arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.09220cs.CVcs.AI
收藏

Flatten:视频动作识别是一项图像分类任务

Flatten: Video Action Recognition is an Image Classification task

Capital Normal University(首都师范大学)

Junlin Chen, Chengcheng Xu, Yangfan Xu, Jian Yang, Jun Li, Zhiping Shi

AI总结:

该研究提出即插即用的视频表示架构Flatten,通过展平操作将三维时空视频数据转为二维空间信息,使普通图像分类模型可直接完成视频动作识别,在多个常用数据集和经典图像模型上验证了性能提升效果。

摘要:

近年来,视频动作识别作为视频理解领域的一项基础任务,已被众多研究者深入探索。大多数传统视频动作识别方法通常会将视频转换为包含时空信息的三维数据,随后利用主流图像理解模型对这些数据进行建模与分析。但这类方法存在显著缺陷:首先,在开展视频动作识别任务时,图像理解模型往往需要针对这些时空任务在模型架构和预处理方面做出相应调整;其次,与低维数据相比,处理高维数据通常面临更大挑战,且会产生更高的时间成本。为弥合图像理解与视频理解任务之间的差距,同时降低视频理解的复杂度,我们提出了一种新型视频表示架构Flatten,它是一个即插即用模块,可无缝集成到任意图像理解网络中,实现高效且高性能的三维时序数据建模。具体而言,通过应用特定的展平操作(例如行优先变换),三维时空数据被转换为二维空间信息,随后利用普通图像理解模型捕捉时序动态与空间语义信息,进而完成高效且准确的视频动作识别。我们在常用数据集(Kinetics-400、Something-Something v2和HMDB-51)以及三个经典图像分类模型(Uniformer、SwinV2和ResNet)上开展了大量实验,结果表明,嵌入Flatten模块后的模型相比原始模型性能有显著提升。

英文摘要:

In recent years, video action recognition, as a fundamental task in the field of video understanding, has been deeply explored by numerous researchers.Most traditional video action recognition methods typically involve converting videos into three-dimensional data that encapsulates both spatial and temporal information, subsequently leveraging prevalent image understanding models to model and analyze these data. However,these methods have significant drawbacks. Firstly, when delving into video action recognition tasks, image understanding models often need to be adapted accordingly in terms of model architecture and preprocessing for these spatiotemporal tasks; Secondly, dealing with high-dimensional data often poses greater challenges and incurs higher time costs compared to its lower-dimensional counterparts.To bridge the gap between image-understanding and video-understanding tasks while simplifying the complexity of video comprehension, we introduce a novel video representation architecture, Flatten, which serves as a plug-and-play module that can be seamlessly integrated into any image-understanding network for efficient and effective 3D temporal data modeling.Specifically, by applying specific flattening operations (e.g., row-major transform), 3D spatiotemporal data is transformed into 2D spatial information, and then ordinary image understanding models are used to capture temporal dynamic and spatial semantic information, which in turn accomplishes effective and efficient video action recognition. Extensive experiments on commonly used datasets (Kinetics-400, Something-Something v2, and HMDB-51) and three classical image classification models (Uniformer, SwinV2, and ResNet), have demonstrated that embedding Flatten provides a significant performance improvements over original model.

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。

↑