Grounded Situation Recognition with Transformers
Published in
British Machine Vision Conference(2021)External Links:
TL
TL;DR
The attention mechanism of the model enables accurate verb classification by capturing high-level semantic feature of an image effectively, and allows the model to flexibly deal with the complicated and image-dependent relations between entities for improved noun classification and localization.
Abstract
Grounded Situation Recognition (GSR) is the task that not only classifies a salient action (verb), but also predicts entities (nouns) associated with semantic roles and their locations in the given image. Inspired by the remarkable success of Transformers in vision tasks, we propose a GSR model based on a Transformer encoder-decoder architecture. The attention mechanism of our model enables accurate verb classification by capturing high-level semantic feature of an image effectively, and allows the model to flexibly deal with the complicated and image-dependent relations between entities for improved noun classification and localization. Our model is the first Transformer architecture for GSR, and achieves the state of the art in every evaluation metric on the SWiG benchmark. Our code is available at https://github.com/jhcho99/gsrtr .
References35 items
1
Temporal Query Networks for Fine-grained Video Understanding
2
Fully Convolutional Scene Graph Generation
3
End-to-End Human Object Interaction Detection with HOI Transformer
4
End-to-End Video Instance Segmentation with Transformers
5