# Detecting Informative Channels: ActionFormer

arXiv: https://arxiv.org/abs/2505.20739 · HTML: https://mlsanity.com/paper/2505.20739/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting](https://mlsanity.com/paper/1907.00235/) (2019)
- [GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond](https://mlsanity.com/paper/1904.11492/) (2019)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [TriDet: Temporal Action Detection with Relative Boundary Modeling](https://mlsanity.com/paper/2303.07347/) (2023)
- [Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks](https://mlsanity.com/paper/1512.04143/) (2015)
- [Probabilistic Forecasting with Temporal Convolutional Neural Network](https://mlsanity.com/paper/1906.04397/) (2019)
- [ACTION-Net: Multipath Excitation for Action Recognition](https://mlsanity.com/paper/2103.07372/) (2021)
- [End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames](https://mlsanity.com/paper/2311.17241/) (2023)
- [WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition](https://mlsanity.com/paper/2304.05088/) (2023)
- [Improving Deep Learning for HAR with shallow LSTMs](https://mlsanity.com/paper/2108.00702/) (2021)
- [Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognition](https://mlsanity.com/paper/2112.10992/) (2021)
- [Sensor Data Augmentation from Skeleton Pose Sequences for Improving Human Activity Recognition](https://mlsanity.com/paper/2406.16886/) (2024)
- [Squeeze-and-Excitation on Spatial and Temporal Deep Feature Space for Action Recognition](https://mlsanity.com/paper/1806.00631/) (2018)

## Abstract (arXiv)

Human Activity Recognition (HAR) has recently witnessed advancements with Transformer-based models. Especially, ActionFormer shows us a new perspectives for HAR in the sense that this approach gives us additional outputs which detect the border of the activities as well as the activity labels. ActionFormer was originally proposed with its input as image/video. However, this was converted to with its input as sensor signals as well. We analyze this extensively in terms of deep learning architectures. Based on the report of high temporal dynamics which limits the model's ability to capture subtle changes effectively and of the interdependencies between the spatial and temporal features. We propose the modified ActionFormer which will decrease these defects for sensor signals. The key to our approach lies in accordance with the Sequence-and-Excitation strategy to minimize the increase in additional parameters and opt for the swish activation function to retain the information about direction in the negative range. Experiments on the WEAR dataset show that our method achieves substantial improvement of a 16.01% in terms of average mAP for inertial data.