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 201225 of 449 papers

TitleStatusHype
An Abstract Specification of VoxML as an Annotation Language0
Human Motion Prediction, Reconstruction, and Generation0
Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models0
Test-time Distribution Learning Adapter for Cross-modal Visual Reasoning0
Human Object Interaction Detection using Two-Direction Spatial Enhancement and Exclusive Object Prior0
Human-Object Interaction Detection via Disentangled Transformer0
Human-Object Interaction Detection via Weak Supervision0
Human-Object Interaction from Human-Level Instructions0
ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation0
Human-Object Interaction with Vision-Language Model Guided Relative Movement Dynamics0
Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment0
HUMOTO: A 4D Dataset of Mocap Human Object Interactions0
HunyuanVideo-HOMA: Generic Human-Object Interaction in Multimodal Driven Human Animation0
The Overlooked Classifier in Human-Object Interaction Recognition0
iMapper: Interaction-guided Joint Scene and Human Motion Mapping from Monocular Videos0
I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions0
THORN: Temporal Human-Object Relation Network for Action Recognition0
Improving Human-Object Interaction Detection via Phrase Learning and Label Composition0
Improving Human-Object Interaction Detection via Virtual Image Learning0
Amplifying Key Cues for Human-Object-Interaction Detection0
THOR: Text to Human-Object Interaction Diffusion via Relation Intervention0
Instant-NVR: Instant Neural Volumetric Rendering for Human-object Interactions from Monocular RGBD Stream0
InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation0
InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing0
Interact as You Intend: Intention-Driven Human-Object Interaction Detection0
Show:102550
← PrevPage 9 of 18Next →

Benchmark Results

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