# Tsanet: Temporal and Scale Alignment for Unsupervised Video Object Segmentation

arXiv: https://arxiv.org/abs/2303.04376 · HTML: https://mlsanity.com/paper/2303.04376/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 8 Mar 2023.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks](https://mlsanity.com/paper/2001.06810/) (2020)
- [VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution](https://mlsanity.com/paper/2206.04647/) (2022)
- [Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks](https://mlsanity.com/paper/2001.06807/) (2020)
- [Full-Duplex Strategy for Video Object Segmentation](https://mlsanity.com/paper/2108.03151/) (2021)
- [Making a Case for 3D Convolutions for Object Segmentation in Videos](https://mlsanity.com/paper/2008.11516/) (2020)
- [Anchor Diffusion for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/1910.10895/) (2019)
- [Deep Video Matting via Spatio-Temporal Alignment and Aggregation](https://mlsanity.com/paper/2104.11208/) (2021)
- [Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2008.01270/) (2020)
- [Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2209.03138/) (2022)
- [F2Net: Learning to Focus on the Foreground for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2012.02534/) (2020)
- [Learning Implicit Feature Alignment Function for Semantic Segmentation](https://mlsanity.com/paper/2206.08655/) (2022)
- [Unsupervised Video Object Segmentation via Prototype Memory Network](https://mlsanity.com/paper/2209.03712/) (2022)
- [Iteratively Selecting an Easy Reference Frame Makes Unsupervised Video Object Segmentation Easier](https://mlsanity.com/paper/2112.12402/) (2021)
- [D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos](https://mlsanity.com/paper/2111.07774/) (2021)
- [Video Salient Object Detection via Contrastive Features and Attention Modules](https://mlsanity.com/paper/2111.02368/) (2021)
- [One-Trimap Video Matting](https://mlsanity.com/paper/2207.13353/) (2022)

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

- [LVMark: Robust Watermark for Latent Video Diffusion Models](https://mlsanity.com/paper/2412.09122/) (2024)
- [Learning Motion and Temporal Cues for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2501.07806/) (2025)

## Abstract (arXiv)

Unsupervised Video Object Segmentation (UVOS) refers to the challenging task of segmenting the prominent object in videos without manual guidance. In recent works, two approaches for UVOS have been discussed that can be divided into: appearance and appearance-motion-based methods, which have limitations respectively. Appearance-based methods do not consider the motion of the target object due to exploiting the correlation information between randomly paired frames. Appearance-motion-based methods have the limitation that the dependency on optical flow is dominant due to fusing the appearance with motion. In this paper, we propose a novel framework for UVOS that can address the aforementioned limitations of the two approaches in terms of both time and scale. Temporal Alignment Fusion aligns the saliency information of adjacent frames with the target frame to leverage the information of adjacent frames. Scale Alignment Decoder predicts the target object mask by aggregating multi-scale feature maps via continuous mapping with implicit neural representation. We present experimental results on public benchmark datasets, DAVIS 2016 and FBMS, which demonstrate the effectiveness of our method. Furthermore, we outperform the state-of-the-art methods on DAVIS 2016.