Transferable Interactiveness Knowledge for Human-Object Interaction Detection

Abstract

Human-Object Interaction (HOI) detection is an important problem to understand how humans interact with objects. In this paper, we explore interactiveness knowledge which indicates whether a human and an object interact with each other or not. We found that interactiveness knowledge can be learned across HOI datasets and bridge the gap between diverse HOI category settings. Our core idea is to exploit an interactiveness network to learn the general interactiveness knowledge from multiple HOI datasets and perform Non-Interaction Suppression (NIS) before HOI classification in inference. On account of the generalization ability of interactiveness, interactiveness network is a transferable knowledge learner and can be cooperated with any HOI detection models to achieve desirable results. We utilize the human instance and body part features together to learn the interactiveness in hierarchical paradigm, i.e., instance-level and body part-level interactivenesses. Thereafter, a consistency task is proposed to guide the learning and extract deeper interactive visual clues. We extensively evaluate the proposed method on HICO-DET, V-COCO, and a newly constructed PaStaNet-HOI dataset. With the learned interactiveness, our method outperforms state-of-the-art HOI detection methods, verifying its efficacy and flexibility. Code is available at https://github.com/DirtyHarryLYL/Transferable-Interactiveness-Network.

TPAMI version of our CVPR2019 paper with a new benchmark PaStaNet-HOI. Code: https://github.com/DirtyHarryLYL/Transferable-Interactiveness-Network. arXiv admin note: substantial text overlap with arXiv:1811.08264

References in corpus (14)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Semi-Supervised Classification with Graph Convolutional Networks
• The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
• Visual Semantic Role Labeling
• Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
• iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection
• HOI Analysis: Integrating and Decomposing Human-Object Interaction
• CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark
• Care about you: towards large-scale human-centric visual relationship detection
• Detailed 2D-3D Joint Representation for Human-Object Interaction
• Object Relation Detection Based on One-shot Learning
• PaStaNet: Toward Human Activity Knowledge Engine
• Beyond Holistic Object Recognition: Enriching Image Understanding with Part States
• Deep RNN Framework for Visual Sequential Applications

Cited by in corpus (7)

• HAKE: Human Activity Knowledge Engine
• Pose-aware Multi-level Feature Network for Human Object Interaction Detection
• Visual Compositional Learning for Human-Object Interaction Detection
• Contextual Heterogeneous Graph Network for Human-Object Interaction Detection
• HOI-aware Adaptive Network for Weakly-supervised Action Segmentation
• Novel Human-Object Interaction Detection via Adversarial Domain Generalization
• GID-Net: Detecting Human-Object Interaction with Global and Instance Dependency