# Event-Driven Refresh and Recurrence Memory to Reduce Stale Grounding in Referring Video Object Segmentation

arXiv: https://arxiv.org/abs/2609.38758 · HTML: https://mlsanity.com/paper/2609.38758/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 23 references that are in the map.
- First posted on arXiv 30 Sep 2026.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model](https://mlsanity.com/paper/2207.07115/) (2022)
- [MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions](https://mlsanity.com/paper/2308.08544/) (2023)
- [Associating Objects with Transformers for Video Object Segmentation](https://mlsanity.com/paper/2106.02638/) (2021)
- [Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation](https://mlsanity.com/paper/2106.05210/) (2021)
- [Language as Queries for Referring Video Object Segmentation](https://mlsanity.com/paper/2201.00487/) (2022)
- [End-to-End Referring Video Object Segmentation with Multimodal Transformers](https://mlsanity.com/paper/2111.14821/) (2021)
- [AdaFrame: Adaptive Frame Selection for Fast Video Recognition](https://mlsanity.com/paper/1811.12432/) (2018)
- [VISA: Reasoning Video Object Segmentation via Large Language Models](https://mlsanity.com/paper/2407.11325/) (2024)
- [Actor and Action Video Segmentation from a Sentence](https://mlsanity.com/paper/1803.07485/) (2018)
- [OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation](https://mlsanity.com/paper/2307.09356/) (2023)
- [FrameExit: Conditional Early Exiting for Efficient Video Recognition](https://mlsanity.com/paper/2104.13400/) (2021)
- [SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation](https://mlsanity.com/paper/2305.17011/) (2023)
- [Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus](https://mlsanity.com/paper/2207.01203/) (2022)
- [Matching Anything by Segmenting Anything](https://mlsanity.com/paper/2406.04221/) (2024)
- [RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation](https://mlsanity.com/paper/2010.00263/) (2020)

## Abstract (arXiv)

Referring Video Object Segmentation (RVOS) aims to produce a pixel-accurate mask sequence for an object specified by natural language. Sa2VA combines a multimodal large language model with SAM2 for grounded segmentation; however, its inference typically grounds the query from a small fixed set of initial keyframes and then relies on propagation. In long or dynamic videos, this can cause stale grounding and persistent false positives when the object composition changes (e.g., distractors enter or the target disappears/re-appears). We propose Event-Driven Refresh + Recurrence Memory (EDRRM), an enhancement that selectively re-invokes Sa2VA only at stable change points. EDRRM triggers refresh boundaries using an EMA-smoothed event score computed from tracking-derived cues (births/deaths and coarse composition/layout changes) with temporal constraints. A recurrence memory further retrieves anchor frames via CLIP similarity to re-condition the model on re-appearance events. Experiments on Ref-DAVIS17, MeViS, and ReVOS show that EDRRM achieves a competitive accuracy-efficiency trade-off relative to fixed-window and FrameDiff-SSIM baselines, maintaining comparable or superior J&F scores at substantially lower average refresh-call budgets and reducing false-positive failures. End-to-end runtime analysis further confirms that the overhead introduced by tracking, CLIP-based recurrence matching, and the identifiability gate remains modest relative to the dominant Sa2VA inference cost, thereby validating the efficiency of the proposed pipeline.