# Action recognition with spatial-temporal discriminative filter banks

arXiv: https://arxiv.org/abs/1908.07625 · HTML: https://mlsanity.com/paper/1908.07625/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Aug 2019.

## Built on by (most cited first, 15 of 15)

- [Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning](https://mlsanity.com/paper/2110.01770/) (2021)
- [No frame left behind: Full Video Action Recognition](https://mlsanity.com/paper/2103.15395/) (2021)
- [Gate-Shift-Fuse for Video Action Recognition](https://mlsanity.com/paper/2203.08897/) (2022)
- [Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition](https://mlsanity.com/paper/2207.13259/) (2022)
- [Attention in Attention: Modeling Context Correlation for Efficient Video Classification](https://mlsanity.com/paper/2204.09303/) (2022)
- [Semantically Guided Representation Learning For Action Anticipation](https://mlsanity.com/paper/2407.02309/) (2024)
- [Motion-driven Visual Tempo Learning for Video-based Action Recognition](https://mlsanity.com/paper/2202.12116/) (2022)
- [Condensing a Sequence to One Informative Frame for Video Recognition](https://mlsanity.com/paper/2201.04022/) (2022)
- [Optimization Planning for 3D ConvNets](https://mlsanity.com/paper/2201.04021/) (2022)
- [Boosting Video Representation Learning with Multi-Faceted Integration](https://mlsanity.com/paper/2201.04023/) (2022)
- [PICNN: A Pathway towards Interpretable Convolutional Neural Networks](https://mlsanity.com/paper/2312.12068/) (2023)
- [Efficient Spatialtemporal Context Modeling for Action Recognition](https://mlsanity.com/paper/2103.11190/) (2021)
- [Early Action Recognition with Action Prototypes](https://mlsanity.com/paper/2312.06598/) (2023)
- [Explicit homography estimation improves contrastive self-supervised learning](https://mlsanity.com/paper/2101.04713/) (2021)
- [ST-ABN: Visual Explanation Taking into Account Spatio-temporal Information for Video Recognition](https://mlsanity.com/paper/2110.15574/) (2021)

## Abstract (arXiv)

Action recognition has seen a dramatic performance improvement in the last few years. Most of the current state-of-the-art literature either aims at improving performance through changes to the backbone CNN network, or they explore different trade-offs between computational efficiency and performance, again through altering the backbone network. However, almost all of these works maintain the same last layers of the network, which simply consist of a global average pooling followed by a fully connected layer. In this work we focus on how to improve the representation capacity of the network, but rather than altering the backbone, we focus on improving the last layers of the network, where changes have low impact in terms of computational cost. In particular, we show that current architectures have poor sensitivity to finer details and we exploit recent advances in the fine-grained recognition literature to improve our model in this aspect. With the proposed approach, we obtain state-of-the-art performance on Kinetics-400 and Something-Something-V1, the two major large-scale action recognition benchmarks.