论文标题
您在哪里看？：一个大规模的头和凝视行为的大规模数据集，用于360度视频和试点研究
Where Are You Looking?: A Large-Scale Dataset of Head and Gaze Behavior for 360-Degree Videos and a Pilot Study
论文作者
论文摘要
近年来，360°视频经历了蓬勃发展的发展。与传统视频相比，360°视频具有不确定的用户行为，带来了机会和挑战。数据集对于研究人员和开发人员探索新想法并进行可再现的分析是必要的，以在不同解决方案之间进行公平比较。但是，现有相关数据集主要集中在用户的视野（FOV）上，忽略了更重要的眼目光信息，更不用说对FOV和Eye Caze的集成提取和分析。此外，用户的行为模式与视频高度相关，但是大多数现有数据集仅包含视频流派的主观和定性分类的视频，这些视频缺乏定量分析，并且无法表征视频场景的固有属性。为此，我们首先针对包含三个客观技术指标的360°视频提出了定量分类。基于此分类法，我们同时收集了一个包含用户头和凝视行为的数据集，该数据集的表现优于现有数据集，这些数据集具有丰富的尺寸，大规模，强大的多样性和高频。然后，我们对用户的行为进行了试点研究，并获得了一些有趣的发现，例如用户的头部方向将遵循他/她的凝视方向，并以最大的时间间隔。后来进行了基于数据集的基于瓷砖的360°视频流中的一个案例，通过利用我们提供的凝视信息来证明现有作品的绩效改善。我们的数据集可从https://cuhksz-inml.github.io/head_gaze_dataset/获得
360° videos in recent years have experienced booming development. Compared to traditional videos, 360° videos are featured with uncertain user behaviors, bringing opportunities as well as challenges. Datasets are necessary for researchers and developers to explore new ideas and conduct reproducible analyses for fair comparisons among different solutions. However, existing related datasets mostly focused on users' field of view (FoV), ignoring the more important eye gaze information, not to mention the integrated extraction and analysis of both FoV and eye gaze. Besides, users' behavior patterns are highly related to videos, yet most existing datasets only contained videos with subjective and qualitative classification from video genres, which lack quantitative analysis and fail to characterize the intrinsic properties of a video scene. To this end, we first propose a quantitative taxonomy for 360° videos that contains three objective technical metrics. Based on this taxonomy, we collect a dataset containing users' head and gaze behaviors simultaneously, which outperforms existing datasets with rich dimensions, large scale, strong diversity, and high frequency. Then we conduct a pilot study on user's behaviors and get some interesting findings such as user's head direction will follow his/her gaze direction with the most possible time interval. A case of application in tile-based 360° video streaming based on our dataset is later conducted, demonstrating a great performance improvement of existing works by leveraging our provided gaze information. Our dataset is available at https://cuhksz-inml.github.io/head_gaze_dataset/
