象,并且它为我们提供对象的运动轨迹。然而,对于许多实际应用,这种输出通常是不够的,因为需要额外的语义信息来作用于视频材料。其示例应用是监视和特定于目标的视频摘要,其中需要相对于某些预定义的约束来监视目标,例如,“当你站在一辆黄色的车旁边”本文探讨,跟踪视觉对象受到额外的语言约束。继Li等人之后,我们对跟踪施加了额外的语言约束,这使得能够实现跟踪的新应用。而在他们的工作中,目标是改进和扩展跟踪本身。为了进行基准测试和实验,我们贡献了两个数据集:c-MOT 16和c-LaSOT,通过向原始LaSOT和MOT 16数据集的框架添加额外的约束来进行管理。我们还对两个深度模型SiamCT-DFG和SiamCT-CA进行了实验,这两个模型是通过扩展最近最先进的暹罗跟踪方法并添加受自然语言处理和视觉问答领域启发的模块而获得的。通过实验结果表明,所提出的模型SiamCT-CA的性能明显优于同类模型。此外,我们的方法使视频的选择性压缩,基于约束的有效性。

英文摘要:

Classically, visual object tracking involves following a target object throughout a given video, and it provides us the motion trajectory of the object. However, for many practical applications, this output is often insufficient since additional semantic information is required to act on the video material. Example applications of this are surveillance and target-specific video summarization, where the target needs to be monitored with respect to certain predefined constraints, e.g., 'when standing near a yellow car'. This paper explores, tracking visual objects subjected to additional lingual constraints. Differently from Li et al., we impose additional lingual constraints upon tracking, which enables new applications of tracking. Whereas in their work the goal is to improve and extend upon tracking itself. To perform benchmarks and experiments, we contribute two datasets: c-MOT16 and c-LaSOT, curated through appending additional constraints to the frames of the original LaSOT and MOT16 datasets. We also experiment with two deep models SiamCT-DFG and SiamCT-CA, obtained through extending a recent state-of-the-art Siamese tracking method and adding modules inspired from the fields of natural language processing and visual question answering. Through experimental results, we show that the proposed model SiamCT-CA can significantly outperform its counterparts. Furthermore, our method enables the selective compression of videos, based on the validity of the constraint.

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。

↑