# TokenMotion: Motion-Guided Vision Transformer for Video Camouflaged Object Detection Via Learnable Token Selection

arXiv: https://arxiv.org/abs/2311.02535 · HTML: https://mlsanity.com/paper/2311.02535/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 17 references that are in the map.
- First posted on arXiv 5 Nov 2023.

## Builds on (most cited first, 13 of 13)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Concealed Object Detection](https://mlsanity.com/paper/2102.10274/) (2021)
- [Learning in the Frequency Domain](https://mlsanity.com/paper/2002.12416/) (2020)
- [Self-supervised Video Object Segmentation by Motion Grouping](https://mlsanity.com/paper/2104.07658/) (2021)
- [Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection](https://mlsanity.com/paper/2203.02688/) (2022)
- [Multimodal Token Fusion for Vision Transformers](https://mlsanity.com/paper/2204.08721/) (2022)
- [Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation](https://mlsanity.com/paper/2011.11630/) (2020)
- [Implicit Motion Handling for Video Camouflaged Object Detection](https://mlsanity.com/paper/2203.07363/) (2022)
- [Enhancing State Estimation in Robots: A Data-Driven Approach with Differentiable Ensemble Kalman Filters](https://mlsanity.com/paper/2308.09870/) (2023)
- [TransUPR: A Transformer-based Uncertain Point Refiner for LiDAR Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2302.08594/) (2023)

## Built on by (most cited first, 2 of 2)

- [A Survey of Camouflaged Object Detection and Beyond](https://mlsanity.com/paper/2408.14562/) (2024)
- [CamSAM2: Segment Anything Accurately in Camouflaged Videos](https://mlsanity.com/paper/2503.19730/) (2025)

## Abstract (arXiv)

The area of Video Camouflaged Object Detection (VCOD) presents unique challenges in the field of computer vision due to texture similarities between target objects and their surroundings, as well as irregular motion patterns caused by both objects and camera movement. In this paper, we introduce TokenMotion (TMNet), which employs a transformer-based model to enhance VCOD by extracting motion-guided features using a learnable token selection. Evaluated on the challenging MoCA-Mask dataset, TMNet achieves state-of-the-art performance in VCOD. It outperforms the existing state-of-the-art method by a 12.8% improvement in weighted F-measure, an 8.4% enhancement in S-measure, and a 10.7% boost in mean IoU. The results demonstrate the benefits of utilizing motion-guided features via learnable token selection within a transformer-based framework to tackle the intricate task of VCOD.