Knowledge Commons of Institute of Automation,CAS
Learning from the raw domain: cross modality distillation for compressed video action recognition | |
Yufan Liu1,2; Jiajiong Cao3; Weiming Bai1,2; Bing Li1,4; Weiming Hu1,2 | |
2023-06 | |
会议名称 | IEEE International Conference on Acoustics, Speech and Signal Processing. (ICASSP) |
会议日期 | 2023.6 |
会议地点 | Rhodes, Greece |
摘要 | Video action recognition is faced with the challenges of both huge computation burdens and performance requirements. Using compressed domain data, which saves much decoding computation, is a possible solution. Unfortunately, existing compressed-domain-based (CD) methods fail to obtain high performance, compared with state-of-the-art (SOTA) raw domain-based (RD) methods. In order to solve the problem, we propose a cross-modality knowledge distillation method to force the CD model to learn the knowledge from the RD model. In particular, spatial knowledge and temporal knowledge are first constructed to align feature space between the raw domain and the compressed domain. Then, an adaptively multi-path knowledge learning scheme is presented to help |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 智能计算与学习 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51645 |
专题 | 多模态人工智能系统全国重点实验室_视频内容安全 |
通讯作者 | Bing Li |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Ant Financial Service Group 4.PeopleAI, Inc. |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yufan Liu,Jiajiong Cao,Weiming Bai,et al. Learning from the raw domain: cross modality distillation for compressed video action recognition[C],2023. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
ICASSP_CameraReady11(411KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论