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 176200 of 449 papers

TitleStatusHype
Discovering Human Interactions in Videos with Limited Data Labeling0
CHORUS : Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images0
A Graph-based Interactive Reasoning for Human-Object Interaction Detection0
HandyPriors: Physically Consistent Perception of Hand-Object Interactions with Differentiable Priors0
Diffgrasp: Whole-Body Grasping Synthesis Guided by Object Motion Using a Diffusion Model0
CHORUS: Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images0
Human-Aware 3D Scene Generation with Spatially-constrained Diffusion Models0
Guiding Human-Object Interactions with Rich Geometry and Relations0
Diagnosing Rarity in Human-Object Interaction Detection0
Group Activity Recognition via Dynamic Composition and Interaction0
HICO: A Benchmark for Recognizing Human-Object Interactions in Images0
Grounded Human-Object Interaction Hotspots from Video (Extended Abstract)0
Hi-Dyna Graph: Hierarchical Dynamic Scene Graph for Robotic Autonomy in Human-Centric Environments0
Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Models0
Hierarchical Video Prediction Using Relational Layouts for Human-Object Interactions0
ChatHuman: Language-driven 3D Human Understanding with Retrieval-Augmented Tool Reasoning0
DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video0
ChatHuman: Chatting about 3D Humans with Tools0
Hoi2Anomaly: An Explainable Anomaly Detection Approach Guided by Human-Object Interaction0
Gravity-Aware Monocular 3D Human-Object Reconstruction0
GraspDiffusion: Synthesizing Realistic Whole-body Hand-Object Interaction0
whu-nercms at trecvid2021:instance search task0
HOIAnimator: Generating Text-prompt Human-object Animations using Novel Perceptive Diffusion Models0
3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds0
Human Centred Object Co-Segmentation0
Show:102550
← PrevPage 8 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