用统一网络实现视频动作定位，提升准确率与效率
Technical Report for ActivityNet Challenge 2022 -- Temporal Action Localization
- 采用VideoSwinTransformer提取特征，统一网络同步生成候选框与类别标签
- Faster-TAD简化流程，在ActivityNet-1.3上表现媲美多阶段方法
- 融合互补模型结果，提升检测鲁棒性，适合追求高效定位的场景
在ActivityNet-1.3数据集的视频动作定位任务中，本文旨在定位未剪辑视频中各类动作的时间边界并预测动作类别。首先，使用VideoSwinTransformer作为特征提取器，获取多尺度特征；随后，采用遵循Faster-TAD框架的统一网络，同时生成候选区域并预测语义标签；最后，通过集成多个互补的时序动作检测模型结果，进一步提升性能。Faster-TAD简化了传统多阶段检测流程，在保持高精度的同时显著提高效率，其表现与复杂多阶段方法相当。
原文摘要 · Abstract (English)
In the task of temporal action localization of ActivityNet-1.3 datasets, we propose to locate the temporal boundaries of each action and predict action class in untrimmed videos. We first apply VideoSwinTransformer as feature extractor to extract different features. Then we apply a unified network following Faster-TAD to simultaneously obtain proposals and semantic labels. Last, we ensemble the results of different temporal action detection models which complement each other. Faster-TAD simplifies the pipeline of TAD and gets remarkable performance, obtaining comparable results as those of multi-step approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。