ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding

• URL: http://arxiv.org/abs/2607.13421v1
• Date: Wed, 15 Jul 2026 03:50:22 GMT
• Title: ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding
• Abstract summary: S-Temporal Video Grounding aims to retrieve the visual trajectory of a specific object from a video stream as described by a natural language expression.<n>Most advanced methods struggle to balance global context modeling with precise boundary localization.<n>We present a novel coarse-to-fine framework that decouples the STVG task into a global-temporal scan and a local boundary focus.
• Score: 23.883675818190188
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spatio-Temporal Video Grounding (STVG) aims to retrieve the visual trajectory of a specific object from a video stream as described by a natural language expression. However, most advanced methods struggle to balance global context modeling with precise boundary localization. Due to the prohibitive computational costs of processing long videos, these approaches typically resort to low-rate temporal downsampling and implicit motion modeling. This inevitably suppresses high-frequency boundary cues and neglects the explicit inter-frame dependencies required for precise boundary delineation. To address these limitations, we present \textbf{ScanFocus}, a novel coarse-to-fine framework that decouples the STVG task into a global spatio-temporal scan and a local boundary focus. Specifically, we utilize a unified vision-language fusion encoder combined with a lightweight Deformable Semantic-Motion Fusion module to efficiently align multimodal features and generate coarse proposals. To recover the suppressed fine-grained details, we introduce the Semantic-Guided Temporal Aggregator (SGTA) in the refinement stage. By densely sampling around coarse boundaries, SGTA explicitly models short-term temporal interactions under semantic guidance, capturing rapid motion changes for precise timestamp regression. Extensive experiments on three widely used benchmarks demonstrate the performance superiority of our proposed method over previous approaches. Code will be released at https://github.com/TenMinutes209/ScanFocus.

Related papers

• Efficient Spatio-Temporal Grounding with Multimodal Large Models via Second-Level Tracking and RL Verification [11.171207895220578]
  temporal-temporal grounding in long videos requires precise temporal localization and robust object tracking conditioned on natural-language queries.<n>We propose a practical pipeline that shifts from frame-level to second-level tracking and performs cross-second annotations to preserve continuity while reducing sequence length.
  arXiv  Detail & Related papers  (2026-06-27T17:42:32Z)
• RAFT-MSF++: Temporal Geometry-Motion Feature Fusion for Self-Supervised Monocular Scene Flow [51.43025173196566]
  Monocular scene flow estimation aims to recover dense 3D motion from image sequences.<n>We propose RAFT-MSF++, a self-supervised multi-frame framework that fuses temporal features to jointly estimate depth and scene flow.<n>Experiments show that RAFT-MSF++ achieves 24.14% SF-all on the KITTI Scene Flow benchmark, with a 30.99% improvement over the baseline and better robustness in occluded regions.
  arXiv  Detail & Related papers  (2026-04-21T11:32:49Z)
• MomentSeg: Moment-Centric Sampling for Enhanced Video Pixel Understanding [40.37010049965347]
  Referring Video Object (RefVOS) seeks to segment target objects in videos guided by natural language descriptions.<n>We propose a unified framework that jointly optimize Temporal Sentence Grounding (TSG) and RefVOS, naturally incorporating key moment grounding capability.
  arXiv  Detail & Related papers  (2025-10-10T11:18:21Z)
• Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion [57.232688209606515]
  We present HTCL, a novel Temporal Temporal Context Learning paradigm for improving camera-based semantic scene completion. Our method ranks $1st$ on the Semantic KITTI benchmark and even surpasses LiDAR-based methods in terms of mIoU.
  arXiv  Detail & Related papers  (2024-07-02T09:11:17Z)
• Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression [59.632286735304156]
  We propose a spatial decomposition and temporal fusion based inter prediction for learned video compression. With the SDD-based motion model and long short-term temporal fusion, our proposed learned video can obtain more accurate inter prediction contexts.
  arXiv  Detail & Related papers  (2024-01-29T03:30:21Z)
• EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model [63.93372634950661]
  We propose a new perspective that maintains the integrity of the original temporal content while introducing more valuable information for expanding the incomplete boundaries. Motivated by video continuity, i.e., visual similarity across adjacent frames, we use powerful multimodal large language models (MLLMs) to annotate each frame within initial pseudo boundaries.
  arXiv  Detail & Related papers  (2023-12-05T04:15:56Z)
• Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding [35.73830796500975]
  We present an end-to-end one-stage framework, termed Spatio-Temporal Consistency-Aware Transformer (STCAT) To generate the above template under sufficient video- perception, an encoder-decoder architecture is proposed for effective global context modeling. Our method outperforms previous state-of-the-arts with clear margins on two challenging video benchmarks.
  arXiv  Detail & Related papers  (2022-09-27T11:13:04Z)
• Video Activity Localisation with Uncertainties in Temporal Boundary [74.7263952414899]
  Methods for video activity localisation over time assume implicitly that activity temporal boundaries are determined and precise. In unscripted natural videos, different activities transit smoothly, so that it is intrinsically ambiguous to determine in labelling precisely when an activity starts and ends over time. We introduce Elastic Moment Bounding (EMB) to accommodate flexible and adaptive activity temporal boundaries.
  arXiv  Detail & Related papers  (2022-06-26T16:45:56Z)
• Temporal Context Aggregation Network for Temporal Action Proposal Refinement [93.03730692520999]
  Temporal action proposal generation is a challenging yet important task in the video understanding field. Current methods still suffer from inaccurate temporal boundaries and inferior confidence used for retrieval. We propose TCANet to generate high-quality action proposals through "local and global" temporal context aggregation.
  arXiv  Detail & Related papers  (2021-03-24T12:34:49Z)
• Learning Salient Boundary Feature for Anchor-free Temporal Action Localization [81.55295042558409]
  Temporal action localization is an important yet challenging task in video understanding. We propose the first purely anchor-free temporal localization method. Our model includes (i) an end-to-end trainable basic predictor, (ii) a saliency-based refinement module, and (iii) several consistency constraints.
  arXiv  Detail & Related papers  (2021-03-24T12:28:32Z)

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.