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 251–300 of 449 papers

TitleStatusHype
Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models—0
Test-time Distribution Learning Adapter for Cross-modal Visual Reasoning—0
Human Object Interaction Detection using Two-Direction Spatial Enhancement and Exclusive Object Prior—0
Human-Object Interaction Detection via Disentangled Transformer—0
Human-Object Interaction Detection via Weak Supervision—0
Human-Object Interaction from Human-Level Instructions—0
ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation—0
Human-Object Interaction with Vision-Language Model Guided Relative Movement Dynamics—0
Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment—0
HUMOTO: A 4D Dataset of Mocap Human Object Interactions—0
HunyuanVideo-HOMA: Generic Human-Object Interaction in Multimodal Driven Human Animation—0
The Overlooked Classifier in Human-Object Interaction Recognition—0
iMapper: Interaction-guided Joint Scene and Human Motion Mapping from Monocular Videos—0
I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions—0
THORN: Temporal Human-Object Relation Network for Action Recognition—0
Improving Human-Object Interaction Detection via Phrase Learning and Label Composition—0
Improving Human-Object Interaction Detection via Virtual Image Learning—0
Amplifying Key Cues for Human-Object-Interaction Detection—0
THOR: Text to Human-Object Interaction Diffusion via Relation Intervention—0
Instant-NVR: Instant Neural Volumetric Rendering for Human-object Interactions from Monocular RGBD Stream—0
InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation—0
InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing—0
Interact as You Intend: Intention-Driven Human-Object Interaction Detection—0
InteractEdit: Zero-Shot Editing of Human-Object Interactions in Images—0
Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detection—0
InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions—0
Towards Flexible Visual Relationship Segmentation—0
Interaction Part Mining: A Mid-Level Approach for Fine-Grained Action Recognition—0
A Graph-based Interactive Reasoning for Human-Object Interaction Detection—0
InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction—0
Agglomerative Transformer for Human-Object Interaction Detection—0
AffordanceLLM: Grounding Affordance from Vision Language Models—0
InterTrack: Tracking Human Object Interaction without Object Templates—0
Is First Person Vision Challenging for Object Tracking?—0
Is First Person Vision Challenging for Object Tracking?—0
Is Object Detection Necessary for Human-Object Interaction Recognition?—0
Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows—0
Joint Hand-object 3D Reconstruction from a Single Image with Cross-branch Feature Fusion—0
Jointly learning heterogeneous features for rgb-d activity recognition—0
Kinematics-based 3D Human-Object Interaction Reconstruction from Single View—0
Kinematics-Guided Reinforcement Learning for Object-Aware 3D Ego-Pose Estimation—0
Knowledge Guided Bidirectional Attention Network for Human-Object Interaction Detection—0
Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding—0
Learning Action Recognition Model From Depth and Skeleton Videos—0
Generating Videos of Zero-Shot Compositions of Actions and Objects—0
Learning Asynchronous and Sparse Human-Object Interaction in Videos—0
Towards Overcoming False Positives in Visual Relationship Detection—0
Learning event representation: As sparse as possible, but not sparser—0
Learning from Observer Gaze:Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition—0
Learning from Observer Gaze: Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition—0
Show:102550
← PrevPage 6 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