mlsanityData to 7 Oct 2026

Detecting Human-Object Interaction via Fabricated Compositional Learning

arXiv 2103.08214 ↗First posted 15 Mar 2021cs.CVcited by 79

Not on the map. Why?

Abstract (arXiv)

Human-Object Interaction (HOI) detection, inferring the relationships between human and objects from images/videos, is a fundamental task for high-level scene understanding. However, HOI detection usually suffers from the open long-tailed nature of interactions with objects, while human has extremely powerful compositional perception ability to cognize rare or unseen HOI samples. Inspired by this, we devise a novel HOI compositional learning framework, termed as Fabricated Compositional Learning (FCL), to address the problem of open long-tailed HOI detection. Specifically, we introduce an object fabricator to generate effective object representations, and then combine verbs and fabricated objects to compose new HOI samples. With the proposed object fabricator, we are able to generate large-scale HOI samples for rare and unseen categories to alleviate the open long-tailed issues in HOI detection. Extensive experiments on the most popular HOI detection dataset, HICO-DET, demonstrate the effectiveness of the proposed method for imbalanced HOI detection and significantly improve the state-of-the-art performance on rare and unseen HOI categories. Code is available at https://github.com/zhihou7/HOI-CL.

Key facts. Cited by 79 papers in the map (data through 7 Oct 2026). Builds on 42 of its 70 references that are in the map. First posted on arXiv 15 Mar 2021.

Builds on

42 of 70 references.

References · 42

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  5. 2016Improved Techniques for Training GANscited by 2,938
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  8. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  9. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  10. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  11. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  12. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
30 more
  1. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  2. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  3. 2016Visual Relationship Detection with Language Priorscited by 333
  4. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  5. 2017Learning to Detect Human-Object Interactionscited by 238
  6. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  7. 2017Detecting and Recognizing Human-Object Interactionscited by 199
  8. 2015Visual Semantic Role Labelingcited by 188
  9. 2018Low-Shot Learning from Imaginary Datacited by 181
  10. 2018Learning Human-Object Interactions by Graph Parsing Neural Networkscited by 176
  11. 2020Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wildcited by 152
  12. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
  13. 2019PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detectioncited by 143
  14. 2020Visual Compositional Learning for Human-Object Interaction Detectioncited by 129
  15. 2018iCAN: Instance-Centric Attention Network for Human-Object Interaction Detectioncited by 126
  16. 2020DRG: Dual Relation Graph for Human-Object Interaction Detectioncited by 117
  17. 2020VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutionscited by 115
  18. 2017Generalized Zero-Shot Learning via Synthesized Examplescited by 114
  19. 2016Range Loss for Deep Face Recognition with Long-tailcited by 111
  20. 2020Learning Human-Object Interaction Detection using Interaction Pointscited by 108
  21. 2017Building machines that adapt and compute like brainscited by 99
  22. 2020Detailed 2D-3D Joint Representation for Human-Object Interactioncited by 93
  23. 2019Pose-aware Multi-level Feature Network for Human Object Interaction Detectioncited by 88
  24. 2020Generalized Zero-Shot Learning Via Over-Complete Distributioncited by 56
  25. 2019Deep Contextual Attention for Human-Object Interaction Detectioncited by 54
  26. 2019Detecting Human-Object Interactions via Functional Generalizationcited by 53
  27. 2018Learning Compositional Representations for Few-Shot Recognitioncited by 50
  28. 2019LaSO: Label-Set Operations networks for multi-label few-shot learningcited by 38
  29. 2019On Exploring Undetermined Relationships for Visual Relationship Detectioncited by 26
  30. 2018Transferable Interactiveness Knowledge for Human-Object Interaction Detectioncited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 14; 2023: 23; 2024: 19; 2025: 14; 2026: 6.

79 papers.

Sort:

By area:

  1. 2022GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detectioncited by 119
  2. 2021Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformercited by 91
  3. 2024TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understandingcited by 85
  4. 2021Affordance Transfer Learning for Human-Object Interaction Detectioncited by 79
  5. 2023HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Modelscited by 60
  6. 2023Exploring Predicate Visual Context in Detecting Human-Object Interactionscited by 56
  7. 2022RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detectioncited by 54
  8. 2022Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detectioncited by 46
  9. 2023RLIPv2: Fast Scaling of Relational Language-Image Pre-trainingcited by 44
  10. 2023ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detectioncited by 41
  11. 2022Interactiveness Field in Human-Object Interactionscited by 40
  12. 2022Human-Object Interaction Detection via Disentangled Transformercited by 40
38 more
  1. 2023Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memorycited by 38
  2. 2022What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactionscited by 35
  3. 2022Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactionscited by 34
  4. 2022Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detectioncited by 34
  5. 2023Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Modelscited by 34
  6. 2022End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge Distillationcited by 30
  7. 2022BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learningcited by 29
  8. 2024Open-World Human-Object Interaction Detection via Multi-modal Promptscited by 28
  9. 2024EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detectioncited by 28
  10. 2024Exploring Conditional Multi-Modal Prompts for Zero-shot HOI Detectioncited by 26
  11. 2023Neural-Logic Human-Object Interaction Detectioncited by 25
  12. 2024Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detectioncited by 25
  13. 2023Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Modelcited by 21
  14. 2024Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learningcited by 20
  15. 2022Discovering Human-Object Interaction Concepts via Self-Compositional Learningcited by 15
  16. 2023Compositional Feature Augmentation for Unbiased Scene Graph Generationcited by 15
  17. 2024Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Modelscited by 15
  18. 2023Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detectioncited by 13
  19. 2025Locality-Aware Zero-Shot Human-Object Interaction Detectioncited by 12
  20. 2025HOLa: Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptationcited by 12
  21. 2023Diagnosing Human-object Interaction Detectorscited by 11
  22. 2024Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detectioncited by 11
  23. 2022Chairs Can be Stood on: Overcoming Object Bias in Human-Object Interaction Detectioncited by 9
  24. 2023HODN: Disentangling Human-Object Feature for HOI Detectioncited by 9
  25. 2021GTNet:Guided Transformer Network for Detecting Human-Object Interactionscited by 8
  26. 2022Distance Matters in Human-Object Interaction Detectioncited by 8
  27. 2023Revealing the Proximate Long-Tail Distribution in Compositional Zero-Shot Learningcited by 8
  28. 2025Open-Vocabulary HOI Detection with Interaction-aware Prompt and Concept Calibrationcited by 7
  29. 2024A Plug-and-Play Method for Rare Human-Object Interactions Detection by Bridging Domain Gapcited by 6
  30. 2026What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generationcited by 6
  31. 2023Exploiting CLIP for Zero-shot HOI Detection Requires Knowledge Distillation at Multiple Levelscited by 5
  32. 2024CycleHOI: Improving Human-Object Interaction Detection with Cycle Consistency of Detection and Generationcited by 5
  33. 2024A Review of Human-Object Interaction Detectioncited by 5
  34. 2023Improving Human-Object Interaction Detection via Virtual Image Learningcited by 4
  35. 2024UAHOI: Uncertainty-aware Robust Interaction Learning for HOI Detectioncited by 4
  36. 2023DDS: Decoupled Dynamic Scene-Graph Generation Networkcited by 3
  37. 2023Enhancing HOI Detection with Contextual Cues from Large Vision-Language Modelscited by 3
  38. 2023Few-Shot Learning from Augmented Label-Uncertain Queries in Bongard-HOIcited by 3

50 most cited of 79 All 79 (JSON)