# Multi-level Multimodal Common Semantic Space for Image-Phrase Grounding

arXiv: https://arxiv.org/abs/1811.11683 · HTML: https://mlsanity.com/paper/1811.11683/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2018.

## Built on by (most cited first, 30 of 32)

- [Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing](https://mlsanity.com/paper/2204.09817/) (2022)
- [Multi-Modal Knowledge Graph Construction and Application: A Survey](https://mlsanity.com/paper/2202.05786/) (2022)
- [Relation-aware Instance Refinement for Weakly Supervised Visual Grounding](https://mlsanity.com/paper/2103.12989/) (2021)
- [Referring Image Segmentation Using Text Supervision](https://mlsanity.com/paper/2308.14575/) (2023)
- [OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling](https://mlsanity.com/paper/2410.08021/) (2024)
- [Separating Skills and Concepts for Novel Visual Question Answering](https://mlsanity.com/paper/2107.09106/) (2021)
- [Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations](https://mlsanity.com/paper/2206.15462/) (2022)
- [DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding](https://mlsanity.com/paper/2211.15516/) (2022)
- [Joint Multimedia Event Extraction from Video and Article](https://mlsanity.com/paper/2109.12776/) (2021)
- [MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding](https://mlsanity.com/paper/2112.10728/) (2021)
- [Look at What I'm Doing: Self-Supervised Spatial Grounding of Narrations in Instructional Videos](https://mlsanity.com/paper/2110.10596/) (2021)
- [Disentangled Motif-aware Graph Learning for Phrase Grounding](https://mlsanity.com/paper/2104.06008/) (2021)
- [Improved Visual Grounding through Self-Consistent Explanations](https://mlsanity.com/paper/2312.04554/) (2023)
- [Detector-Free Weakly Supervised Grounding by Separation](https://mlsanity.com/paper/2104.09829/) (2021)
- [Who's Waldo? Linking People Across Text and Images](https://mlsanity.com/paper/2108.07253/) (2021)
- [InstructDET: Diversifying Referring Object Detection with Generalized Instructions](https://mlsanity.com/paper/2310.05136/) (2023)
- [PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding](https://mlsanity.com/paper/2208.05647/) (2022)
- [Co-Grounding Networks with Semantic Attention for Referring Expression Comprehension in Videos](https://mlsanity.com/paper/2103.12346/) (2021)
- [What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs](https://mlsanity.com/paper/2206.09358/) (2022)
- [What, when, and where? -- Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions](https://mlsanity.com/paper/2303.16990/) (2023)
- [Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2501.17053/) (2025)
- [NICE: Improving Panoptic Narrative Detection and Segmentation with Cascading Collaborative Learning](https://mlsanity.com/paper/2310.10975/) (2023)
- [Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Grounding](https://mlsanity.com/paper/2311.01091/) (2023)
- [Top-Down Framework for Weakly-supervised Grounded Image Captioning](https://mlsanity.com/paper/2306.07490/) (2023)
- [Learning from Synthetic Data for Visual Grounding](https://mlsanity.com/paper/2403.13804/) (2024)
- [Re-Aligning Language to Visual Objects with an Agentic Workflow](https://mlsanity.com/paper/2503.23508/) (2025)
- [Predicting Physical World Destinations for Commands Given to Self-Driving Cars](https://mlsanity.com/paper/2112.05419/) (2021)
- [Box-based Refinement for Weakly Supervised and Unsupervised Localization Tasks](https://mlsanity.com/paper/2309.03874/) (2023)
- [Q-GroundCAM: Quantifying Grounding in Vision Language Models via GradCAM](https://mlsanity.com/paper/2404.19128/) (2024)
- [Weakly-Supervised Visual-Textual Grounding with Semantic Prior Refinement](https://mlsanity.com/paper/2305.10913/) (2023)

## Abstract (arXiv)

We address the problem of phrase grounding by lear ing a multi-level common semantic space shared by the textual and visual modalities. We exploit multiple levels of feature maps of a Deep Convolutional Neural Network, as well as contextualized word and sentence embeddings extracted from a character-based language model. Following dedicated non-linear mappings for visual features at each level, word, and sentence embeddings, we obtain multiple instantiations of our common semantic space in which comparisons between any target text and the visual content is performed with cosine similarity. We guide the model by a multi-level multimodal attention mechanism which outputs attended visual features at each level. The best level is chosen to be compared with text content for maximizing the pertinence scores of image-sentence pairs of the ground truth. Experiments conducted on three publicly available datasets show significant performance gains (20%-60% relative) over the state-of-the-art in phrase localization and set a new performance record on those datasets. We provide a detailed ablation study to show the contribution of each element of our approach and release our code on GitHub.