mlsanityData to 7 Oct 2026

T-STAR: A Large-Scale Benchmark for Spatio-Temporal Panoptic Scene Graph Generation in Satellite Video

arXiv 2607.21228 ↗First posted 23 Jul 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Structured understanding of satellite video is essential for advancing dynamic geospatial scene analysis from low-level perception to high-level cognition. To move beyond object-centric perception, this paper introduces spatio-temporal panoptic scene graph generation (TPSG) in satellite video as a new benchmark task. TPSG aims to generate a structured graph composed of a set of triplets <subject, relationship, object> with explicit temporal spans, thereby describing dynamic geospatial scenes by jointly modeling identity-consistent instance masks and spatio-temporal relationships among panoptic scene elements. However, there is still no dedicated dataset for TPSG in satellite video. Moreover, TPSG in satellite video is intrinsically challenging, as objects are often small and weakly textured, cross-frame association is easily disrupted by occlusion and background clutter, and relationship semantics are highly coupled with spatial structure and temporal evolution. Consequently, TPSG models developed for natural videos are not directly applicable to satellite video. This paper presents T-STAR, a large-scale benchmark dataset for TPSG in satellite video, comprising over 1.1 million instance masks and over 3.8 million spatio-temporal triplets across 39 fine-grained object categories and 70 fine-grained relationship categories. To enable TPSG in satellite video, we propose a unified framework to enhance cross-frame instance consistency and spatio-temporal relationship prediction. Extensive experiments demonstrate the significance of T-STAR and the effectiveness of the proposed framework, establishing a strong benchmark for future research on structured satellite video understanding. The dataset and code are available at https://github.com/linlin-dev/T-STAR.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 69 references that are in the map. First posted on arXiv 23 Jul 2026.

Builds on

37 of 69 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  3. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  4. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  5. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 413
  6. 2020Unbiased Scene Graph Generation from Biased Trainingcited by 355
  7. 2016Visual Relationship Detection with Language Priorscited by 333
  8. 2018Auto-Encoding Scene Graphs for Image Captioningcited by 254
  9. 2019Action Genome: Actions as Composition of Spatio-temporal Scene Graphscited by 249
  10. 2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
  11. 2021A Comprehensive Survey of Scene Graphs: Generation and Applicationcited by 125
  12. 2019Relation-Aware Graph Attention Network for Visual Question Answeringcited by 119
25 more
  1. 2022Panoptic Scene Graph Generationcited by 114
  2. 2017Detecting Visual Relationships with Deep Relational Networkscited by 97
  3. 2021Spatial-Temporal Transformer for Dynamic Scene Graph Generationcited by 95
  4. 2020Bridging Knowledge Graphs to Generate Scene Graphscited by 86
  5. 2018Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generationcited by 78
  6. 2020Using satellite imagery to understand and promote sustainable developmentcited by 71
  7. 2022Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generationcited by 67
  8. 2017Visual Relationship Detection with Internal and External Linguistic Knowledge Distillationcited by 60
  9. 2023Panoptic Video Scene Graph Generationcited by 46
  10. 2023Unbiased Scene Graph Generation in Videoscited by 38
  11. 2024STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagerycited by 31
  12. 2024OED: Towards One-stage End-to-End Dynamic Scene Graph Generationcited by 22
  13. 2023Unbiased Scene Graph Generation via Two-stage Causal Modelingcited by 21
  14. 2022Meta Spatio-Temporal Debiasing for Video Scene Graph Generationcited by 20
  15. 2021Detecting and Tracking Small and Dense Moving Objects in Satellite Videos: A Benchmarkcited by 17
  16. 2025A Causal Adjustment Module for Debiasing Scene Graph Generationcited by 14
  17. 2024CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videoscited by 11
  18. 2023Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generationcited by 10
  19. 2025DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generationcited by 10
  20. 2024Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generationcited by 9
  21. 2024Vehicle Perception from Satellitecited by 7
  22. 2024Highly Efficient and Unsupervised Framework for Moving Object Detection in Satellite Videoscited by 7
  23. 2025Unbiased Video Scene Graph Generation via Visual and Semantic Dual Debiasingcited by 6
  24. 2024ReCon1M:A Large-scale Benchmark Dataset for Relation Comprehension in Remote Sensing Imagerycited by 3
  25. 2024Fine-Grained Scene Graph Generation via Sample-Level Bias Predictioncited by 1

Built on by

Not cited yet.