arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.09861cs.CV
收藏

上下文感知的RCNN:视频中动作检测的基线

Context-Aware RCNN: A Baseline for Action Detection in Videos

Nanjing University(南京大学);SenseTime Research(商汤科技研究院)

Jianchao Wu, Zhanghui Kuang, Limin Wang, Wayne Zhang, Gangshan Wu

摘要:

视频动作检测方法通常遵循Faster-RCNN的标准管道,在RoI池特征上进行以演员为中心的动作识别。在这项工作中,我们第一次经验性地发现识别精度是高度相关的限界框大小的演员,因此更高的分辨率的演员有助于更好的性能。然而,视频模型需要在时间上进行密集采样以实现准确的识别。为了适应GPU内存,骨干网络的帧必须保持低分辨率,导致RoI-Pooling层的特征图粗糙。因此,我们在使用I3 D深度网络进行特征提取之前,通过裁剪和隐藏演员周围的图像补丁来重新访问RCNN以进行以演员为中心的动作识别。此外,我们发现稍微扩展演员边界框并融合上下文特征可以进一步提高性能。因此,我们开发了一个令人惊讶的有效基线(上下文感知RCNN),它在AVA和JHMDB两个具有挑战性的动作检测基准上取得了新的最先进的结果。我们的观察结果挑战了传统的基于ROI池的管道的智慧,并鼓励研究人员重新思考以演员为中心的动作识别中分辨率的重要性。我们的方法可以作为一个强大的基线视频动作检测,并有望激发新的想法,这一领域。代码可在\url{https://github.com/MCG-NJU/CRCNN-Action}上获得。

英文摘要:

Video action detection approaches usually conduct actor-centric action recognition over RoI-pooled features following the standard pipeline of Faster-RCNN. In this work, we first empirically find the recognition accuracy is highly correlated with the bounding box size of an actor, and thus higher resolution of actors contributes to better performance. However, video models require dense sampling in time to achieve accurate recognition. To fit in GPU memory, the frames to backbone network must be kept low-resolution, resulting in a coarse feature map in RoI-Pooling layer. Thus, we revisit RCNN for actor-centric action recognition via cropping and resizing image patches around actors before feature extraction with I3D deep network. Moreover, we found that expanding actor bounding boxes slightly and fusing the context features can further boost the performance. Consequently, we develop a surpringly effective baseline (Context-Aware RCNN) and it achieves new state-of-the-art results on two challenging action detection benchmarks of AVA and JHMDB. Our observations challenge the conventional wisdom of RoI-Pooling based pipeline and encourage researchers rethink the importance of resolution in actor-centric action recognition. Our approach can serve as a strong baseline for video action detection and is expected to inspire new ideas for this filed. The code is available at \url{https://github.com/MCG-NJU/CRCNN-Action}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑