Files
icassp2027-experiment/literature_notes/04_miniroad.md
2026-08-26 17:18:50 +08:00

15 lines
1015 B
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# MiniROAD: Minimal RNN Framework for Online Action Detection
- 会议:ICCV 2023
- 阅读深度:重点章节阅读
- 官方链接:https://openaccess.thecvf.com/content/ICCV2023/html/An_MiniROAD_Minimal_RNN_Framework_for_Online_Action_Detection_ICCV_2023_paper.html
## 摘要(中文转述)
MiniROAD 重新审视在线动作检测,指出递归模型表现不佳的重要原因是训练与推理过程不一致,而不一定是 RNN 本身能力不足。论文通过简单的递归结构和时间步损失设计获得较好的准确率与效率平衡,并把方法扩展到动作预判,展示轻量在线模型的竞争力。
## 与当前项目的关系
本项目已经把归一化 MiniROAD 风格损失作为消融候选。它给出的关键启示是:训练时必须模拟真正的流式状态演进;若训练头看到完整序列、推理却逐步更新,损失微调很难弥补语义错位。它也是 transition-focused 监督训练比直接采用强化学习更稳妥的依据之一。