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 110 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 Interactions0
On the Robustness of Human-Object Interaction Detection against Distribution Shift0
Egocentric Human-Object Interaction Detection: A New Benchmark and Method0
InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions0
HunyuanVideo-HOMA: Generic Human-Object Interaction in Multimodal Driven Human Animation0
HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance0
Zero-Shot Temporal Interaction Localization for Egocentric VideosCode1
Show:102550
← PrevPage 1 of 45Next →

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