SOTAVerified

Human-Object Interaction Detection

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 449 papers

TitleStatusHype
RoHOI: Robustness Benchmark for Human-Object Interaction DetectionCode0
Bilateral Collaboration with Large Vision-Language Models for Open Vocabulary Human-Object Interaction DetectionCode0
VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and CollisionsCode2
HOIverse: A Synthetic Scene Graph Dataset With Human Object Interactions—0
On the Robustness of Human-Object Interaction Detection against Distribution Shift—0
Egocentric Human-Object Interaction Detection: A New Benchmark and Method—0
InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions—0
HunyuanVideo-HOMA: Generic Human-Object Interaction in Multimodal Driven Human Animation—0
HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance—0
Zero-Shot Temporal Interaction Localization for Egocentric VideosCode1
Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videos—0
Multiverse Through Deepfakes: The MultiFakeVerse Dataset of Person-Centric Visual and Conceptual ManipulationsCode0
Hi-Dyna Graph: Hierarchical Dynamic Scene Graph for Robotic Autonomy in Human-Centric Environments—0
InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing—0
Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic PriorsCode1
Locality-Aware Zero-Shot Human-Object Interaction DetectionCode1
MaskedManipulator: Versatile Whole-Body Control for Loco-Manipulation—0
UniHM: Universal Human Motion Generation with Object Interactions in Indoor Scenes—0
ViSA-Flow: Accelerating Robot Skill Learning via Large-Scale Video Semantic Action Flow—0
Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration—0
Generalized Visual Relation Detection with Diffusion Models—0
HUMOTO: A 4D Dataset of Mocap Human Object Interactions—0
HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation—0
Efficient Explicit Joint-level Interaction Modeling with Mamba for Text-guided HOI GenerationCode0
ForcePose: A Deep Learning Approach for Force Calculation Based on Action Recognition Using MediaPipe Pose Estimation Combined with Object Detection—0
Guiding Human-Object Interactions with Rich Geometry and Relations—0
Zero-Shot Human-Object Interaction Synthesis with Multimodal Priors—0
Target-Aware Video Diffusion Models—0
Human-Object Interaction with Vision-Language Model Guided Relative Movement Dynamics—0
An Image-like Diffusion Method for Human-Object Interaction Detection—0
Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model—0
Auto-Regressive Diffusion for Generating 3D Human-Object InteractionsCode1
Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions—0
3D Human Interaction Generation: A Survey—0
Hoi2Anomaly: An Explainable Anomaly Detection Approach Guided by Human-Object Interaction—0
GASPACHO: Gaussian Splatting for Controllable Humans and Objects—0
InteractEdit: Zero-Shot Editing of Human-Object Interactions in Images—0
End-to-End HOI Reconstruction Transformer with Graph-based Encoding—0
From Infants to AI: Incorporating Infant-like Learning in Models Boosts Efficiency and Generalization in Learning Social Prediction Tasks—0
SGC-Net: Stratified Granular Comparison Network for Open-Vocabulary HOI DetectionCode1
EigenActor: Variant Body-Object Interaction Generation Evolved from Invariant Action Basis Reasoning—0
3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds—0
InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object InteractionsCode3
Human Motion Prediction, Reconstruction, and Generation—0
RHINO: Learning Real-Time Humanoid-Human-Object Interaction from Human Demonstrations—0
DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human ReferencesCode2
Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment—0
Functional 3D Scene Synthesis through Human-Scene Optimization—0
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models—0
B-RIGHT: Benchmark Re-evaluation for Integrity in Generalized Human-Object Interaction TestingCode0
Show:102550
← PrevPage 1 of 9Next →
All datasetsHICO-DETV-COCOHICOVidHOIAmbiguious-HOIMECCANO

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Ours (PViC+)mAP46.49—Unverified
2RLIPv2 (Swin-L)mAP45.09—Unverified
3PViC-SwinLmAP44.32—Unverified
4SOV-STG (Swin-L)mAP43.35—Unverified
5DiffHOImAP41.5—Unverified
6ViPLOmAP37.22—Unverified
7FGAHOImAP37.18—Unverified
8ERNetmAP36.89—Unverified
9CQL+GEN-VLKT-LmAP36.03—Unverified
10QAHOI (Swin-L)mAP35.78—Unverified
#ModelMetricClaimedVerifiedStatus
1RLIPv2AP(S1)72.1—Unverified
2MURENAP(S1)68.8—Unverified
3STIPAP(S1)66—Unverified
4DiffHOIAP(S1)65.7—Unverified
5OCN (ResNet101)AP(S1)65.3—Unverified
6OCN (ResNet50)AP(S1)64.2—Unverified
7CDN (ResNet101)AP(S1)63.91—Unverified
8HOICLIPAP(S1)63.5—Unverified
9QPIC + CPCMAP63.1—Unverified
10Body Part InteractivenessAP(S1)63—Unverified
#ModelMetricClaimedVerifiedStatus
1DEFRmAP65.6—Unverified
2HAKEmAP47.1—Unverified
3PaStaNetmAP46.3—Unverified
4RelViTmAP43.98—Unverified
5Pairwise-PartmAP39.9—Unverified
6Mallya & LazebnikmAP36.1—Unverified
7Girdhar & RamananmAP34.6—Unverified
8R*CNNmAP28.5—Unverified
#ModelMetricClaimedVerifiedStatus
1HOI4ABOTDetection: Full (mAP@0.5)11.12—Unverified
2ST-GAZEDetection: Full (mAP@0.5)10.4—Unverified
3STTRANDetection: Full (mAP@0.5)7.61—Unverified
#ModelMetricClaimedVerifiedStatus
1DJ-RNmAP10.37—Unverified
2iCANmAP8.14—Unverified
#ModelMetricClaimedVerifiedStatus
1SlowFast + FasterRCNNmAP@0.5 role25.93—Unverified