arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.12475cs.CV
收藏

帧顺序很重要:一种用于少样本动作识别的时间序列感知模型

Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition

Zhejiang University(浙江大学)

Bozheng Li, Mushui Liu, Gaoang Wang, Yunlong Yu

AI总结:

本文提出了一种用于少样本动作识别的时间序列感知模型TSAM,通过整合序列感知器适配器、大型语言模型文本语料库和不平衡最优传输策略,在五个数据集上以巨大优势刷新了基准。

摘要:

在本文中,我们提出了一种用于少样本动作识别(FSAR)的新型时间序列感知模型(TSAM),该模型将一个序列感知器适配器整合到预训练框架中,以将空间信息和连续的时间动态集成到特征嵌入中。与现有的通过探索所有帧之间的关系来捕获时间信息的微调方法不同,我们基于感知器的适配器沿着时间线循环地捕获连续动态,从而能够感知顺序的变化。为了获得每个类别的判别性表示,我们扩展了从大型语言模型(LLMs)导出的每个类别的文本语料库,并通过整合上下文语义信息来丰富视觉原型。此外,我们引入了一种不平衡最优传输策略用于特征匹配,以减轻与类别无关特征的影响,从而促进更有效的决策。在五个FSAR数据集上的实验结果表明,我们的方法设定了新的基准,以巨大优势击败了次优竞争者。

英文摘要:

In this paper, we propose a novel Temporal Sequence-Aware Model (TSAM) for few-shot action recognition (FSAR), which incorporates a sequential perceiver adapter into the pre-training framework, to integrate both the spatial information and the sequential temporal dynamics into the feature embeddings. Different from the existing fine-tuning approaches that capture temporal information by exploring the relationships among all the frames, our perceiver-based adapter recurrently captures the sequential dynamics alongside the timeline, which could perceive the order change. To obtain the discriminative representations for each class, we extend a textual corpus for each class derived from the large language models (LLMs) and enrich the visual prototypes by integrating the contextual semantic information. Besides, We introduce an unbalanced optimal transport strategy for feature matching that mitigates the impact of class-unrelated features, thereby facilitating more effective decision-making. Experimental results on five FSAR datasets demonstrate that our method set a new benchmark, beating the second-best competitors with large margins.

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。

↑