Spot The Ball：视觉社会推理基准
Spot The Ball: A Benchmark for Visual Social Inference
AI总结：
该研究针对视觉社会推理能力，引入Spot The Ball基准，以体育领域图像中定位被移除的球为任务，评估VLMs性能，发现人类准确率远高于模型，揭示了人类-模型差距并强调编码行为线索的重要性。
摘要：
人类擅长视觉社会推理，即从他人的凝视、姿势和朝向等细微行为线索中推断场景隐藏元素的能力。这种能力推动人类日常社会推理，对开发更类人AI智能体至关重要。我们引入Spot The Ball，这是一个挑战性基准，以体育为测试领域评估视觉-语言模型（VLMs）的视觉社会推理能力。任务是从足球、篮球和排球图像中定位被移除的运动球。我们提出包含人类基线的精选评估集和生成额外测试项的可扩展管道。我们使用三种提示策略评估四个最先进VLMs（Gemini、GPT、LLaMA、Qwen），发现人类在所有运动项目中的准确率始终是模型的2到3倍（20-34% vs ≤17%）。我们的分析表明，模型依赖表面空间启发式（如猜测图像中心或附近球员），而人类利用凝视方向和身体姿势等社会线索。这些发现揭示了视觉社会推理中持续存在的人类-模型差距，并强调需要明确编码结构化行为线索的架构以实现稳健、类人的推理。
英文摘要：
Humans excel at visual social inference, the ability to infer hidden elements of a scene from subtle behavioral cues such as other people's gaze, pose, and orientation. This ability drives everyday social reasoning in humans and is critical for developing more human-like AI agents. We introduce Spot The Ball, a challenging benchmark for evaluating visual social inference in vision-language models (VLMs) using sports as a test domain. The task is to localize a removed sports ball from soccer, basketball, and volleyball images. We present a curated evaluation set with human baselines and a scalable pipeline for generating additional test items. We evaluate four state-of-the-art VLMs (Gemini, GPT, LLaMA, Qwen) using three prompting strategies, finding that humans are consistently two to three times more accurate (20-34%) than models ($\leq$ 17%) across all sports. Our analyses show that models rely on superficial spatial heuristics--such as guessing near the image center or nearby players--while humans leverage social cues like gaze direction and body pose. These findings reveal a persistent human-model gap in visual social reasoning and underscore the need for architectures that explicitly encode structured behavioral cues to achieve robust, human-like inference.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
