We propose Subject-Conditional Relation Detection SCoRD, where conditioned on an input subject, the goal is to predict all its relations to other objects in a scene along with their locations. Based on the Open Images dataset, we propose a challenging OIv6-SCoRD benchmark such that the training and testing splits have a distribution shift in terms of the occurrence statistics of $\langle$subject, relation, object$\rangle$ triplets. To solve this problem, we propose an auto-regressive model that given a subject, it predicts its relations, objects, and object locations by casting this output as a sequence of tokens. First, we show that previous scene-graph prediction methods fail to produce as exhaustive an enumeration of relation-object pairs when conditioned on a subject on this benchmark. Particularly, we obtain a recall@3 of 83.8% for our relation-object predictions compared to the 49.75% obtained by a recent scene graph detector. Then, we show improved generalization on both relation-object and object-box predictions by leveraging during training relation-object pairs obtained automatically from textual captions and for which no object-box annotations are available. Particularly, for $\langle$subject, relation, object$\rangle$ triplets for which no object locations are available during training, we are able to obtain a recall@3 of 42.59% for relation-object pairs and 32.27% for their box locations.

翻译：本文提出主题条件关系检测方法SCoRD，其目标是在给定输入主题的条件下，预测场景中该主题与所有其他对象之间的关系及其位置。基于Open Images数据集，我们构建了具有挑战性的OIv6-SCoRD基准，使得训练集和测试集在<主体，关系，对象>三元组出现统计分布上存在偏移。为解决该问题，我们提出自回归模型：给定主题后，通过将输出编码为标记序列，预测其关系、对象及对象位置。首先，我们发现在该基准上，现有场景图预测方法无法在约束主题条件下穷尽枚举关系-对象对。具体而言，我们的关系-对象预测召回率@3达到83.8%，而近期场景图检测器仅为49.75%。其次，通过利用从文本描述自动获取且无对象框标注的关系-对象对进行训练，我们证明了模型在关系-对象和对象框预测上的泛化能力提升。特别地，对于训练阶段未提供对象位置的<主体，关系，对象>三元组，我们仍能对关系-对象对获得42.59%的召回率@3，对其框位置获得32.27%的召回率。