The increasing variety and quantity of tagged multimedia content on platforms such as TikTok provides an opportunity to advance computer vision modeling. We have curated a distinctive dataset of 283,582 unique video clips categorized under 386 hashtags relating to modern human actions. We release this dataset as a valuable resource for building domain-specific foundation models for human movement modeling tasks such as action recognition. To validate this dataset, which we name TikTokActions, we perform two sets of experiments. First, we pretrain the state-of-the-art VideoMAEv2 with a ViT-base backbone on TikTokActions subset, and then fine-tune and evaluate on popular datasets such as UCF101 and the HMDB51. We find that the performance of the model pre-trained using our Tik-Tok dataset is comparable to models trained on larger action recognition datasets (95.3% on UCF101 and 53.24% on HMDB51). Furthermore, our investigation into the relationship between pre-training dataset size and fine-tuning performance reveals that beyond a certain threshold, the incremental benefit of larger training sets diminishes. This work introduces a useful TikTok video dataset that is available for public use and provides insights into the marginal benefit of increasing pre-training dataset sizes for video-based foundation models.

翻译：TikTok等平台上带标签的多媒体内容种类与数量日益增长，为推进计算机视觉建模提供了机遇。我们整理了一个包含283,582个独特视频片段的数据集，这些片段涵盖386个与现代人类动作相关的主题标签。我们将该数据集作为构建动作识别等人类运动建模任务的领域特定基础模型的宝贵资源公开。为验证该数据集（命名为TikTokActions），我们开展了两组实验。首先，我们在TikTokActions子集上对基于ViT-base骨干网络的当前最优模型VideoMAEv2进行预训练，随后在UCF101和HMDB51等主流数据集上进行微调与评估。结果表明，使用我们TikTok数据集预训练的模型性能可与在更大动作识别数据集上训练的模型相媲美（在UCF101上达95.3%，在HMDB51上达53.24%）。此外，我们对预训练数据集规模与微调性能之间关系的探究显示，超过特定阈值后，更大训练集带来的边际效益逐渐递减。本工作引入了一个可供公开使用的有用TikTok视频数据集，并为视频基础模型增加预训练数据集规模的边际效益提供了见解。