# SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation

arXiv: https://arxiv.org/abs/2411.17646 · HTML: https://mlsanity.com/paper/2411.17646/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 54 references that are in the map.
- First posted on arXiv 26 Nov 2024.

## Builds on (most cited first, 30 of 44)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [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)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks](https://mlsanity.com/paper/2208.10442/) (2022)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [Cross-Modal Self-Attention Network for Referring Image Segmentation](https://mlsanity.com/paper/1904.04745/) (2019)
- [Modeling Context Between Objects for Referring Expression Understanding](https://mlsanity.com/paper/1608.00525/) (2016)
- [MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions](https://mlsanity.com/paper/2308.08544/) (2023)
- [Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers](https://mlsanity.com/paper/2106.05392/) (2021)
- [Language as Queries for Referring Video Object Segmentation](https://mlsanity.com/paper/2201.00487/) (2022)
- [To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks](https://mlsanity.com/paper/1903.05987/) (2019)
- [Video Object Segmentation with Language Referring Expressions](https://mlsanity.com/paper/1803.08006/) (2018)
- [End-to-End Referring Video Object Segmentation with Multimodal Transformers](https://mlsanity.com/paper/2111.14821/) (2021)
- [VISA: Reasoning Video Object Segmentation via Large Language Models](https://mlsanity.com/paper/2407.11325/) (2024)
- [VLT: Vision-Language Transformer and Query Generation for Referring Segmentation](https://mlsanity.com/paper/2210.15871/) (2022)
- [Actor and Action Video Segmentation from a Sentence](https://mlsanity.com/paper/1803.07485/) (2018)
- [Cross-Modal Progressive Comprehension for Referring Segmentation](https://mlsanity.com/paper/2105.07175/) (2021)
- [One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos](https://mlsanity.com/paper/2409.19603/) (2024)

## Built on by (most cited first, 30 of 44)

- [Advancing Complex Video Object Segmentation via Progressive Concept Construction](https://mlsanity.com/paper/2507.15852/) (2025)
- [Multimodal Referring Segmentation: A Survey](https://mlsanity.com/paper/2508.00265/) (2025)
- [ReSurgSAM2: Referring Segment Anything in Surgical Video via Credible Long-term Tracking](https://mlsanity.com/paper/2505.08581/) (2025)
- [OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts](https://mlsanity.com/paper/2507.05427/) (2025)
- [SAM2 for Image and Video Segmentation: A Comprehensive Survey](https://mlsanity.com/paper/2503.12781/) (2025)
- [Deforming Videos to Masks: Flow Matching for Referring Video Segmentation](https://mlsanity.com/paper/2510.06139/) (2025)
- [CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for Videos](https://mlsanity.com/paper/2505.18561/) (2025)
- [SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation](https://mlsanity.com/paper/2505.21795/) (2025)
- [UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation](https://mlsanity.com/paper/2512.07831/) (2025)
- [HiM2SAM: Enhancing SAM2 with Hierarchical Motion Estimation and Memory Optimization towards Long-term Tracking](https://mlsanity.com/paper/2507.07603/) (2025)
- [Towards High-Consistency Embodied World Model with Multi-View Trajectory Videos](https://mlsanity.com/paper/2511.12882/) (2025)
- [BrokenVideos: A Benchmark Dataset for Fine-Grained Artifact Localization in AI-Generated Videos](https://mlsanity.com/paper/2506.20103/) (2025)
- [MomentSeg: Moment-Centric Sampling for Enhanced Video Pixel Understanding](https://mlsanity.com/paper/2510.09274/) (2025)
- [3AM: 3egment Anything with Geometric Consistency in Videos](https://mlsanity.com/paper/2601.08831/) (2026)
- [Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation](https://mlsanity.com/paper/2503.03492/) (2025)
- [Depthwise-Dilated Convolutional Adapters for Medical Object Tracking and Segmentation Using the Segment Anything Model 2](https://mlsanity.com/paper/2507.14613/) (2025)
- [Segment Anything for Video: A Comprehensive Review of Video Object Segmentation and Tracking from Past to Future](https://mlsanity.com/paper/2507.22792/) (2025)
- [Distractor-Aware Memory-Based Visual Object Tracking](https://mlsanity.com/paper/2509.13864/) (2025)
- [Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval](https://mlsanity.com/paper/2602.08224/) (2026)
- [SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction](https://mlsanity.com/paper/2605.20110/) (2026)
- [Temporal-Conditional Referring Video Object Segmentation with Noise-Free Text-to-Video Diffusion Model](https://mlsanity.com/paper/2508.13584/) (2025)
- [SAM 2++: Tracking Anything at Any Granularity](https://mlsanity.com/paper/2510.18822/) (2025)
- [SAM-pose2seg: Pose-Guided Human Instance Segmentation in Crowds](https://mlsanity.com/paper/2601.08982/) (2026)
- [Conditional Flow Matching for Visually-Guided Acoustic Highlighting](https://mlsanity.com/paper/2602.03762/) (2026)
- [VIRST: Video-Instructed Reasoning Assistant for SpatioTemporal Segmentation](https://mlsanity.com/paper/2603.27060/) (2026)
- [UniSurgSAM: A Unified Promptable Model for Reliable Surgical Video Segmentation](https://mlsanity.com/paper/2604.03645/) (2026)
- [PanopticQuery: Unified Query-Time Reasoning for 4D Scenes](https://mlsanity.com/paper/2604.05638/) (2026)
- [Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification](https://mlsanity.com/paper/2605.17531/) (2026)
- [Temporal Grounding as a Learning Signal for Referring Video Object Segmentation](https://mlsanity.com/paper/2508.11955/) (2025)
- [BBoxMaskPose v2: Expanding Mutual Conditioning to 3D](https://mlsanity.com/paper/2601.15200/) (2026)

## Abstract (arXiv)

Referring Video Object Segmentation (RVOS) relies on natural language expressions to segment an object in a video clip. Existing methods restrict reasoning either to independent short clips, losing global context, or process the entire video offline, impairing their application in a streaming fashion. In this work, we aim to surpass these limitations and design an RVOS method capable of effectively operating in streaming-like scenarios while retaining contextual information from past frames. We build upon the Segment-Anything 2 (SAM2) model, that provides robust segmentation and tracking capabilities and is naturally suited for streaming processing. We make SAM2 wiser, by empowering it with natural language understanding and explicit temporal modeling at the feature extraction stage, without fine-tuning its weights, and without outsourcing modality interaction to external models. To this end, we introduce a novel adapter module that injects temporal information and multi-modal cues in the feature extraction process. We further reveal the phenomenon of tracking bias in SAM2 and propose a learnable module to adjust its tracking focus when the current frame features suggest a new object more aligned with the caption. Our proposed method, SAMWISE, achieves state-of-the-art across various benchmarks, by adding a negligible overhead of less than 5 M parameters. Code is available at https://github.com/ClaudiaCuttano/SAMWISE .