Spatial Relation Recognition

Multi-Modal Reading (MMR) Benchmark includes 550 annotated question-answer pairs across 11 distinct tasks involving texts, fonts, visual elements, bounding boxes, spatial relations, and grounding, with carefully designed evaluation metrics.

Understanding spatial relations (e.g., “laptop on table”) in visual input is important for both humans and robots. Existing datasets are insufficient as they lack largescale, high-quality 3D ground truth information, which is critical for learning spatial relations. In this paper, we fill this gap by constructing Rel3D: the first large-scale, human-annotated dataset for grounding spatial relations in 3D. Rel3D enables quantifying the effectiveness of 3D information in predicting spatial relations on large-scale human data. Moreover, we propose minimally contrastive data collection—a novel crowdsourcing method for reducing dataset bias. The 3D scenes in our dataset come in minimally contrastive pairs: two scenes in a pair are almost identical, but a spatial relation holds in one and fails in the other. We empirically validate that minimally contrastive examples can diagnose issues with current relation detection models as well as lead to sample-efficient training. Code and data are available at https://github.com/princeton-vl/Rel3D.

ReSQ is a real-world Spatial Question Answering dataset with human-generated questions built on an existing corpus with SpRL annotations. This dataset can be used to evaluate spatial language processing models in realistic situations.

SpatialSense Benchmark is a dataset specializing in spatial relation recognition which captures a broad spectrum of such challenges, allowing for proper benchmarking of computer vision techniques. Source: SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition

Green family of datasets for emergent communications on relations. By comparison with other relations datasets, TexRel provides rapid training and experimentation, whilst being sufficiently large to avoid overfitting in the context of emergent communications.