# MamBOA: State-Space Architecture for Video Recognition

arXiv: https://arxiv.org/abs/2606.15275 · HTML: https://mlsanity.com/paper/2606.15275/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 22 of its 25 references that are in the map.
- First posted on arXiv 13 Jun 2026.

## Placed in

- State-space sequence models (S4, Mamba) / [Video, motion and generative Mamba models](https://mlsanity.com/ssm/video-motion-and-generative-mamba-models/)

## Builds on (most cited first, 22 of 22)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (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)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [VideoMamba: State Space Model for Efficient Video Understanding](https://mlsanity.com/paper/2403.06977/) (2024)
- [TDN: Temporal Difference Networks for Efficient Action Recognition](https://mlsanity.com/paper/2012.10071/) (2020)
- [TEA: Temporal Excitation and Aggregation for Action Recognition](https://mlsanity.com/paper/2004.01398/) (2020)
- [Long Movie Clip Classification with State-Space Video Models](https://mlsanity.com/paper/2204.01692/) (2022)
- [Grouped Spatial-Temporal Aggregation for Efficient Action Recognition](https://mlsanity.com/paper/1909.13130/) (2019)
- [Dual-path Adaptation from Image to Video Transformers](https://mlsanity.com/paper/2303.09857/) (2023)
- [Can An Image Classifier Suffice For Action Recognition?](https://mlsanity.com/paper/2106.14104/) (2021)

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

- [Groupwise Selective State-Space Filtering for Accurate and Streaming Action Boundary Detection](https://mlsanity.com/paper/2609.33400/) (2026)

## Abstract (arXiv)

Fine-grained action recognition demands temporal reasoning that general-purpose architectures address through different cost-accuracy tradeoffs: 3D dense operators couple computation to the input volume, while difference-based methods approximate motion through rigid, hand-crafted subtraction of uncontextualized features - each reflecting a deliberate design choice with corresponding limitations in expressiveness or flexibility. We present MamBOA, a backbone-agnostic temporal framework built upon a novel interleaved scan structure that recasts the selective state-space recurrence (S6) as a native motion synthesizer. By interleaving consecutive feature representations extracted from a pretrained backbone into a single alternating sequence, the proposed scan structurally drives the recurrence to encode both temporal observations of each position within a shared hidden state, separated by only a single decay step - rendering the inter-frame transition an intrinsic component of the state dynamics rather than an externally computed quantity. A cascade of dedicated alignment and decoding operations then distills this joint encoding into an explicit motion representation, which a dual-path pooling mechanism adaptively aggregates by balancing attention-driven selection with uniform temporal coverage. The framework interfaces seamlessly with CNN, Transformer, and Mamba backbone families, adding only ~2.1 GFLOPs per feature pair. On Diving48, MamBOA achieves 85.02% Top-1 accuracy with an image-pretrained backbone and 86.24% with a video-pretrained backbone processing the entire video in a single forward pass - demonstrating that structurally induced state-space dynamics constitute a principled and general foundation for motion modeling.