Referring Video Object Segmentation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

5 leaderboard tables shown for this task, 5 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

4 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 50 papers with code (74 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• VISA: Reasoning Video Object Segmentation via Large Language Models
  16 Jul 2024 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  In this paper, we introduce a new task, Reasoning Video Object Segmentation (ReasonVOS).
• UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces
  25 Dec 2023 2 repositories listed Syntology ran 9 of 9 samples · 0 unverified
  We evaluate our unified models on various benchmarks.
• LISA: Reasoning Segmentation via Large Language Model
  1 Aug 2023 2 repositories listed
  In this work, we propose a new segmentation task -- reasoning segmentation.
• End-to-End Referring Video Object Segmentation with Multimodal Transformers
  29 Nov 2021 2 repositories listed Syntology ran 6 of 11 samples · 5 unverified
  Due to the complex nature of this multimodal task, which combines text reasoning, video understanding, instance segmentation and tracking, existing approaches typically rely on sophisticated pipelines in order to tackle…
• VideoMolmo: Spatio-Temporal Grounding Meets Pointing
  5 Jun 2025 1 repository listed
  Current video-based approaches, while proficient in tracking, lack the sophisticated reasoning capabilities of large language models, limiting their contextual understanding and generalization.
• Few-Shot Referring Video Single- and Multi-Object Segmentation via Cross-Modal Affinity with Instance Sequence Matching
  18 Apr 2025 1 repository listed
  Referring video object segmentation (RVOS) aims to segment objects in videos guided by natural language descriptions.
• GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation
  10 Apr 2025 1 repository listed Syntology ran 3 of 12 samples · 9 unverified · 12 pointer-only (licence)
  This paper proposes a novel framework utilizing multi-modal large language models (MLLMs) for referring video object segmentation (RefVOS).
• The 1st Solution for 4th PVUW MeViS Challenge: Unleashing the Potential of Large Multimodal Models for Referring Video Segmentation
  7 Apr 2025 1 repository listed
  Motion expression video segmentation is designed to segment objects in accordance with the input motion expressions.
• 4th PVUW MeViS 3rd Place Report: Sa2VA
  1 Apr 2025 1 repository listed
  Referring video object segmentation (RVOS) is a challenging task that requires the model to segment the object in a video given the language description.
• ReferDINO-Plus: 2nd Solution for 4th PVUW MeViS Challenge at CVPR 2025
  30 Mar 2025 1 repository listed
  This task has attracted increasing attention in the field of computer vision due to its promising applications in video editing and human-agent interaction.
• Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation
  5 Mar 2025 1 repository listed
  This reference is then utilized by a dedicated propagation module to track and segment the object across the entire video.
• MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation
  23 Jan 2025 1 repository listed Syntology ran 5 of 16 samples · 11 unverified
  Referring video object segmentation (RVOS) aims to segment objects in a video according to textual descriptions, which requires the integration of multimodal information and temporal dynamics perception.
• InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling
  21 Jan 2025 1 repository listed
  This paper aims to improve the performance of video multimodal large language models (MLLM) via long and rich context (LRC) modeling.
• The Devil is in Temporal Token: High Quality Video Reasoning Segmentation
  15 Jan 2025 1 repository listed
  Existing methods for Video Reasoning Segmentation rely heavily on a single special token to represent the object in the keyframe or the entire video, inadequately capturing spatial complexity and inter-frame motion.
• Multi-Context Temporal Consistent Modeling for Referring Video Object Segmentation
  9 Jan 2025 1 repository listed
  The Aligner removes noise from queries and aligns them to achieve query consistency.
• Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
  7 Jan 2025 1 repository listed
  This work presents Sa2VA, the first unified model for dense grounded understanding of both images and videos.
• DTOS: Dynamic Time Object Sensing with Large Multimodal Model
  1 Jan 2025 1 repository listed
  We identify three critical challenges: (C1) insufficient quantitative representation of textual numerical data, (C2) repetitive and degraded response templates for spatiotemporal referencing, and (C3) loss of visual…
• Referring Video Object Segmentation via Language-aligned Track Selection
  2 Dec 2024 1 repository listed
  Referring video object segmentation (RVOS) requires tracking and segmenting an object throughout a video according to a given natural language expression, demanding both complex motion understanding and the alignment of…
• SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation
  26 Nov 2024 1 repository listed
  Referring Video Object Segmentation (RVOS) relies on natural language expressions to segment an object in a video clip.
• HyperSeg: Towards Universal Visual Segmentation with Large Language Model
  26 Nov 2024 1 repository listed Syntology ran 7 of 17 samples · 10 unverified
  This paper aims to address universal segmentation for image and video perception with the strong reasoning ability empowered by Visual Large Language Models (VLLMs).
• One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos
  29 Sep 2024 1 repository listed Syntology ran 7 of 16 samples · 9 unverified
  We introduce VideoLISA, a video-based multimodal large language model designed to tackle the problem of language-instructed reasoning segmentation in videos.
• ActionVOS: Actions as Prompts for Video Object Segmentation
  10 Jul 2024 1 repository listed Syntology ran 14 of 15 samples · 1 unverified · 15 pointer-only (licence)
  Experimental results on VISOR dataset reveal that ActionVOS significantly reduces the mis-segmentation of inactive objects, confirming that actions help the ActionVOS model understand objects' involvement.
• 1st Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation
  11 Jun 2024 1 repository listed
  Motion Expression guided Video Segmentation (MeViS), as an emerging task, poses many new challenges to the field of referring video object segmentation (RVOS).
• Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding
  12 Apr 2024 1 repository listed
  The complexity of this task increases with the intricacy of the sentences provided.
• Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation
  4 Apr 2024 1 repository listed Syntology ran 2 of 7 samples · 5 unverified · 7 pointer-only (licence)
  In fact, static cues can sometimes interfere with temporal perception by overshadowing motion cues.
• Temporally Consistent Referring Video Object Segmentation with Hybrid Memory
  28 Mar 2024 1 repository listed Syntology ran 14 of 15 samples · 1 unverified
  Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other visually similar objects.
• Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation
  18 Mar 2024 1 repository listed Syntology ran 16 of 20 samples · 4 unverified · 20 pointer-only (licence)
  We hypothesize that the latent representation learned from a pretrained generative T2V model encapsulates rich semantics and coherent temporal correspondences, thereby naturally facilitating video understanding.
• UniVS: Unified and Universal Video Segmentation with Prompts as Queries
  28 Feb 2024 1 repository listed Syntology ran 12 of 14 samples · 2 unverified · 14 pointer-only (licence)
  Despite the recent advances in unified image segmentation (IS), developing a unified video segmentation (VS) model remains a challenge.
• 1st Place Solution for 5th LSVOS Challenge: Referring Video Object Segmentation
  1 Jan 2024 1 repository listed
  The recent transformer-based models have dominated the Referring Video Object Segmentation (RVOS) task due to the superior performance.
• Tracking with Human-Intent Reasoning
  29 Dec 2023 1 repository listed
  The perception component then generates the tracking results based on the embeddings.

Syntology lines on 12 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.