UCF 运动行为视频数据集

UCF Sports dataset consists of a set of actions collected from various sports which are typically featured on broadcast television channels such as the BBC and ESPN. The video sequences were obtained from a wide range of stock footage websites including BBC Motion gallery and GettyImages. The dataset includes a total of 150 sequences with the resolution of 720 x 480. The collection represents a natural pool of actions featured in a wide range of scenes and viewpoints. By releasing the data set we hope to encourage further research into this class of action recognition in unconstrained environments. Since its introduction, the dataset has been used for numerous applications such as: action recognition, action localization, and saliency detection. The dataset includes the following 10 actions. The figure above shows the a sample frame of all ten actions, along with their bounding box annotations of the humans shown in yellow. Diving (14 videos) Golf Swing (18 videos) Kicking (20 videos) Lifting (6 videos) Riding Horse (12 videos) Running (13 videos) SkateBoarding (12 videos) Swing-Bench (20 videos) Swing-Side (13 videos) Walking (22 videos) The following table summarizes the characteristics of the dataset. Figure: Summary of the characteristics of UCF Sports. The following figure shows the distribution of the number of clips per action as the number of clips in each class is not the same. Figure: Number of clips per action class. The following figure illustrates the total duration of clips (blue) and the average clip length (green) for every action class. It is evident that certain actions are short in nature, such as kicking, as compared to walking or running, which are relatively longer and have more periodicity. However, it is apparent from the chart that the average duration of action clips shows great similarities across different classes. Therefore, merely considering the duration of one clip would not be enough for identifying the action. Figure: The total time of video clips for each action class is shown in blue. Average length of clips for each action is shown in green. The data set can be downloaded by clicking here. Human gaze annotations can be downloaded by clicking here. Train/Test splits for Action localization can be downloaded by clicking here. If you use this data set, please cite the following papers:

UCF Sports数据集由从BBC、ESPN等主流广播电视频道常播出的各类体育赛事动作中采集得到。其视频序列来源于BBC Motion图库、GettyImages等多家商用素材网站。该数据集共包含150段视频序列，分辨率为720×480，涵盖了多样化场景与拍摄视角下的各类自然体育动作。
本数据集的发布旨在推动无约束环境下动作识别领域的相关研究。自发布以来，该数据集已被广泛应用于动作识别、动作定位、显著性检测等诸多研究任务中。
该数据集包含以下10类动作：跳水（14段视频）、高尔夫挥杆（18段视频）、踢击（20段视频）、举重（6段视频）、骑马（12段视频）、跑步（13段视频）、滑板运动（12段视频）、秋千摆（20段视频）、侧摆（13段视频）与行走（22段视频）。上方图示展示了全部10类动作的单帧样本，以及对应人体的黄色边界框（bounding box）标注。
下表汇总了该数据集的各项特征：
图1：UCF Sports数据集特征汇总
下一张图示展示了各动作类别的视频片段数量分布——由于不同类别间的片段数存在差异：
图2：各动作类别的视频片段数量分布
下一张图示展示了各类动作的总片段时长（蓝色柱）与平均片段时长（绿色柱）。不难发现，踢击等动作本身时长较短，而跑步、行走等动作则相对更长且更具周期性。但从图表中可明显看出，不同动作类别的平均片段时长差异极小。因此，仅依靠单段视频的时长不足以完成动作识别任务。
图3：各动作类别的视频总时长以蓝色柱展示，平均片段时长以绿色柱展示。
可点击此处下载该数据集。可点击此处下载人体注视点标注数据。可点击此处下载动作定位任务所需的训练/测试划分集。若您在研究中使用该数据集，请引用以下文献：

搜集汇总

背景与挑战

背景概述

UCF运动行为视频数据集包含150个分辨率为720x480的视频序列，涵盖10种运动行为，适用于动作识别和定位研究。数据集来自广播电视台的素材，支持无约束环境下的动作分析。