Cascaded Human-Object Interaction Recognition
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4262-4271
Abstract
Rapid progress has been witnessed for human-object interaction (HOI) recognition, but most existing models are confined to single-stage reasoning pipelines. Considering the intrinsic complexity of the task, we introduce a cascade architecture for a multi-stage, coarse-to-fine HOI understanding. At each stage, an instance localization network progressively refines HOI proposals and feeds them into an interaction recognition network. Each of the two networks is also connected to its predecessor at the previous stage, enabling cross-stage information propagation. The interaction recognition network has two crucial parts: a relation ranking module for high-quality HOI proposal selection and a triple-stream classifier for relation prediction. With our carefully-designed human-centric relation features, these two modules work collaboratively towards effective interaction understanding. Further beyond relation detection on a bounding-box level, we make our framework flexible to perform fine-grained pixel-wise relation segmentation; this provides a new glimpse into better relation modeling. Our approach reached the $1^{st}$ place in the ICCV2019 Person in Context Challenge, on both relation detection and segmentation tasks. It also shows promising results on V-COCO.
Keywords
All Related Versions
This publication has 41 references indexed in Scilit:
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Deep Residual Learning for Image Recognition2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Fast R-CNN2015
- Detecting Actions, Poses, and Objects with Relational Phraselets2012
- Observing Human-Object Interactions: Using Spatial and Functional Compatibility for RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Objects in Action: An Approach for Combining Action Understanding and Object Perception2007
- Efficient Belief Propagation for Early VisionInternational Journal of Computer Vision, 2006
- Gaze and eye contact: A research review.Psychological Bulletin, 1986
- Optimization by Simulated AnnealingScience, 1983