TY - JOUR AU - Yu, Fei AU - Tang, Jiji AU - Yin, Weichong AU - Sun, Yu AU - Tian, Hao AU - Wu, Hua AU - Wang, Haifeng PY - 2021/05/18 Y2 - 2024/03/29 TI - ERNIE-ViL: Knowledge Enhanced Vision-Language Representations through Scene Graphs JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 35 IS - 4 SE - AAAI Technical Track on Computer Vision III DO - 10.1609/aaai.v35i4.16431 UR - https://ojs.aaai.org/index.php/AAAI/article/view/16431 SP - 3208-3216 AB - We propose a knowledge-enhanced approach, ERNIE-ViL, which incorporates structured knowledge obtained from scene graphs to learn joint representations of vision-language. ERNIE-ViL tries to build the detailed semantic connections (objects, attributes of objects and relationships between objects) across vision and language, which are essential to vision-language cross-modal tasks. Utilizing scene graphs of visual scenes, ERNIE-ViL constructs Scene Graph Prediction tasks, i.e., Object Prediction, Attribute Prediction and Relationship Prediction tasks in the pre-training phase. Specifically, these prediction tasks are implemented by predicting nodes of different types in the scene graph parsed from the sentence. Thus, ERNIE-ViL can learn the joint representations characterizing the alignments of the detailed semantics across vision and language. After pre-training on large scale image-text aligned datasets, we validate the effectiveness of ERNIE-ViL on 5 cross-modal downstream tasks. ERNIE-ViL achieves state-of-the-art performances on all these tasks and ranks the first place on the VCR leaderboard with an absolute improvement of 3.7%. ER -