RefAtomNet++: 意味検索に基づくマルチトラジェクトリMambaによる参照的原子ビデオ行動認識の高度化
RefAtomNet++: Advancing Referring Atomic Video Action Recognition using Semantic Retrieval based Multi-Trajectory Mamba
自然言語で指定された人物の細粒度行動を認識するタスク(RAVAR)に対し、部分キーワード・シーン属性・文全体の3階層で意味を揃えたクロスアテンションとマルチトラジェクトリMambaを組み合わせたRefAtomNet++を提案し、大規模データセットRefAVA++で評価した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Kunyu Peng, Di Wen, Jia Fu, Jiamin Wu, Kailun Yang, Junwei Zheng, Ruiping Liu, Yufan Chen, Yuqian Fu, Danda Pani Paudel, Luc Van Gool, Rainer Stiefelhagen
分類: cs.CV, cs.MM, cs.RO, eess.IV
原文アブストラクト
Referring Atomic Video Action Recognition (RAVAR) aims to recognize fine-grained, atomic-level actions of a specific person of interest conditioned on natural language descriptions. Distinct from conventional action recognition and detection tasks, RAVAR emphasizes precise language-guided action understanding, which is particularly critical for interactive human action analysis in complex multi-person scenarios. In this work, we extend our previously introduced RefAVA dataset to RefAVA++, which comprises >2.9 million frames and >75.1k annotated persons in total. We benchmark this dataset using baselines from multiple related domains, including atomic action localization, video question answering, and text-video retrieval, as well as our earlier model, RefAtomNet. Although RefAtomNet surpasses other baselines by incorporating agent attention to highlight salient features, its ability to align and retrieve cross-modal information remains limited, leading to suboptimal performance in localizing the target person and predicting fine-grained actions. To overcome the aforementioned limitations, we introduce RefAtomNet++, a novel framework that advances cross-modal token aggregation through a multi-hierarchical semantic-aligned cross-attention mechanism combined with multi-trajectory Mamba modeling at the partial-keyword, scene-attribute, and holistic-sentence levels. In particular, scanning trajectories are constructed by dynamically selecting the nearest visual spatial tokens at each timestep for both partial-keyword and scene-attribute levels. Moreover, we design a multi-hierarchical semantic-aligned cross-attention strategy, enabling more effective aggregation of spatial and temporal tokens across different semantic hierarchies. Experiments show that RefAtomNet++ establishes new state-of-the-art results. The dataset and code are released at https://github.com/KPeng9510/refAVA2.
