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 1–50 of 449 papers

TitleStatusHype
Open-Set Image Tagging with Multi-Grained Text SupervisionCode4
Human-Humanoid Robots Cross-Embodiment Behavior-Skill Transfer Using Decomposed Adversarial Learning from DemonstrationCode4
SkillMimic: Learning Basketball Interaction Skills from DemonstrationsCode3
InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object InteractionsCode3
DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human ReferencesCode2
Space-time 2D Gaussian Splatting for Accurate Surface Reconstruction under Complex Dynamic ScenesCode2
InterDiff: Generating 3D Human-Object Interactions with Physics-Informed DiffusionCode2
Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion ModelsCode2
RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic ManipulationCode2
CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangementCode2
InterFusion: Text-Driven Generation of 3D Human-Object InteractionCode2
HAKE: A Knowledge Engine Foundation for Human Activity UnderstandingCode2
VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and CollisionsCode2
Geometric Features Informed Multi-person Human-object Interaction Recognition in VideosCode1
EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level PlanningCode1
Glance and Focus: Memory Prompting for Multi-Event Video Question AnsweringCode1
DRG: Dual Relation Graph for Human-Object Interaction DetectionCode1
Disentangled Pre-training for Human-Object Interaction DetectionCode1
End-to-End Human Object Interaction Detection with HOI TransformerCode1
Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction DetectionCode1
Detecting Human-Object Interaction via Fabricated Compositional LearningCode1
Detecting Human-Object Interactions with Action Co-occurrence PriorsCode1
Discovering Human Interactions With Novel Objects via Zero-Shot LearningCode1
Discovering Human-Object Interaction Concepts via Self-Compositional LearningCode1
Distance-Aware Occlusion Detection with Focused AttentionCode1
BEHAVE: Dataset and Method for Tracking Human Object InteractionsCode1
Dynamics-Regulated Kinematic Policy for Egocentric Pose EstimationCode1
Efficient Adaptive Human-Object Interaction Detection with Concept-guided MemoryCode1
Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise TransformerCode1
GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI DetectionCode1
FGAHOI: Fine-Grained Anchors for Human-Object Interaction DetectionCode1
Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI DetectionCode1
Detailed 2D-3D Joint Representation for Human-Object InteractionCode1
EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI DetectionCode1
First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language AlignmentCode1
Category Query Learning for Human-Object Interaction ClassificationCode1
Articulated 3D Human-Object Interactions from RGB Videos: An Empirical Analysis of Approaches and ChallengesCode1
ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction DetectionCode1
D3D-HOI: Dynamic 3D Human-Object Interactions from VideosCode1
DECO: Dense Estimation of 3D Human-Scene Contact In The WildCode1
Diagnosing Human-object Interaction DetectorsCode1
Full-Body Articulated Human-Object InteractionCode1
Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation ModelsCode1
Detecting Human-Object Interactions with Action Co-occurrence PriorsCode1
Cascaded Human-Object Interaction RecognitionCode1
Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated SemanticsCode1
ACP++: Action Co-occurrence Priors for Human-Object Interaction DetectionCode1
Discovering A Variety of Objects in Spatio-Temporal Human-Object InteractionsCode1
Auto-Regressive Diffusion for Generating 3D Human-Object InteractionsCode1
Affordance Transfer Learning for Human-Object Interaction DetectionCode1
Show:102550
← PrevPage 1 of 9Next →

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