.png){kind=icon}
返回
Space or time for video classification transformers
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-023-04756-5.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Spatial and temporal attention plays an important role in video classification tasks. However, there are few studies about the mechanism of spatial and temporal attention behind classification problems. Transformer owns excellent capabilities at training scalability and capturing long-range dependencies among sequences because of its self-attention mechanism, which has achieved great success in many fields, especially in video classifications. The spatio-temporal attention is separated into a temporal attention module and a spatial attention module through Divided-Space-Time Attention, which makes it more conveniently to configure the attention module and adjust the way of attention interaction. Then single-stream models and two-stream models are designed to study the laws of information interaction between spatial attention and temporal attention with a lot of carefully designed experiments. Experiments show that the spatial attention is more critical than the temporal attention, thus the balanced strategy that is commonly used is not always the best choice. Furthermore, there is a necessity to consider the classical two-stream structure models in some cases, which can get better results than the popular single-stream structure models.
Keyword:
Video classification
Spatial attention
Temporal attention
Transformer
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
Human activity recognition using tools of convolutional neural networks: A state of the art review, data sets, challenges, and future prospects使用卷积神经网络工具进行人类活动识别: 最新技术综述，数据集，挑战和未来前景
OAAI
OAAI分享收藏
分享收藏Human action recognition using convolutional LSTM and fully-connected LSTM with different attentions基于不同注意力的卷积LSTM和全连接LSTM的人体动作识别.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Reflectance indices for the detection of water stress in greenhouse tomato (Solanum lycopersicum)
PREAI
分享收藏
查看更多内容