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 101125 of 449 papers

TitleStatusHype
Distance-Aware Occlusion Detection with Focused AttentionCode1
PaStaNet: Toward Human Activity Knowledge EngineCode1
Polysemy Deciphering Network for Robust Human-Object Interaction DetectionCode1
Pose-based Modular Network for Human-Object Interaction DetectionCode1
Glance and Focus: Memory Prompting for Multi-Event Video Question AnsweringCode1
QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual InformationCode1
BEHAVE: Dataset and Method for Tracking Human Object InteractionsCode1
DRG: Dual Relation Graph for Human-Object Interaction DetectionCode1
RelViT: Concept-guided Vision Transformer for Visual Relational ReasoningCode1
RLIP: Relational Language-Image Pre-training for Human-Object Interaction DetectionCode1
HOTR: End-to-End Human-Object Interaction Detection with TransformersCode1
Dynamics-Regulated Kinematic Policy for Egocentric Pose EstimationCode1
Spot What Matters: Learning Context Using Graph Convolutional Networks for Weakly-Supervised Action DetectionCode1
Efficient Adaptive Human-Object Interaction Detection with Concept-guided MemoryCode1
ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction DetectionCode1
ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in VideosCode1
Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise TransformerCode1
The MECCANO Dataset: Understanding Human-Object Interactions from Egocentric Videos in an Industrial-like DomainCode1
Exploring Predicate Visual Context in Detecting Human-Object InteractionsCode1
Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI DetectionCode1
ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction DetectionCode1
EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level PlanningCode1
Visual-Semantic Graph Attention Networks for Human-Object Interaction DetectionCode1
Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI DetectionCode1
Zero-Shot Temporal Interaction Localization for Egocentric VideosCode1
Show:102550
← PrevPage 5 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 ([email protected])11.12Unverified
2ST-GAZEDetection: Full ([email protected])10.4Unverified
3STTRANDetection: Full ([email protected])7.61Unverified
#ModelMetricClaimedVerifiedStatus
1DJ-RNmAP10.37Unverified
2iCANmAP8.14Unverified
#ModelMetricClaimedVerifiedStatus
1SlowFast + FasterRCNN[email protected] role25.93Unverified