mlsanityData to 7 Oct 2026

Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks

arXiv 1812.04794 ↗First posted 12 Dec 2018cs.CVcited by 102

Not on the map. Why?

Abstract (arXiv)

The task in referring expression comprehension is to localise the object instance in an image described by a referring expression phrased in natural language. As a language-to-vision matching task, the key to this problem is to learn a discriminative object feature that can adapt to the expression used. To avoid ambiguity, the expression normally tends to describe not only the properties of the referent itself, but also its relationships to its neighbourhood. To capture and exploit this important information we propose a graph-based, language-guided attention mechanism. Being composed of node attention component and edge attention component, the proposed graph attention mechanism explicitly represents inter-object relationships, and properties with a flexibility and power impossible with competing approaches. Furthermore, the proposed graph attention mechanism enables the comprehension decision to be visualisable and explainable. Experiments on three referring expression comprehension datasets show the advantage of the proposed approach.

Key facts. Cited by 102 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 24; 2022: 34; 2023: 24; 2024: 13; 2025: 4; 2026: 3.

102 papers.

Sort:

By area:

  1. 2021TransVG: End-to-End Visual Grounding with Transformerscited by 269
  2. 2023GRES: Generalized Referring Expression Segmentationcited by 252
  3. 2023What does CLIP know about a red circle? Visual prompt engineering for VLMscited by 215
  4. 2021InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referringcited by 140
  5. 2021Similarity Reasoning and Filtration for Image-Text Matchingcited by 121
  6. 2022RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Datacited by 121
  7. 2022VLT: Vision-Language Transformer and Query Generation for Referring Segmentationcited by 110
  8. 20223D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selectioncited by 109
  9. 2022TubeDETR: Spatio-Temporal Video Grounding with Transformerscited by 97
  10. 2023Referring Multi-Object Trackingcited by 91
  11. 2023Open-vocabulary Object Segmentation with Diffusion Modelscited by 82
  12. 2021Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloudcited by 81
38 more
  1. 2022Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoningcited by 69
  2. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  3. 2022Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Groundingcited by 52
  4. 2021Look Before You Leap: Learning Landmark Features for One-Stage Visual Groundingcited by 51
  5. 2022Instance-Specific Feature Propagation for Referring Segmentationcited by 45
  6. 2021Visual Grounding with Transformerscited by 42
  7. 2022Local-Global Context Aware Transformer for Language-Guided Video Segmentationcited by 41
  8. 2022TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformercited by 41
  9. 2022Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Groundingcited by 40
  10. 2023GREC: Generalized Referring Expression Comprehensioncited by 39
  11. 2023Multi-Modal Mutual Attention and Iterative Interaction for Referring Image Segmentationcited by 36
  12. 2021Relation-aware Instance Refinement for Weakly Supervised Visual Groundingcited by 35
  13. 2023CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Groundingcited by 35
  14. 2023GPT-4 Enhanced Multimodal Grounding for Autonomous Driving: Leveraging Cross-Modal Attention with Large Language Modelscited by 31
  15. 2022Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Groundingcited by 29
  16. 2023Parallel Vertex Diffusion for Unified Visual Groundingcited by 28
  17. 2021Coarse-to-Fine Reasoning for Visual Question Answeringcited by 25
  18. 2023Context Disentangling and Prototype Inheriting for Robust Visual Groundingcited by 23
  19. 2022Vision+X: A Survey on Multimodal Learning in the Light of Datacited by 22
  20. 2023Mono3DVG: 3D Visual Grounding in Monocular Imagescited by 22
  21. 2021Discriminative Triad Matching and Reconstruction for Weakly Referring Expression Groundingcited by 21
  22. 2021Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learningcited by 20
  23. 2023Language-Guided 3D Object Detection in Point Cloud for Autonomous Drivingcited by 19
  24. 20243D-GRES: Generalized 3D Referring Expression Segmentationcited by 18
  25. 2021Disentangled Motif-aware Graph Learning for Phrase Groundingcited by 17
  26. 2023Advancing Visual Grounding with Scene Knowledge: Benchmark and Methodcited by 17
  27. 2021Word2Pix: Word to Pixel Cross Attention Transformer in Visual Groundingcited by 16
  28. 2022YORO -- Lightweight End to End Visual Groundingcited by 16
  29. 2023Referring Expression Comprehension Using Language Adaptive Inferencecited by 15
  30. 2023RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environmentscited by 15
  31. 2021Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Imagescited by 14
  32. 2024SegVG: Transferring Object Bounding Box to Segmentation for Visual Groundingcited by 14
  33. 2021GoG: Relation-aware Graph-over-Graph Network for Visual Dialogcited by 13
  34. 2021Trajectory Prediction with Linguistic Representationscited by 13
  35. 2022FindIt: Generalized Localization with Natural Language Queriescited by 13
  36. 2024WaterVG: Waterway Visual Grounding based on Text-Guided Vision and mmWave Radarcited by 13
  37. 2022SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Groundingcited by 12
  38. 2022PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Groundingcited by 12

50 most cited of 102 All 102 (JSON)