# Phantom-Insight: Adaptive Multi-cue Fusion for Video Camouflaged Object Detection with Multimodal LLM

arXiv: https://arxiv.org/abs/2509.06422 · HTML: https://mlsanity.com/paper/2509.06422/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Builds on (most cited first, 16 of 16)

- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [PraNet: Parallel Reverse Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2006.11392/) (2020)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [PixelLM: Pixel Reasoning with Large Multimodal Model](https://mlsanity.com/paper/2312.02228/) (2023)
- [Concealed Object Detection](https://mlsanity.com/paper/2102.10274/) (2021)
- [Self-supervised Video Object Segmentation by Motion Grouping](https://mlsanity.com/paper/2104.07658/) (2021)
- [Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers](https://mlsanity.com/paper/2303.14816/) (2023)
- [It's Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videos](https://mlsanity.com/paper/1604.00136/) (2016)
- [Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation](https://mlsanity.com/paper/2011.11630/) (2020)
- [Advances in Deep Concealed Scene Understanding](https://mlsanity.com/paper/2304.11234/) (2023)
- [Chain of Visual Perception: Harnessing Multimodal Large Language Models for Zero-shot Camouflaged Object Detection](https://mlsanity.com/paper/2311.11273/) (2023)
- [SAM-PM: Enhancing Video Camouflaged Object Detection using Spatio-Temporal Attention](https://mlsanity.com/paper/2406.05802/) (2024)
- [Search and Rescue in the Face of Uncertain Threats](https://mlsanity.com/paper/1902.05432/) (2019)

## Abstract (arXiv)

Video camouflaged object detection (VCOD) is challenging due to dynamic environments. Existing methods face two main issues: (1) SAM-based methods struggle to separate camouflaged object edges due to model freezing, and (2) MLLM-based methods suffer from poor object separability as large language models merge foreground and background. To address these issues, we propose a novel VCOD method based on SAM and MLLM, called Phantom-Insight. To enhance the separability of object edge details, we represent video sequences with temporal and spatial clues and perform feature fusion via LLM to increase information density. Next, multiple cues are generated through the dynamic foreground visual token scoring module and the prompt network to adaptively guide and fine-tune the SAM model, enabling it to adapt to subtle textures. To enhance the separability of objects and background, we propose a decoupled foreground-background learning strategy. By generating foreground and background cues separately and performing decoupled training, the visual token can effectively integrate foreground and background information independently, enabling SAM to more accurately segment camouflaged objects in the video. Experiments on the MoCA-Mask dataset show that Phantom-Insight achieves state-of-the-art performance across various metrics. Additionally, its ability to detect unseen camouflaged objects on the CAD2016 dataset highlights its strong generalization ability.