# Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation

arXiv: https://arxiv.org/abs/2106.05210 · HTML: https://mlsanity.com/paper/2106.05210/

## Key facts

- Cited by 203 papers in the map (data through 14 Oct 2026).
- Builds on 69 of its 88 references that are in the map.
- First posted on arXiv 9 Jun 2021.

## Builds on (most cited first, 30 of 69)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [MOT16: A Benchmark for Multi-Object Tracking](https://mlsanity.com/paper/1603.00831/) (2016)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark](https://mlsanity.com/paper/1809.03327/) (2018)
- [Fast Online Object Tracking and Segmentation: A Unifying Approach](https://mlsanity.com/paper/1812.05050/) (2018)
- [One-Shot Video Object Segmentation](https://mlsanity.com/paper/1611.05198/) (2016)
- [Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector](https://mlsanity.com/paper/1908.01998/) (2019)
- [FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation](https://mlsanity.com/paper/1902.09513/) (2019)
- [The Lipschitz Constant of Self-Attention](https://mlsanity.com/paper/2006.04710/) (2020)
- [FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation](https://mlsanity.com/paper/1907.12347/) (2019)
- [Learning Video Object Segmentation from Static Images](https://mlsanity.com/paper/1612.02646/) (2016)
- [TAO: A Large-Scale Benchmark for Tracking Any Object](https://mlsanity.com/paper/2005.10356/) (2020)
- [Collaborative Video Object Segmentation by Foreground-Background Integration](https://mlsanity.com/paper/2003.08333/) (2020)

## Built on by (most cited first, 30 of 203)

- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model](https://mlsanity.com/paper/2207.07115/) (2022)
- [MOSE: A New Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2302.01872/) (2023)
- [Tracking Anything with Decoupled Video Segmentation](https://mlsanity.com/paper/2309.03903/) (2023)
- [Segment and Track Anything](https://mlsanity.com/paper/2305.06558/) (2023)
- [Universal Instance Perception as Object Discovery and Retrieval](https://mlsanity.com/paper/2303.06674/) (2023)
- [Language as Queries for Referring Video Object Segmentation](https://mlsanity.com/paper/2201.00487/) (2022)
- [Decoupling Features in Hierarchical Propagation for Video Object Segmentation](https://mlsanity.com/paper/2210.09782/) (2022)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [Towards Grand Unification of Object Tracking](https://mlsanity.com/paper/2207.07078/) (2022)
- [ReasonNet: End-to-End Driving with Temporal and Global Reasoning](https://mlsanity.com/paper/2305.10507/) (2023)
- [SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree](https://mlsanity.com/paper/2410.16268/) (2024)
- [LVOS: A Benchmark for Long-term Video Object Segmentation](https://mlsanity.com/paper/2211.10181/) (2022)
- [Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips](https://mlsanity.com/paper/2309.05663/) (2023)
- [HIPTrack: Visual Tracking with Historical Prompts](https://mlsanity.com/paper/2311.02072/) (2023)
- [BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video](https://mlsanity.com/paper/2209.12118/) (2022)
- [MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2508.05630/) (2025)
- [InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior](https://mlsanity.com/paper/2404.11613/) (2024)
- [XMem++: Production-level Video Segmentation From Few Annotated Frames](https://mlsanity.com/paper/2307.15958/) (2023)
- [Recurrent Dynamic Embedding for Video Object Segmentation](https://mlsanity.com/paper/2205.03761/) (2022)
- [Vivim: a Video Vision Mamba for Medical Video Segmentation](https://mlsanity.com/paper/2401.14168/) (2024)
- [Breaking the "Object" in Video Object Segmentation](https://mlsanity.com/paper/2212.06200/) (2022)
- [Towards Open-Vocabulary Video Instance Segmentation](https://mlsanity.com/paper/2304.01715/) (2023)
- [LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation](https://mlsanity.com/paper/2404.19326/) (2024)
- [NeRF-In: Free-Form NeRF Inpainting with RGB-D Priors](https://mlsanity.com/paper/2206.04901/) (2022)
- [Per-Clip Video Object Segmentation](https://mlsanity.com/paper/2208.01924/) (2022)
- [GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removal](https://mlsanity.com/paper/2404.13679/) (2024)
- [Learning Quality-aware Dynamic Memory for Video Object Segmentation](https://mlsanity.com/paper/2207.07922/) (2022)
- [Look Before You Match: Instance Understanding Matters in Video Object Segmentation](https://mlsanity.com/paper/2212.06826/) (2022)

## Abstract (arXiv)

This paper presents a simple yet effective approach to modeling space-time correspondences in the context of video object segmentation. Unlike most existing approaches, we establish correspondences directly between frames without re-encoding the mask features for every object, leading to a highly efficient and robust framework. With the correspondences, every node in the current query frame is inferred by aggregating features from the past in an associative fashion. We cast the aggregation process as a voting problem and find that the existing inner-product affinity leads to poor use of memory with a small (fixed) subset of memory nodes dominating the votes, regardless of the query. In light of this phenomenon, we propose using the negative squared Euclidean distance instead to compute the affinities. We validated that every memory node now has a chance to contribute, and experimentally showed that such diversified voting is beneficial to both memory efficiency and inference accuracy. The synergy of correspondence networks and diversified voting works exceedingly well, achieves new state-of-the-art results on both DAVIS and YouTubeVOS datasets while running significantly faster at 20+ FPS for multiple objects without bells and whistles.