Show Me When and Where: Towards Referring Video Object Segmentation in the Wild

• URL: http://arxiv.org/abs/2603.14300v1
• Date: Sun, 15 Mar 2026 09:30:33 GMT
• Title: Show Me When and Where: Towards Referring Video Object Segmentation in the Wild
• Abstract summary: In this work, we introduce a new setting towards in-the-wild RVOS.<n>Our new benchmark challenges RVOS methods to show not only where but also when objects appear in videos.<n>Our YoURVOS dataset offers an imperative benchmark, which will push forward the advancement of RVOS methods for practical applications.
• Score: 98.87931411432106
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Referring video object segmentation (RVOS) has recently generated great popularity in computer vision due to its widespread applications. Existing RVOS setting contains elaborately trimmed videos, with text-referred objects always appearing in all frames, which however fail to fully reflect the realistic challenges of this task. This simplified setting requires RVOS methods to only predict where objects, with no need to show when the objects appear. In this work, we introduce a new setting towards in-the-wild RVOS. To this end, we collect a new benchmark dataset using Youtube Untrimmed videos for RVOS - YoURVOS, which contains 1,120 in-the-wild videos with 7 times more duration and scenes than existing datasets. Our new benchmark challenges RVOS methods to show not only where but also when objects appear in videos. To set a baseline, we propose Object-level Multimodal TransFormers (OMFormer) to tackle the challenges, which are characterized by encoding object-level multimodal interactions for efficient and global spatial-temporal localisation. We demonstrate that previous VOS methods struggle on our YoURVOS benchmark, especially with the increase of target-absent frames, while our OMFormer consistently performs well. Our YoURVOS dataset offers an imperative benchmark, which will push forward the advancement of RVOS methods for practical applications.

Related papers

• HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback [0.0]
  We introduce HQ-SMem, for High Quality video segmentation and tracking using Smart Memory.<n>Our approach incorporates three key innovations: (i) leveraging SAM with High-Quality masks (SAM-HQ) alongside appearance-based candidate-selection to refine coarse segmentation masks, resulting in improved object boundaries; (ii) implementing a dynamic smart memory mechanism that selectively stores relevant key frames while discarding redundant ones; and (iii) dynamically updating the appearance model to effectively handle complex topological object variations and reduce drift throughout the video.
  arXiv  Detail & Related papers  (2025-07-25T03:28:05Z)
• Long-RVOS: A Comprehensive Benchmark for Long-term Referring Video Object Segmentation [51.2732688481343]
  We introduce Longtextbf-RVOS, a large-scale benchmark for long-term referring object segmentation.<n>Long-RVOS contains 2,000+ videos of an average duration exceeding 60 seconds, covering a variety of objects.<n>Unlike previous benchmarks that rely solely on the per-frame spatial evaluation, we introduce two metrics to assess the temporal andtemporal consistency.
  arXiv  Detail & Related papers  (2025-05-19T04:52:31Z)
• 4th PVUW MeViS 3rd Place Report: Sa2VA [105.88675577642204]
  We show that with a simple modification to the test time inference method on stronger MLLMs, we can lead to stronger results on MeVIS.<n>In particular, we adopt the recent method Sa2VA, a unified model for dense grounded understanding of both images and videos.
  arXiv  Detail & Related papers  (2025-04-01T07:06:47Z)
• LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation [29.07092353094942]
  Video object segmentation (VOS) aims to distinguish and track target objects in a video. Existing benchmarks mainly focus on short-term videos, where objects remain visible most of the time. We propose a novel benchmark named LVOS, comprising 720 videos with 296,401 frames and 407,945 high-quality annotations. Videos in LVOS last 1.14 minutes on average, approximately 5 times longer than videos in existing datasets.
  arXiv  Detail & Related papers  (2024-04-30T07:50:29Z)
• MOSE: A New Dataset for Video Object Segmentation in Complex Scenes [106.64327718262764]
  Video object segmentation (VOS) aims at segmenting a particular object throughout the entire video clip sequence. The state-of-the-art VOS methods have achieved excellent performance (e.g., 90+% J&F) on existing datasets. We collect a new VOS dataset called coMplex video Object SEgmentation (MOSE) to study the tracking and segmenting objects in complex environments.
  arXiv  Detail & Related papers  (2023-02-03T17:20:03Z)
• LVOS: A Benchmark for Long-term Video Object Segmentation [31.76468328063721]
  We present a new benchmark dataset named textbfLVOS, which consists of 220 videos with a total duration of 421 minutes. The videos in our LVOS last 1.59 minutes on average, which is 20 times longer than videos in existing VOS datasets. We propose a Diverse Dynamic Memory network (DDMemory) that consists of three complementary memory banks to exploit temporal information adequately.
  arXiv  Detail & Related papers  (2022-11-18T11:59:37Z)
• Region Aware Video Object Segmentation with Deep Motion Modeling [56.95836951559529]
  Region Aware Video Object (RAVOS) is a method that predicts regions of interest for efficient object segmentation and memory storage. For efficient segmentation, object features are extracted according to the ROIs, and an object decoder is designed for object-level segmentation. For efficient memory storage, we propose motion path memory to filter out redundant context by memorizing the features within the motion path of objects between two frames.
  arXiv  Detail & Related papers  (2022-07-21T01:44:40Z)
• Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation [140.4291169276062]
  Referring video object segmentation (RVOS) aims to segment video objects with the guidance of natural language reference. Previous methods typically tackle RVOS through directly grounding linguistic reference over the image lattice. In this work, we put forward a two-stage, top-down RVOS solution. First, an exhaustive set of object tracklets is constructed by propagating object masks detected from several sampled frames to the entire video. Second, a Transformer-based tracklet-language grounding module is proposed, which models instance-level visual relations and cross-modal interactions simultaneously and efficiently.
  arXiv  Detail & Related papers  (2021-06-02T10:26:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.