Data to 7 Oct 2026

Detecting Human-Object Interactions with Action Co-occurrence Priors

arXiv 2007.08728 ↗First posted 17 Jul 2020cs.CV cs.LGcited by 72

Not on the map. Why?

Abstract (arXiv)

A common problem in human-object interaction (HOI) detection task is that numerous HOI classes have only a small number of labeled examples, resulting in training sets with a long-tailed distribution. The lack of positive labels can lead to low classification accuracy for these classes. Towards addressing this issue, we observe that there exist natural correlations and anti-correlations among human-object interactions. In this paper, we model the correlations as action co-occurrence matrices and present techniques to learn these priors and leverage them for more effective training, especially in rare classes. The utility of our approach is demonstrated experimentally, where the performance of our approach exceeds the state-of-the-art methods on both of the two leading HOI detection benchmark datasets, HICO-Det and V-COCO.

Key facts. Cited by 72 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 23; 2023: 18; 2024: 7; 2025: 3; 2026: 1.

72 papers.

Sort:

By area:

2021HOTR: End-to-End Human-Object Interaction Detection with Transformerscited by 183
2021QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Informationcited by 147
2021End-to-End Human Object Interaction Detection with HOI Transformercited by 134
2022GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detectioncited by 119
2021Mining the Benefits of Two-stage and One-stage HOI Detectioncited by 103
2021Reformulating HOI Detection as Adaptive Set Predictioncited by 95
2021Affordance Transfer Learning for Human-Object Interaction Detectioncited by 79
2022A Survey on Long-Tailed Visual Recognitioncited by 75
2023HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Modelscited by 60
2021Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detectioncited by 58
2022RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detectioncited by 54
2021DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learningcited by 51

38 more

2022Interactiveness Field in Human-Object Interactionscited by 40
2022Human-Object Interaction Detection via Disentangled Transformercited by 40
2023Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memorycited by 38
2022What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactionscited by 35
2022MSTR: Multi-Scale Transformer for End-to-End Human-Object Interaction Detectioncited by 34
2021LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentationcited by 33
2021Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queriescited by 31
2022End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge Distillationcited by 30
2022HAKE: A Knowledge Engine Foundation for Human Activity Understandingcited by 28
2023Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Modelscited by 27
2023Neural-Logic Human-Object Interaction Detectioncited by 25
2022Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semanticscited by 22
2023Category Query Learning for Human-Object Interaction Classificationcited by 21
2022Iwin: Human-Object Interaction Detection via Transformer with Irregular Windowscited by 19
2021MCDAL: Maximum Classifier Discrepancy for Active Learningcited by 18
2022Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detectioncited by 16
2021Improving Human-Object Interaction Detection via Phrase Learning and Label Compositioncited by 15
2023Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detectioncited by 15
2021Dealing with Missing Modalities in the Visual Question Answer-Difference Prediction Task through Knowledge Distillationcited by 14
2022Video-based Human-Object Interaction Detection from Tubelet Tokenscited by 13
2023Unified Visual Relationship Detection with Vision and Language Modelscited by 13
2023Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detectioncited by 13
2022Towards Hard-Positive Query Mining for DETR-based Human-Object Interaction Detectioncited by 12
2022Generative Bias for Robust Visual Question Answeringcited by 12
2021ACP++: Action Co-occurrence Priors for Human-Object Interaction Detectioncited by 11
2022Highlighting Object Category Immunity for the Generalization of Human-Object Interaction Detectioncited by 9
2022Chairs Can be Stood on: Overcoming Object Bias in Human-Object Interaction Detectioncited by 9
2023HODN: Disentangling Human-Object Feature for HOI Detectioncited by 9
2021GTNet:Guided Transformer Network for Detecting Human-Object Interactionscited by 8
2022LocATe: End-to-end Localization of Actions in 3D with Transformerscited by 8
2022Signing Outside the Studio: Benchmarking Background Robustness for Continuous Sign Language Recognitioncited by 8
2023Agglomerative Transformer for Human-Object Interaction Detectioncited by 8
2023Revealing the Proximate Long-Tail Distribution in Compositional Zero-Shot Learningcited by 8
2021The Overlooked Classifier in Human-Object Interaction Recognitioncited by 7
2024Exploring Self- and Cross-Triplet Correlations for Human-Object Interaction Detectioncited by 7
2024Seeing Beyond Classes: Zero-Shot Grounded Situation Recognition via Language Explainercited by 7
2021Single-Modal Entropy based Active Learning for Visual Question Answeringcited by 6
2023Weakly-Supervised HOI Detection from Interaction Labels Only and Language/Vision-Language Priorscited by 6

50 most cited of 72 All 72 (JSON)