mlsanityData to 14 Oct 2026

SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition

arXiv 1908.02660 ↗First posted 7 Aug 2019cs.CVcited by 55

Not on the map. Why?

Abstract (arXiv)

Understanding the spatial relations between objects in images is a surprisingly challenging task. A chair may be "behind" a person even if it appears to the left of the person in the image (depending on which way the person is facing). Two students that appear close to each other in the image may not in fact be "next to" each other if there is a third student between them. We introduce SpatialSense, a dataset specializing in spatial relation recognition which captures a broad spectrum of such challenges, allowing for proper benchmarking of computer vision techniques. SpatialSense is constructed through adversarial crowdsourcing, in which human annotators are tasked with finding spatial relations that are difficult to predict using simple cues such as 2D spatial configuration or language priors. Adversarial crowdsourcing significantly reduces dataset bias and samples more interesting relations in the long tail compared to existing datasets. On SpatialSense, state-of-the-art recognition models perform comparably to simple baselines, suggesting that they rely on straightforward cues instead of fully reasoning about this complex task. The SpatialSense benchmark provides a path forward to advancing the spatial reasoning capabilities of computer vision systems. The dataset and code are available at https://github.com/princeton-vl/SpatialSense.

Key facts. Cited by 55 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 5; 2024: 9; 2025: 14; 2026: 19.

55 papers.

Sort:

By area:

  1. 2024SAT: Dynamic Spatial Aptitude Training for Multimodal Language Modelscited by 114
  2. 2025Baichuan-Omni-1.5 Technical Reportcited by 111
  3. 2022Scene Graph Generation: A Comprehensive Surveycited by 73
  4. 2025MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMscited by 73
  5. 2024Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Modelscited by 54
  6. 2025FineVision: Open Data Is All You Needcited by 53
  7. 2021Finding and Fixing Spurious Patterns with Explanationscited by 38
  8. 2026LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decodingcited by 28
  9. 2025SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Modelscited by 25
  10. 2025SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligencecited by 24
  11. 2025Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluationcited by 24
  12. 2024FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehensioncited by 20
38 more
  1. 2025Can Multimodal Large Language Models Understand Spatial Relations?cited by 20
  2. 2025T5Gemma 2: Seeing, Reading, and Understanding Longercited by 17
  3. 2023Generating Visual Spatial Description via Holistic 3D Scene Understandingcited by 16
  4. 2023Evaluation and Enhancement of Semantic Grounding in Large Vision-Language Modelscited by 13
  5. 2025FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representationscited by 13
  6. 2025Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal Assistantscited by 12
  7. 2024Can Transformers Capture Spatial Relations between Objects?cited by 11
  8. 2022What is Right for Me is Not Yet Right for You: A Dataset for Grounding Relative Directions via Multi-Task Learningcited by 10
  9. 2022AGRO: Adversarial Discovery of Error-prone groups for Robust Optimizationcited by 10
  10. 2023Adaptive Visual Scene Understanding: Incremental Scene Graph Generationcited by 8
  11. 2024In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Modelscited by 8
  12. 2025LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sightcited by 8
  13. 20212.5D Visual Relationship Detectioncited by 7
  14. 2025Mitigating Hallucinations in Multimodal Spatial Relations through Constraint-Aware Promptingcited by 7
  15. 2022Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generationcited by 6
  16. 2023VisionKG: Unleashing the Power of Visual Datasets via Knowledge Graphcited by 5
  17. 2023STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoningcited by 3
  18. 2024Q-GroundCAM: Quantifying Grounding in Vision Language Models via GradCAMcited by 3
  19. 2024ReCon1M:A Large-scale Benchmark Dataset for Relation Comprehension in Remote Sensing Imagerycited by 3
  20. 2025Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neurosciencecited by 3
  21. 2026Transferability Between Understanding and Generation in Unified Multimodal Modelscited by 3
  22. 2024Structured Spatial Reasoning with Open Vocabulary Object Detectorscited by 2
  23. 2026NoReGeo: Non-Reasoning Geometry Benchmarkcited by 2
  24. 2026SATURN: Symbolic Spatial Reasoning for Multi-Perspective Groundingcited by 2
  25. 2026ReSTI: A Source-Grounded Audit and Repair of STI-Benchcited by 2
  26. 2024Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Imagecited by 1
  27. 2026Learning to Perceive "Where": Spatial Pretext Tasks for Robust Self-Supervised Learningcited by 1
  28. 2026PhysScene: A Scene Graph Dataset for Scientific Visual Reasoning in Physics Experimentscited by 1
  29. 2026SEER: A Self-Grounded Evidence Interface for Controlled Spatial Relation Classificationcited by 1
  30. 2026StateSight: Benchmarking Latent Spatial-State Reconstruction in Vision-Language Modelscited by 1
  31. 2021Commonsense Spatial Reasoning for Visually Intelligent Agentscited by 0
  32. 2022Neuro-Symbolic Spatio-Temporal Reasoningcited by 0
  33. 2025Omni Geometry Representation Learning vs Large Language Models for Geospatial Entity Resolutioncited by 0
  34. 2026MentalBlackboard: Evaluating Spatial Visualization via Mathematical Transformationscited by 0
  35. 2026Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystemscited by 0
  36. 2026Multi-hop Relational Contrastive Learning: Extending Spatial Contrastive Pre-training Beyond Pairwise Relationscited by 0
  37. 2026EmbodimentSemantic: A Spatial Scene-Graph Dataset and Benchmark for Vision-Language Models on Embodied Manipulation Trajectoriescited by 0
  38. 2026Modeling Scientific Experiment Scenes: Dataset and Modelcited by 0

50 most cited of 55 All 55 (JSON)