计算机科学
骨架(计算机编程)
代表(政治)
弹丸
人工智能
动作识别
模式识别(心理学)
关系数据库
自然语言处理
人机交互
情报检索
班级(哲学)
程序设计语言
有机化学
法学
化学
政治
政治学
作者
Jingyun Tian,Jinjing Gu,Yuanyuan Pu,Zhengpeng Zhao
标识
DOI:10.1109/tmm.2024.3521767
摘要
Few-shot action recognition aims to identify new action classes with limited training samples. Most existing methods overlook the low information content and diversity of skeleton features, failing to exploit useful information in rare samples during meta-training. This leads to poor feature discriminability and recognition accuracy. To address both issues, we propose a novel Enriched Skeleton Representation and Multi-relational Metrics (ESR-MM) method for skeleton-based few-shot action recognition. First, a Frobenius Norm Diversity Loss is introduced to enrich skeleton representation by maximizing the Frobenius norm of the skeleton feature matrix. This mitigates over-smoothing and boosts information content and diversity. Leveraging these enriched features, we propose a multi-relational metrics strategy exploiting cross-sample task-specific information, intra-sample temporal order, and inter-sample distance. Specifically, Support-Adaptive Attention leverages task-specific cues between samples to generate attention-enhanced features. Then, the Bidirectional Temporal Coherent Mean Hausdorff Metric integrates Temporal Coherence Measure into the Bidirectional Mean Hausdorff Metric for class separation by accounting for temporal order. Finally, Prototype-discriminative Contrastive Loss exploits distances from class prototypes to query samples. ESR-MM demonstrates superior performance on two benchmarks.
科研通智能强力驱动
Strongly Powered by AbleSci AI