Human-Object Interaction Detection

94 papers with code • 5 benchmarks • 20 datasets

Human-Object Interaction (HOI) detection is a task of identifying "a set of interactions" in an image, which involves the i) localization of the subject (i.e., humans) and target (i.e., objects) of interaction, and ii) the classification of the interaction labels.

Libraries

Use these libraries to find Human-Object Interaction Detection models and implementations

Most implemented papers

iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection

vt-vl-lab/iCAN 30 Aug 2018

Our core idea is that the appearance of a person or an object instance contains informative cues on which relevant parts of an image to attend to for facilitating interaction prediction.

Visual Compositional Learning for Human-Object Interaction Detection

zhihou7/VCL ECCV 2020

The integration of decomposition and composition enables VCL to share object and verb features among different HOI samples and images, and to generate new interaction samples and new types of HOI, and thus largely alleviates the long-tail distribution problem and benefits low-shot or zero-shot HOI detection.

Temporal Relational Reasoning in Videos

metalbubble/TRN-pytorch ECCV 2018

Temporal relational reasoning, the ability to link meaningful transformations of objects or entities over time, is a fundamental property of intelligent species.

No-Frills Human-Object Interaction Detection: Factorization, Layout Encodings, and Training Techniques

BigRedT/no_frills_hoi_det ICCV 2019

We show that for human-object interaction detection a relatively simple factorized model with appearance and layout encodings constructed from pre-trained object detectors outperforms more sophisticated approaches.

Transferable Interactiveness Knowledge for Human-Object Interaction Detection

DirtyHarryLYL/Transferable-Interactiveness-Network CVPR 2019

On account of the generalization of interactiveness, interactiveness network is a transferable knowledge learner and can be cooperated with any HOI detection models to achieve desirable results.

Visual-Semantic Graph Attention Networks for Human-Object Interaction Detection

birlrobotics/vs-gats 7 Jan 2020

Few works have studied the disambiguating contribution of subsidiary relations made available via graph networks.

Contextual Action Recognition with R*CNN

gkioxari/RstarCNN ICCV 2015

In this work, we exploit the simple observation that actions are accompanied by contextual cues to build a strong action recognition system.

Detecting and Recognizing Human-Object Interactions

facebookresearch/detectron CVPR 2018

Our hypothesis is that the appearance of a person -- their pose, clothing, action -- is a powerful cue for localizing the objects they are interacting with.

HAKE: Human Activity Knowledge Engine

DirtyHarryLYL/HAKE-Action-Torch 13 Apr 2019

To address these and promote the activity understanding, we build a large-scale Human Activity Knowledge Engine (HAKE) based on the human body part states.

PaStaNet: Toward Human Activity Knowledge Engine

DirtyHarryLYL/HAKE-Action-Torch CVPR 2020

In light of this, we propose a new path: infer human part states first and then reason out the activities based on part-level semantics.