Decompose and Transfer: CoT-Prompting Enhanced Alignment for Open-Vocabulary Temporal Action Detection
About
Open-Vocabulary Temporal Action Detection (OV-TAD) aims to classify and localize action segments in untrimmed videos for unseen categories. Previous methods rely solely on global alignment between label-level semantics and visual features, which is insufficient to transfer temporal consistent visual knowledge from seen to unseen classes. To address this, we propose a Phase-wise Decomposition and Alignment (PDA) framework, which enables fine-grained action pattern learning for effective prior knowledge transfer. Specifically, we first introduce the CoT-Prompting Semantic Decomposition (CSD) module, which leverages the chain-of-thought (CoT) reasoning ability of large language models to automatically decompose action labels into coherent phase-level descriptions, emulating human cognitive processes. Then, Text-infused Foreground Filtering (TIF) module is introduced to adaptively filter action-relevant segments for each phase leveraging phase-wise semantic cues, producing semantically aligned visual representations. Furthermore, we propose the Adaptive Phase-wise Alignment (APA) module to perform phase-level visual-textual matching, and adaptively aggregates alignment results across phases for final prediction. This adaptive phase-wise alignment facilitates the capture of transferable action patterns and significantly enhances generalization to unseen actions. Extensive experiments on two OV-TAD benchmarks demonstrated the superiority of the proposed method.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Temporal Action Detection | THUMOS 50% Seen / 50% Unseen 14 | mAP@0.365.4 | 11 | |
| Temporal Action Detection | ActivityNet v1.3 (50% Seen 50% Unseen) | mAP@0.5053.1 | 11 | |
| Temporal Action Detection | THUMOS 75% Seen / 25% Unseen 14 | mAP@0.370.5 | 11 | |
| Temporal Action Detection | ActivityNet 75% Seen / 25% Unseen v1.3 | mAP @ IoU=0.556.2 | 11 |