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

Showing 26–50 of 449 papers

TitleStatusHype
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 2 of 18Next →

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 ([email protected])11.12—Unverified
2ST-GAZEDetection: Full ([email protected])10.4—Unverified
3STTRANDetection: Full ([email protected])7.61—Unverified
#ModelMetricClaimedVerifiedStatus
1DJ-RNmAP10.37—Unverified
2iCANmAP8.14—Unverified
#ModelMetricClaimedVerifiedStatus
1SlowFast + FasterRCNN[email protected] role25.93—Unverified