# Beyond still images: Temporal features and input variance resilience

arXiv: https://arxiv.org/abs/2311.00800 · HTML: https://mlsanity.com/paper/2311.00800/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 1 Nov 2023.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [Convolutional Two-Stream Network Fusion for Video Action Recognition](https://mlsanity.com/paper/1604.06573/) (2016)
- [YouTube-8M: A Large-Scale Video Classification Benchmark](https://mlsanity.com/paper/1609.08675/) (2016)
- [Long-Term Feature Banks for Detailed Video Understanding](https://mlsanity.com/paper/1812.05038/) (2018)
- [Wider or Deeper: Revisiting the ResNet Model for Visual Recognition](https://mlsanity.com/paper/1611.10080/) (2016)
- [Long-term Temporal Convolutions for Action Recognition](https://mlsanity.com/paper/1604.04494/) (2016)
- [Visual Recognition with Deep Nearest Centroids](https://mlsanity.com/paper/2209.07383/) (2022)
- [Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors](https://mlsanity.com/paper/1505.04868/) (2015)
- [Learnable pooling with Context Gating for video classification](https://mlsanity.com/paper/1706.06905/) (2017)
- [Comparing deep neural networks against humans: object recognition when the signal gets weaker](https://mlsanity.com/paper/1706.06969/) (2017)
- [Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2308.12595/) (2023)
- [Deep Temporal Linear Encoding Networks](https://mlsanity.com/paper/1611.06678/) (2016)
- [Hidden Two-Stream Convolutional Networks for Action Recognition](https://mlsanity.com/paper/1704.00389/) (2017)
- [NeXtVLAD: An Efficient Neural Network to Aggregate Frame-level Features for Large-scale Video Classification](https://mlsanity.com/paper/1811.05014/) (2018)
- [Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition](https://mlsanity.com/paper/1508.03929/) (2015)
- [Large Scale Holistic Video Understanding](https://mlsanity.com/paper/1904.11451/) (2019)
- [Non-local NetVLAD Encoding for Video Classification](https://mlsanity.com/paper/1810.00207/) (2018)

## Built on by (most cited first, 1 of 1)

- [Brain-Aligned Multi-Stream Video Transformers with Sparse Self-Selection](https://mlsanity.com/paper/2607.17625/) (2026)

## Abstract (arXiv)

Traditionally, vision models have predominantly relied on spatial features extracted from static images, deviating from the continuous stream of spatiotemporal features processed by the brain in natural vision. While numerous video-understanding models have emerged, incorporating videos into image-understanding models with spatiotemporal features has been limited. Drawing inspiration from natural vision, which exhibits remarkable resilience to input changes, our research focuses on the development of a brain-inspired model for vision understanding trained with videos. Our findings demonstrate that models that train on videos instead of still images and include temporal features become more resilient to various alternations on input media.