mlsanityData to 7 Oct 2026

Improving One-stage Visual Grounding by Recursive Sub-query Construction

arXiv 2008.01059 ↗First posted 3 Aug 2020cs.CVcited by 137

Not on the map. Why?

Abstract (arXiv)

We improve one-stage visual grounding by addressing current limitations on grounding long and complex queries. Existing one-stage methods encode the entire language query as a single sentence embedding vector, e.g., taking the embedding from BERT or the hidden state from LSTM. This single vector representation is prone to overlooking the detailed descriptions in the query. To address this query modeling deficiency, we propose a recursive sub-query construction framework, which reasons between image and query for multiple rounds and reduces the referring ambiguity step by step. We show our new one-stage method obtains 5.0%, 4.5%, 7.5%, 12.8% absolute improvements over the state-of-the-art one-stage baseline on ReferItGame, RefCOCO, RefCOCO+, and RefCOCOg, respectively. In particular, superior performances on longer and more complex queries validates the effectiveness of our query modeling.

Key facts. Cited by 137 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 35; 2023: 32; 2024: 29; 2025: 21; 2026: 3.

137 papers.

Sort:

By area:

  1. 2021TransVG: End-to-End Visual Grounding with Transformerscited by 269
  2. 2023GRES: Generalized Referring Expression Segmentationcited by 252
  3. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  4. 2024EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domaincited by 181
  5. 2021Referring Transformer: A One-step Approach to Multi-task Visual Groundingcited by 143
  6. 2022SeqTR: A Simple yet Universal Network for Visual Groundingcited by 138
  7. 2021Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Cloudscited by 128
  8. 2021SAT: 2D Semantics Assisted Training for 3D Visual Groundingcited by 124
  9. 2022RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Datacited by 121
  10. 2022Vision-Language Pre-training: Basics, Recent Advances, and Future Trendscited by 117
  11. 2024SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Modelcited by 112
  12. 2022VLT: Vision-Language Transformer and Query Generation for Referring Segmentationcited by 110
38 more
  1. 20223D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selectioncited by 109
  2. 2022TubeDETR: Spatio-Temporal Video Grounding with Transformerscited by 97
  3. 2023Vision-Language Models in Remote Sensing: Current Progress and Future Trendscited by 93
  4. 2023Open-vocabulary Object Segmentation with Diffusion Modelscited by 82
  5. 2022Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoningcited by 69
  6. 2023Joint Visual Grounding and Tracking with Natural Language Specificationcited by 59
  7. 2022Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Groundingcited by 52
  8. 2024Toward Visual Grounding: A Surveycited by 52
  9. 2021Look Before You Leap: Learning Landmark Features for One-Stage Visual Groundingcited by 51
  10. 2021Visual Grounding with Transformerscited by 42
  11. 2022TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformercited by 41
  12. 2022Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Groundingcited by 41
  13. 2022Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Groundingcited by 40
  14. 2023GREC: Generalized Referring Expression Comprehensioncited by 39
  15. 2023Multi-Modal Mutual Attention and Iterative Interaction for Referring Image Segmentationcited by 36
  16. 2024SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusioncited by 36
  17. 2023CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Groundingcited by 35
  18. 2023Language Adaptive Weight Generation for Multi-task Visual Groundingcited by 35
  19. 2021Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Imagescited by 33
  20. 2022Pseudo-Q: Generating Pseudo Language Queries for Visual Groundingcited by 33
  21. 2021YouRefIt: Embodied Reference Understanding with Language and Gesturecited by 32
  22. 2022ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenescited by 32
  23. 2023GPT-4 Enhanced Multimodal Grounding for Autonomous Driving: Leveraging Cross-Modal Attention with Large Language Modelscited by 31
  24. 2024HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Groundingcited by 31
  25. 2022Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Groundingcited by 29
  26. 2023Parallel Vertex Diffusion for Unified Visual Groundingcited by 28
  27. 2024OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modelingcited by 28
  28. 2024Unifying Visual and Vision-Language Tracking via Contrastive Learningcited by 27
  29. 2022DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Groundingcited by 24
  30. 2023Context Disentangling and Prototype Inheriting for Robust Visual Groundingcited by 23
  31. 2022Entity-enhanced Adaptive Reconstruction Network for Weakly Supervised Referring Expression Groundingcited by 22
  32. 2022Vision+X: A Survey on Multimodal Learning in the Light of Datacited by 22
  33. 2023Mono3DVG: 3D Visual Grounding in Monocular Imagescited by 22
  34. 2022Adapting CLIP For Phrase Localization Without Further Trainingcited by 21
  35. 2024An Efficient and Effective Transformer Decoder-Based Framework for Multi-Task Visual Groundingcited by 21
  36. 2021Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learningcited by 20
  37. 2023Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual Groundingcited by 18
  38. 2024ScanFormer: Referring Expression Comprehension by Iteratively Scanningcited by 18

50 most cited of 137 All 137 (JSON)