THUMOS14

Automatically recognizing and localizing a large number of action categories from videos in the wild of significant importance for video understanding and multimedia event detection. THUMOS workshop and challenge aims at exploring new challenges and approaches for large-scale action recognition with large number of classes from open source videos in a realistic setting. Most of the existing action recognition datasets are composed of videos that have been manually trimmed to bound the action of interest. This has been identified to be a considerable limitation as it poorly matches how action recognition is applied in practical settings. Therefore, THUMOS 2014 will conduct the challenge on temporally untrimmed videos. The participants may train their methods using trimmed clips but will be required to test their systems on untrimmed data. It includes 1,010 videos and 1,574 videos with 20 action classes in the validation and test sets, respectively. There are 200 and 212 videos with temporal annotations of actions labeled in the validation and testing sets, respectively. A new forward-looking dataset containing over 254 hours of video data and 25 million frames with the following components is made available under this challenge: All videos are collected from YouTube, and their pre-extracted low-level features (Improved Dense Trajectory Features) are made available. The entries to the challenge will be evaluated using the new THUMOS 2014 Dataset in two tasks: For more details, please see the Evaluation Setup document or the released resources.

自动识别并定位真实野外场景视频中的大量动作类别，对于视频理解与多媒体事件检测具有至关重要的意义。THUMOS研讨会与挑战赛旨在针对现实场景下源自开源视频的大规模多类别动作识别任务，探索全新的挑战与解决方案。当前绝大多数现有动作识别数据集均由经人工裁剪以框定目标动作的视频构成，这一局限已被证实十分显著——因其与实际场景中动作识别的应用方式严重不符。因此，THUMOS 2014挑战赛将采用未进行时间裁剪的视频开展赛事。参赛选手可使用裁剪后的视频片段训练模型，但需在未裁剪的数据集上测试其系统性能。该挑战赛的验证集与测试集分别包含1010段、1574段视频，涵盖20个动作类别。其中，验证集与测试集中分别有200段、212段视频带有动作时间标注。本次挑战赛还推出了一项兼具前瞻性的全新数据集，包含超过254小时的视频数据与2500万帧图像，其组成如下：所有视频均采集自YouTube，且已预先提取了底层视觉特征（改进稠密轨迹特征，Improved Dense Trajectory Features）。本次挑战赛的参赛作品将基于THUMOS 2014新数据集在两项任务中进行评估。如需了解更多细节，请参阅《评估设置》文档或已发布的相关资源。

搜集汇总

背景与挑战

背景概述

THUMOS14是一个专注于视频动作识别和时序动作检测的数据集，包含超过254小时的YouTube视频和25百万帧，分为训练集、验证集、背景集和测试集。该数据集特别挑战在未修剪视频上进行动作识别，包含101个动作类别的识别任务和20个动作类别的时序检测任务。