mlsanityData to 14 Oct 2026

Visual Compositional Learning for Human-Object Interaction Detection

arXiv 2007.12407 ↗First posted 24 Jul 2020cs.CVcited by 130

Not on the map. Why?

Abstract (arXiv)

Human-Object interaction (HOI) detection aims to localize and infer relationships between human and objects in an image. It is challenging because an enormous number of possible combinations of objects and verbs types forms a long-tail distribution. We devise a deep Visual Compositional Learning (VCL) framework, which is a simple yet efficient framework to effectively address this problem. VCL first decomposes an HOI representation into object and verb specific features, and then composes new interaction samples in the feature space via stitching the decomposed features. The integration of decomposition and composition enables VCL to share object and verb features among different HOI samples and images, and to generate new interaction samples and new types of HOI, and thus largely alleviates the long-tail distribution problem and benefits low-shot or zero-shot HOI detection. Extensive experiments demonstrate that the proposed VCL can effectively improve the generalization of HOI detection on HICO-DET and V-COCO and outperforms the recent state-of-the-art methods on HICO-DET. Code is available at https://github.com/zhihou7/VCL.

Key facts. Cited by 130 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 20; 2022: 32; 2023: 33; 2024: 15; 2025: 18; 2026: 12.

130 papers.

Sort:

By area:

  1. 2021HOTR: End-to-End Human-Object Interaction Detection with Transformerscited by 183
  2. 2021QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Informationcited by 147
  3. 2021End-to-End Human Object Interaction Detection with HOI Transformercited by 135
  4. 2022GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detectioncited by 120
  5. 2022Panoptic Scene Graph Generationcited by 114
  6. 2021Mining the Benefits of Two-stage and One-stage HOI Detectioncited by 103
  7. 2021Reformulating HOI Detection as Adaptive Set Predictioncited by 95
  8. 2021Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformercited by 91
  9. 2024TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understandingcited by 88
  10. 2021Detecting Human-Object Interaction via Fabricated Compositional Learningcited by 79
  11. 2021Affordance Transfer Learning for Human-Object Interaction Detectioncited by 79
  12. 2023HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Modelscited by 61
38 more
  1. 2021Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detectioncited by 58
  2. 2023Exploring Predicate Visual Context in Detecting Human-Object Interactionscited by 56
  3. 2022RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detectioncited by 55
  4. 2023RLIPv2: Fast Scaling of Relational Language-Image Pre-trainingcited by 45
  5. 2023ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detectioncited by 41
  6. 2022Interactiveness Field in Human-Object Interactionscited by 40
  7. 2022Human-Object Interaction Detection via Disentangled Transformercited by 40
  8. 2023Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memorycited by 38
  9. 2023Relational Context Learning for Human-Object Interaction Detectioncited by 36
  10. 2022What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactionscited by 35
  11. 2022MSTR: Multi-Scale Transformer for End-to-End Human-Object Interaction Detectioncited by 34
  12. 2022Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactionscited by 34
  13. 2022Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detectioncited by 34
  14. 2023Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Modelscited by 34
  15. 2021Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queriescited by 31
  16. 2022End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge Distillationcited by 30
  17. 2023FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detectioncited by 30
  18. 2022BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learningcited by 29
  19. 2022Probabilistic Compositional Embeddings for Multimodal Image Retrievalcited by 29
  20. 2021QAHOI: Query-Based Anchors for Human-Object Interaction Detectioncited by 28
  21. 2022HAKE: A Knowledge Engine Foundation for Human Activity Understandingcited by 28
  22. 2024Open-World Human-Object Interaction Detection via Multi-modal Promptscited by 28
  23. 2024EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detectioncited by 28
  24. 2025Explain Before You Answer: A Survey on Compositional Visual Reasoningcited by 28
  25. 2024Exploring Conditional Multi-Modal Prompts for Zero-shot HOI Detectioncited by 26
  26. 2023Neural-Logic Human-Object Interaction Detectioncited by 25
  27. 2024Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detectioncited by 25
  28. 2022Category-Aware Transformer Network for Better Human-Object Interaction Detectioncited by 22
  29. 2023Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Modelcited by 22
  30. 2022Iwin: Human-Object Interaction Detection via Transformer with Irregular Windowscited by 19
  31. 2023From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understandingcited by 19
  32. 2021PSI: A Benchmark for Human Interpretation and Response in Traffic Interactionscited by 17
  33. 2024Learning from Observer Gaze:Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognitioncited by 17
  34. 2022Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detectioncited by 16
  35. 2023Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learningcited by 16
  36. 2021Improving Human-Object Interaction Detection via Phrase Learning and Label Compositioncited by 15
  37. 2022Discovering Human-Object Interaction Concepts via Self-Compositional Learningcited by 15
  38. 2022RelViT: Concept-guided Vision Transformer for Visual Relational Reasoningcited by 15

50 most cited of 130 All 130 (JSON)