# The 2nd Solution for LSVOS Challenge RVOS Track: Spatial-temporal Refinement for Consistent Semantic Segmentation

arXiv: https://arxiv.org/abs/2408.12447 · HTML: https://mlsanity.com/paper/2408.12447/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 15 references that are in the map.
- First posted on arXiv 22 Aug 2024.

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [MOSE: A New Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2302.01872/) (2023)
- [MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions](https://mlsanity.com/paper/2308.08544/) (2023)
- [Multilingual Constituency Parsing with Self-Attention and Pre-Training](https://mlsanity.com/paper/1812.11760/) (2018)
- [Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation](https://mlsanity.com/paper/2404.03645/) (2024)
- [Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation](https://mlsanity.com/paper/2305.16318/) (2023)
- [PVUW 2024 Challenge on Complex Video Understanding: Methods and Results](https://mlsanity.com/paper/2406.17005/) (2024)
- [3rd Place Solution for MeViS Track in CVPR 2024 PVUW workshop: Motion Expression guided Video Segmentation](https://mlsanity.com/paper/2406.04842/) (2024)
- [1st Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation](https://mlsanity.com/paper/2406.07043/) (2024)
- [2nd Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation](https://mlsanity.com/paper/2406.13939/) (2024)

## Built on by (most cited first, 3 of 3)

- [On Efficient Variants of Segment Anything Model: A Survey](https://mlsanity.com/paper/2410.04960/) (2024)
- [Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation](https://mlsanity.com/paper/2604.10950/) (2026)
- [Planner-Refiner: Dynamic Space-Time Refinement for Vision-Language Alignment in Videos](https://mlsanity.com/paper/2508.07330/) (2025)

## Abstract (arXiv)

Referring Video Object Segmentation (RVOS) is a challenging task due to its requirement for temporal understanding. Due to the obstacle of computational complexity, many state-of-the-art models are trained on short time intervals. During testing, while these models can effectively process information over short time steps, they struggle to maintain consistent perception over prolonged time sequences, leading to inconsistencies in the resulting semantic segmentation masks. To address this challenge, we take a step further in this work by leveraging the tracking capabilities of the newly introduced Segment Anything Model version 2 (SAM-v2) to enhance the temporal consistency of the referring object segmentation model. Our method achieved a score of 60.40 mathcalJ&F on the test set of the MeViS dataset, placing 2nd place in the final ranking of the RVOS Track at the ECCV 2024 LSVOS Challenge.