# Mamba-OTR: a Mamba-based Solution for Online Take and Release Detection from Untrimmed Egocentric Video

arXiv: https://arxiv.org/abs/2507.16342 · HTML: https://mlsanity.com/paper/2507.16342/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Point clouds, detection and remote sensing, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 12 of its 16 references that are in the map.
- First posted on arXiv 22 Jul 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Point clouds, detection and remote sensing](https://mlsanity.com/ssm/point-clouds-detection-and-remote-sensing/)

## Builds on (most cited first, 12 of 12)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding](https://mlsanity.com/paper/2403.09626/) (2024)
- [Long Short-Term Transformer for Online Action Detection](https://mlsanity.com/paper/2107.03377/) (2021)
- [An Outlook into the Future of Egocentric Vision](https://mlsanity.com/paper/2308.07123/) (2023)
- [OadTR: Online Action Detection with Transformers](https://mlsanity.com/paper/2106.11149/) (2021)
- [Temporal Recurrent Networks for Online Action Detection](https://mlsanity.com/paper/1811.07391/) (2018)
- [Real-time Online Video Detection with Temporal Smoothing Transformers](https://mlsanity.com/paper/2209.09236/) (2022)
- [StartNet: Online Detection of Action Start in Untrimmed Videos](https://mlsanity.com/paper/1903.09868/) (2019)
- [WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos](https://mlsanity.com/paper/2006.03732/) (2020)
- [Online Detection of Action Start in Untrimmed, Streaming Videos](https://mlsanity.com/paper/1802.06822/) (2018)

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

- [VidParse: Online Parsing of Egocentric Procedures Like a Pro](https://mlsanity.com/paper/2608.27562/) (2026)

## Abstract (arXiv)

This work tackles the problem of Online detection of Take and Release (OTR) of an object in untrimmed egocentric videos. This task is challenging due to severe label imbalance, with temporally sparse positive annotations, and the need for precise temporal predictions. Furthermore, methods need to be computationally efficient in order to be deployed in real-world online settings. To address these challenges, we propose Mamba-OTR, a model based on the Mamba architecture. Mamba-OTR is designed to exploit temporal recurrence during inference while being trained on short video clips. To address label imbalance, our training pipeline incorporates the focal loss and a novel regularization scheme that aligns model predictions with the evaluation metric. Extensive experiments on EPIC-KITCHENS-100, the comparisons with transformer-based approach, and the evaluation of different training and test schemes demonstrate the superiority of Mamba-OTR in both accuracy and efficiency. These finding are particularly evident when evaluating full-length videos or high frame-rate sequences, even when trained on short video snippets for computational convenience. The proposed Mamba-OTR achieves a noteworthy mp-mAP of 45.48 when operating in a sliding-window fashion, and 43.35 in streaming mode, versus the 20.32 of a vanilla transformer and 25.16 of a vanilla Mamba, thus providing a strong baseline for OTR. We will publicly release the source code of Mamba-OTR to support future research.