2026/02/18 by Chuhan Li, Ruilin Han, Rilyn Han +6 · 1 voice
Computer Science · Psychology · #Benchmark (surveying) #Bridge (graph theory) #Exploit #Foundation (evidence) #Human Pose and Action Recognition #Multimodal Machine Learning Applications #Perception #Situated #Situated learning #Social Robot Interaction and HRI #Spatial intelligence #cs.CV
paper · pdf · doi:10.48550/arxiv.2602.16682
openalex publication_date 2026/02/18 · arxiv published 2026/02/18 · openalex created_date 2026/02/20 · arxiv updated 2026/05/28 · openalex updated_date 2026/07/28
A core aspect of human perception is situated awareness, the ability to relate ourselves to the surrounding physical environment and reason over possible actions in context. However, most existing benchmarks for multimodal foundation models (MFMs) emphasize environment-centric spatial relations (relations among objects in a scene), while largely overlooking observer-centric relationships that require reasoning relative to agent's viewpoint, pose, and motion. To bridge this gap, we introduce SAW-Bench (Situated Awareness in the Real World), a novel benchmark for evaluating egocentric situated awareness using real-world videos. SAW-Bench comprises 786 self-recorded videos captured with Ray-Ban Meta (Gen 2) smart glasses spanning diverse indoor and outdoor environments, and over 2,071 human-annotated question-answer pairs. It probes a model's observer-centric understanding with six different awareness tasks. Our comprehensive evaluation reveals a human-model performance gap of 37.66%, even with the best-performing MFM, Gemini 3 Flash. Beyond this gap, our in-depth analysis uncovers several notable findings; for example, while models can exploit partial geometric cues in egocentric videos, they often fail to infer a coherent camera geometry, leading to systematic spatial reasoning errors. We position SAW-Bench as a benchmark for situated spatial intelligence, moving beyond passive observation to understanding physically grounded, observer-centric dynamics.