`Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation

• URL: http://arxiv.org/abs/2607.07230v1
• Date: Wed, 08 Jul 2026 10:13:20 GMT
• Title: `Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation
• Abstract summary: Video object segmentation (VOS) is a fundamental task in video understanding, requiring accurate delineation and consistent tracking of objects across frames.<n>We propose a self-supervised framework, Cross-Temporal Consistency and Clustering, that learns part-aware representations by combining attention-guided token selection with lightweight temporal clustering.
• Score: 16.700937089524803
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video object segmentation (VOS) is a fundamental task in video understanding, requiring accurate delineation and consistent tracking of objects across frames. While supervised methods achieve strong performance, they rely on densely annotated datasets that are costly to obtain and have limited domain coverage. Self-supervised learning offers a promising alternative by removing the need for manual labels; however, existing approaches often struggle to jointly maintain spatial accuracy and temporal coherence, particularly in unconstrained multi-object scenarios. Many rely on optical flow, synthetic motion cues, or task-specific pretraining, limiting scalability and generalisation. We propose a self-supervised framework, Cross-Temporal Consistency and Clustering, that learns mid-level, part-aware representations by combining attention-guided token selection with lightweight temporal clustering. Instead of operating at the pixel or whole-object level, the method aligns soft part assignments across time using a saliency-weighted symmetric consistency objective. The framework leverages a frozen transformer backbone with lightweight modules for adaptive token selection and multi-offset temporal alignment, enabling efficient scaling across resolutions and motion patterns.

Related papers

• SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction [65.15449703659772]
  Video Object (VOS) is a core task in computer vision, requiring models to track and segment target objects across video frames.<n>We propose Segment Concept (SeC), a concept-driven segmentation framework that shifts from conventional feature matching to the progressive construction and utilization of high-level, object-centric representations.<n>SeC achieves an 11.8-point improvement over SAM SeCVOS, establishing a new state-of-the-art concept-aware video object segmentation.
  arXiv  Detail & Related papers  (2025-07-21T17:59:02Z)
• MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning [66.53533434848369]
  We propose a motion-guided self-learning framework that learns densely consistent representations.<n>We improve state-of-the-art by 1% to 6% on six image and video datasets and four evaluation benchmarks.
  arXiv  Detail & Related papers  (2025-06-10T11:20:32Z)
• SemanticFlow: A Self-Supervised Framework for Joint Scene Flow Prediction and Instance Segmentation in Dynamic Environments [10.303368447554591]
  This paper proposes a multi-task framework to simultaneously predict scene flow and instance segmentation of full-temporal point clouds.<n>The novelty of this work is threefold: 1) developing a coarse-to-fine prediction based multitask scheme, where an initial coarse segmentation of static backgrounds and dynamic objects is used to provide contextual information for refining motion and semantic information through a shared feature processing module; 2) developing a set of loss functions to enhance the performance of scene flow estimation and instance segmentation, while can help ensure spatial and temporal consistency of both static and dynamic objects within traffic scenes; 3) developing a self-supervised learning scheme, which utilizes coarse
  arXiv  Detail & Related papers  (2025-03-19T02:43:19Z)
• Learning Motion and Temporal Cues for Unsupervised Video Object Segmentation [49.113131249753714]
  We propose an efficient algorithm, termed MTNet, which concurrently exploits motion and temporal cues.<n> MTNet is devised by effectively merging appearance and motion features during the feature extraction process within encoders.<n>We employ a cascade of decoders all feature levels across all feature levels to optimally exploit the derived features.
  arXiv  Detail & Related papers  (2025-01-14T03:15:46Z)
• Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation [47.047267066525265]
  We introduce a novel approach that incorporates object-level contextual knowledge within images.<n>Our proposed approach achieves state-of-the-art performance with strong generalizability across diverse datasets.
  arXiv  Detail & Related papers  (2024-11-26T06:34:48Z)
• Spatial-Temporal Multi-level Association for Video Object Segmentation [89.32226483171047]
  This paper proposes spatial-temporal multi-level association, which jointly associates reference frame, test frame, and object features. Specifically, we construct a spatial-temporal multi-level feature association module to learn better target-aware features.
  arXiv  Detail & Related papers  (2024-04-09T12:44:34Z)
• Appearance-Based Refinement for Object-Centric Motion Segmentation [85.2426540999329]
  We introduce an appearance-based refinement method that leverages temporal consistency in video streams to correct inaccurate flow-based proposals. Our approach involves a sequence-level selection mechanism that identifies accurate flow-predicted masks as exemplars. Its performance is evaluated on multiple video segmentation benchmarks, including DAVIS, YouTube, SegTrackv2, and FBMS-59.
  arXiv  Detail & Related papers  (2023-12-18T18:59:51Z)
• Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation [76.68301884987348]
  We propose a simple yet effective approach for self-supervised video object segmentation (VOS) Our key insight is that the inherent structural dependencies present in DINO-pretrained Transformers can be leveraged to establish robust-temporal segmentation correspondences in videos. Our method demonstrates state-of-the-art performance across multiple unsupervised VOS benchmarks and excels in complex real-world multi-object video segmentation tasks.
  arXiv  Detail & Related papers  (2023-11-29T18:47:17Z)
• A Spatiotemporal Correspondence Approach to Unsupervised LiDAR Segmentation with Traffic Applications [16.260518238832887]
  Key idea is to leverage the nature of a dynamic point cloud sequence and introduce drastically stronger scenarios. We alternate between optimizing semantic into groups and clustering using point-wisetemporal labels. Our method can learn discriminative features in an unsupervised learning fashion.
  arXiv  Detail & Related papers  (2023-08-23T21:32:46Z)
• Unsupervised Spatio-temporal Latent Feature Clustering for Multiple-object Tracking and Segmentation [0.5591659577198183]
  We propose a strategy that treats the temporal identification task as a heterogeneous-temporal clustering problem. We use a convolutional and fully connected autoencoder to learn discriminative features from segmentation masks and detection bounding boxes. Our results show that our technique outperforms several state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-07-14T16:47:56Z)

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.