mlsanityData to 14 Oct 2026

Conditional Image-Text Embedding Networks

arXiv 1711.08389 ↗First posted 22 Nov 2017cs.CVcited by 50

Not on the map. Why?

Abstract (arXiv)

This paper presents an approach for grounding phrases in images which jointly learns multiple text-conditioned embeddings in a single end-to-end model. In order to differentiate text phrases into semantically distinct subspaces, we propose a concept weight branch that automatically assigns phrases to embeddings, whereas prior works predefine such assignments. Our proposed solution simplifies the representation requirements for individual embeddings and allows the underrepresented concepts to take advantage of the shared representations before feeding them into concept-specific layers. Comprehensive experiments verify the effectiveness of our approach across three phrase grounding datasets, Flickr30K Entities, ReferIt Game, and Visual Genome, where we obtain a (resp.) 4%, 3%, and 4% improvement in grounding performance over a strong region-phrase embedding baseline.

Key facts. Cited by 50 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 19; 2022: 19; 2023: 4; 2024: 6; 2025: 1; 2026: 1.

50 papers.

Sort:

By area:

  1. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 819
  2. 2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 531
  3. 2021TransVG: End-to-End Visual Grounding with Transformerscited by 271
  4. 2021Referring Transformer: A One-step Approach to Multi-task Visual Groundingcited by 143
  5. 2022Vision-Language Pre-training: Basics, Recent Advances, and Future Trendscited by 117
  6. 2022Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoningcited by 69
  7. 2021Look Before You Leap: Learning Landmark Features for One-Stage Visual Groundingcited by 52
  8. 2024Toward Visual Grounding: A Surveycited by 52
  9. 2021Visual Grounding with Transformerscited by 42
  10. 2022TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformercited by 42
  11. 2021Relation-aware Instance Refinement for Weakly Supervised Visual Groundingcited by 35
  12. 2022SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Textcited by 30
38 more
  1. 2022Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Groundingcited by 29
  2. 2022DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Groundingcited by 24
  3. 2023Context Disentangling and Prototype Inheriting for Robust Visual Groundingcited by 23
  4. 2022Adapting CLIP For Phrase Localization Without Further Trainingcited by 21
  5. 2021Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learningcited by 20
  6. 2022Ground then Navigate: Language-guided Navigation in Dynamic Scenescited by 20
  7. 2021Disentangled Motif-aware Graph Learning for Phrase Groundingcited by 17
  8. 2022YORO -- Lightweight End to End Visual Groundingcited by 17
  9. 2021Deconfounded Visual Groundingcited by 16
  10. 2022Toward Explainable and Fine-Grained 3D Grounding through Referring Textual Phrasescited by 16
  11. 2024SegVG: Transferring Object Bounding Box to Segmentation for Visual Groundingcited by 14
  12. 2022DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generationcited by 13
  13. 2024Uncertainty-aware Medical Diagnostic Phrase Identification and Groundingcited by 13
  14. 2022PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Groundingcited by 12
  15. 2024You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrievalcited by 12
  16. 2022Correspondence Matters for Video Referring Expression Comprehensioncited by 10
  17. 2021Comprehensive Multi-Modal Interactions for Referring Image Segmentationcited by 9
  18. 2021Effectively Leveraging Attributes for Visual Similaritycited by 9
  19. 2023NICE: Improving Panoptic Narrative Detection and Segmentation with Cascading Collaborative Learningcited by 8
  20. 2022Unpaired Referring Expression Grounding via Bidirectional Cross-Modal Matchingcited by 7
  21. 2024Visual Grounding with Attention-Driven Constraint Balancingcited by 7
  22. 2023Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Groundingcited by 6
  23. 2024ResVG: Enhancing Relation and Semantic Understanding in Multiple Instances for Visual Groundingcited by 6
  24. 2021Contextualizing Meta-Learning via Learning to Decomposecited by 5
  25. 2022Suspected Object Matters: Rethinking Model's Prediction for One-stage Visual Groundingcited by 4
  26. 2022Identifying Ambiguous Similarity Conditions via Semantic Matchingcited by 4
  27. 2022One for All: One-stage Referring Expression Comprehension with Dynamic Reasoningcited by 3
  28. 2023Language-Guided Diffusion Model for Visual Groundingcited by 3
  29. 2021Few-Shot Visual Grounding for Natural Human-Robot Interactioncited by 2
  30. 2021VL-NMS: Breaking Proposal Bottlenecks in Two-Stage Visual-Language Matchingcited by 2
  31. 2021Distributed Attention for Grounded Image Captioningcited by 2
  32. 2021Anchoring to Exemplars for Training Mixture-of-Expert Cell Embeddingscited by 2
  33. 2021A Better Loss for Visual-Textual Groundingcited by 1
  34. 2021Reconstructing and grounding narrated instructional videos in 3Dcited by 0
  35. 2021From Coarse to Fine-grained Concept based Discrimination for Phrase Detectioncited by 0
  36. 2022Multimodal Query-guided Object Localizationcited by 0
  37. 2025Prototype-Aware Multimodal Alignment for Open-Vocabulary Visual Groundingcited by 0
  38. 2026PositionOCR: Augmenting Positional Awareness in Multi-Modal Models via Hybrid Specialist Integrationcited by 0