What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactions

Adnan Iftekhar, Hao Chen, Kaustav Kundu, Xinyu Li, Joseph Tighe, Davide Modolo

20222022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)51 citationsDOI

Abstract

We propose a novel one-stage Transformer-based semantic and spatial refined transformer (SSRT) to solve the Human-Object Interaction detection task, which requires to localize humans and objects, and predicts their interactions. Differently from previous Transformer-based HOI approaches, which mostly focus at improving the design of the decoder outputs for the final detection, SSRT introduces two new modules to help select the most relevant object-action pairs within an image and refine the queries' representation using rich semantic and spatial features. These enhancements lead to state-of-the-art results on the two most popular HOI benchmarks: V-COCO and HICO-DET.

Topics & Concepts

Computer scienceTransformerArtificial intelligenceObject detectionComputer visionPattern recognition (psychology)VoltageEngineeringElectrical engineeringMultimodal Machine Learning ApplicationsHuman Pose and Action RecognitionDomain Adaptation and Few-Shot Learning