# A Temporal Modeling Framework for Video Pre-Training on Video Instance Segmentation

arXiv: https://arxiv.org/abs/2503.17672 · HTML: https://mlsanity.com/paper/2503.17672/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 38 references that are in the map.
- First posted on arXiv 22 Mar 2025.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [End-to-End Video Instance Segmentation with Transformers](https://mlsanity.com/paper/2011.14503/) (2020)
- [Video Instance Segmentation](https://mlsanity.com/paper/1905.04804/) (2019)
- [Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation](https://mlsanity.com/paper/2206.02777/) (2022)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [Text2LIVE: Text-Driven Layered Image and Video Editing](https://mlsanity.com/paper/2204.02491/) (2022)
- [Mask2Former for Video Instance Segmentation](https://mlsanity.com/paper/2112.10764/) (2021)
- [Occluded Video Instance Segmentation: A Benchmark](https://mlsanity.com/paper/2102.01558/) (2021)
- [Robust High-Resolution Video Matting with Temporal Guidance](https://mlsanity.com/paper/2108.11515/) (2021)
- [Layered Neural Atlases for Consistent Video Editing](https://mlsanity.com/paper/2109.11418/) (2021)
- [SeqFormer: Sequential Transformer for Video Instance Segmentation](https://mlsanity.com/paper/2112.08275/) (2021)
- [In Defense of Online Models for Video Instance Segmentation](https://mlsanity.com/paper/2207.10661/) (2022)
- [VITA: Video Instance Segmentation via Object Token Association](https://mlsanity.com/paper/2206.04403/) (2022)
- [MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training](https://mlsanity.com/paper/2208.02245/) (2022)
- [Temporal Action Segmentation: An Analysis of Modern Techniques](https://mlsanity.com/paper/2210.10352/) (2022)
- [Crossover Learning for Fast Online Video Instance Segmentation](https://mlsanity.com/paper/2104.05970/) (2021)
- [DVIS: Decoupled Video Instance Segmentation Framework](https://mlsanity.com/paper/2306.03413/) (2023)
- [Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2212.04976/) (2022)
- [A Generalized Framework for Video Instance Segmentation](https://mlsanity.com/paper/2211.08834/) (2022)
- [CTVIS: Consistent Training for Online Video Instance Segmentation](https://mlsanity.com/paper/2307.12616/) (2023)
- [Make-A-Protagonist: Generic Video Editing with An Ensemble of Experts](https://mlsanity.com/paper/2305.08850/) (2023)
- [Video Class Agnostic Segmentation Benchmark for Autonomous Driving](https://mlsanity.com/paper/2103.11015/) (2021)
- [Leveraging Action Affinity and Continuity for Semi-supervised Temporal Action Segmentation](https://mlsanity.com/paper/2207.08653/) (2022)
- [Temporal Action Segmentation with High-level Complex Activity Labels](https://mlsanity.com/paper/2108.06706/) (2021)

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

- [A Novel Local Focusing Mechanism for Deepfake Detection Generalization](https://mlsanity.com/paper/2508.17029/) (2025)

## Abstract (arXiv)

Contemporary Video Instance Segmentation (VIS) methods typically adhere to a pre-train then fine-tune regime, where a segmentation model trained on images is fine-tuned on videos. However, the lack of temporal knowledge in the pre-trained model introduces a domain gap which may adversely affect the VIS performance. To effectively bridge this gap, we present a novel video pre-training approach to enhance VIS models, especially for videos with intricate instance relationships. Our crucial innovation focuses on reducing disparities between the pre-training and fine-tuning stages. Specifically, we first introduce consistent pseudo-video augmentations to create diverse pseudo-video samples for pre-training while maintaining the instance consistency across frames. Then, we incorporate a multi-scale temporal module to enhance the model's ability to model temporal relations through self- and cross-attention at short- and long-term temporal spans. Our approach does not set constraints on model architecture and can integrate seamlessly with various VIS methods. Experiment results on commonly adopted VIS benchmarks show that our method consistently outperforms state-of-the-art methods. Our approach achieves a notable 4.0% increase in average precision on the challenging OVIS dataset.