# Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation

arXiv: https://arxiv.org/abs/2204.02791 · HTML: https://mlsanity.com/paper/2204.02791/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 65 references that are in the map.
- First posted on arXiv 6 Apr 2022.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Hierarchical Question-Image Co-Attention for Visual Question Answering](https://mlsanity.com/paper/1606.00061/) (2016)
- [One-Shot Video Object Segmentation](https://mlsanity.com/paper/1611.05198/) (2016)
- [YouTube-VOS: Sequence-to-Sequence Video Object Segmentation](https://mlsanity.com/paper/1809.00461/) (2018)
- [UnitBox: An Advanced Object Detection Network](https://mlsanity.com/paper/1608.01471/) (2016)
- [Deeply supervised salient object detection with short connections](https://mlsanity.com/paper/1611.04849/) (2016)
- [Learning Video Object Segmentation from Static Images](https://mlsanity.com/paper/1612.02646/) (2016)
- [See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks](https://mlsanity.com/paper/2001.06810/) (2020)
- [SegFlow: Joint Learning for Video Object Segmentation and Optical Flow](https://mlsanity.com/paper/1709.06750/) (2017)
- [RVOS: End-to-End Recurrent Network for Video Object Segmentation](https://mlsanity.com/paper/1903.05612/) (2019)
- [Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks](https://mlsanity.com/paper/2001.06807/) (2020)
- [FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos](https://mlsanity.com/paper/1701.05384/) (2017)
- [Learning Video Object Segmentation with Visual Memory](https://mlsanity.com/paper/1704.05737/) (2017)
- [Motion-Attentive Transition for Zero-Shot Video Object Segmentation](https://mlsanity.com/paper/2003.04253/) (2020)
- [Learning Motion Patterns in Videos](https://mlsanity.com/paper/1612.07217/) (2016)
- [Anchor Diffusion for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/1910.10895/) (2019)
- [Dynamic Coattention Networks For Question Answering](https://mlsanity.com/paper/1611.01604/) (2016)
- [Learning to Segment Moving Objects](https://mlsanity.com/paper/1712.01127/) (2017)
- [Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2008.01270/) (2020)
- [PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency Detection](https://mlsanity.com/paper/1812.06314/) (2018)
- [Video Object Segmentation using Teacher-Student Adaptation in a Human Robot Interaction (HRI) Setting](https://mlsanity.com/paper/1810.07733/) (2018)
- [EpO-Net: Exploiting Geometric Constraints on Dense Trajectories for Motion Saliency](https://mlsanity.com/paper/1909.13258/) (2019)
- [ALBA : Reinforcement Learning for Video Object Segmentation](https://mlsanity.com/paper/2005.13039/) (2020)

## Built on by (most cited first, 10 of 10)

- [Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition](https://mlsanity.com/paper/2207.11518/) (2022)
- [Adversarial Attacks on Video Object Segmentation with Hard Region Discovery](https://mlsanity.com/paper/2309.13857/) (2023)
- [Online Unsupervised Video Object Segmentation via Contrastive Motion Clustering](https://mlsanity.com/paper/2306.12048/) (2023)
- [Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2309.11707/) (2023)
- [SpVOS: Efficient Video Object Segmentation with Triple Sparse Convolution](https://mlsanity.com/paper/2310.15115/) (2023)
- [Hierarchical Graph Pattern Understanding for Zero-Shot VOS](https://mlsanity.com/paper/2312.09525/) (2023)
- [IDPro: Flexible Interactive Video Object Segmentation by ID-queried Concurrent Propagation](https://mlsanity.com/paper/2401.12480/) (2024)
- [Few-Shot Video Object Segmentation in X-Ray Angiography Using Local Matching and Spatio-Temporal Consistency Loss](https://mlsanity.com/paper/2601.00988/) (2026)
- [Towards Imbalanced Motion: Part-Decoupling Network for Video Portrait Segmentation](https://mlsanity.com/paper/2307.16565/) (2023)
- [Treating Motion as Option with Output Selection for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2309.14786/) (2023)

## Abstract (arXiv)

Unsupervised video object segmentation (UVOS) aims at automatically separating the primary foreground object(s) from the background in a video sequence. Existing UVOS methods either lack robustness when there are visually similar surroundings (appearance-based) or suffer from deterioration in the quality of their predictions because of dynamic background and inaccurate flow (flow-based). To overcome the limitations, we propose an implicit motion-compensated network (IMCNet) combining complementary cues (textiti.e., appearance and motion) with aligned motion information from the adjacent frames to the current frame at the feature level without estimating optical flows. The proposed IMCNet consists of an affinity computing module (ACM), an attention propagation module (APM), and a motion compensation module (MCM). The light-weight ACM extracts commonality between neighboring input frames based on appearance features. The APM then transmits global correlation in a top-down manner. Through coarse-to-fine iterative inspiring, the APM will refine object regions from multiple resolutions so as to efficiently avoid losing details. Finally, the MCM aligns motion information from temporally adjacent frames to the current frame which achieves implicit motion compensation at the feature level. We perform extensive experiments on textitDAVIS_textit16 and textitYouTube-Objects. Our network achieves favorable performance while running at a faster speed compared to the state-of-the-art methods.