Late Temporal Modeling in 3D CNN Architectures with BERT for Action Recognition

By Muhammet Esat Kalfaoglu, Sinan Kalkan, Aydin Alatan. 2020

162 citations recorded by the source corpus.

In this work, we combine 3D convolution with late temporal modeling for action recognition. For this aim, we replace the conventional Temporal Global Average Pooling (TGAP) layer at the end of 3D convolutional architecture with the Bidirectional Encoder Representations from Transformers (BERT) layer in order to better utilize the temporal information with BERT's attention mechanism. We show that this replacement improves the performances of many popular 3D convolution architectures for action recognition, including ResNeXt, I3D, SlowFast and R(2+1)D. Moreover, we provide the-state-of-the-art results on both HMDB51 and UCF101 datasets with 85.10% and 98.69% top-1 accuracy, respectively. The code is publicly available.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Zihui Xue
2. Chenzhuang Du
3. Yu Huang
4. Xuanyao Chen
5. Hang Zhao

In Computer Vision and Pattern Recognition

1. Zihui Xue
2. Chenzhuang Du
3. Yu Huang
4. Xuanyao Chen
5. Hang Zhao
6. Luc Van Gool
7. Xiaogang Wang
8. Dacheng Tao

In Natural Language Processing

1. Hang Zhao

Citations in the corpus

• What Makes Multimodal Learning Better than Single (Provably) (2021, methodology): “Our model corresponds to the recent progress of deep multi-modal learning on various applications, such as scene classification [9] and action recognition [24, 43].”