# On the Relevance of Temporal Features for Medical Ultrasound Video Recognition

arXiv: https://arxiv.org/abs/2310.10453 · HTML: https://mlsanity.com/paper/2310.10453/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 31 references that are in the map.
- First posted on arXiv 16 Oct 2023.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Multiple Object Tracking: A Literature Review](https://mlsanity.com/paper/1409.7618/) (2014)
- [Multiple Instance Learning: A Survey of Problem Characteristics and Applications](https://mlsanity.com/paper/1612.03365/) (2016)
- [Spatial Temporal Transformer Network for Skeleton-based Action Recognition](https://mlsanity.com/paper/2012.06399/) (2020)

## Abstract (arXiv)

Many medical ultrasound video recognition tasks involve identifying key anatomical features regardless of when they appear in the video suggesting that modeling such tasks may not benefit from temporal features. Correspondingly, model architectures that exclude temporal features may have better sample efficiency. We propose a novel multi-head attention architecture that incorporates these hypotheses as inductive priors to achieve better sample efficiency on common ultrasound tasks. We compare the performance of our architecture to an efficient 3D CNN video recognition model in two settings: one where we expect not to require temporal features and one where we do. In the former setting, our model outperforms the 3D CNN - especially when we artificially limit the training data. In the latter, the outcome reverses. These results suggest that expressive time-independent models may be more effective than state-of-the-art video recognition models for some common ultrasound tasks in the low-data regime.