# 3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting

arXiv: https://arxiv.org/abs/2404.17273 · HTML: https://mlsanity.com/paper/2404.17273/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 77 references that are in the map.
- First posted on arXiv 26 Apr 2024.

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training](https://mlsanity.com/paper/1908.06066/) (2019)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [Multi-scale Interactive Network for Salient Object Detection](https://mlsanity.com/paper/2007.09062/) (2020)
- [UPSNet: A Unified Panoptic Segmentation Network](https://mlsanity.com/paper/1901.03784/) (2019)
- [Learning the Best Pooling Strategy for Visual Semantic Embedding](https://mlsanity.com/paper/2011.04305/) (2020)
- [Salient Object Detection: A Benchmark](https://mlsanity.com/paper/1501.02741/) (2015)
- [Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisited](https://mlsanity.com/paper/2303.13835/) (2023)
- [Similarity Reasoning and Filtration for Image-Text Matching](https://mlsanity.com/paper/2101.01368/) (2021)
- [Learning Two-Branch Neural Networks for Image-Text Matching Tasks](https://mlsanity.com/paper/1704.03470/) (2017)
- [IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval](https://mlsanity.com/paper/2003.03772/) (2020)
- [Learning Semantic Concepts and Order for Image and Sentence Matching](https://mlsanity.com/paper/1712.02036/) (2017)
- [Consensus-Aware Visual-Semantic Embedding for Image-Text Matching](https://mlsanity.com/paper/2007.08883/) (2020)
- [You Only Segment Once: Towards Real-Time Panoptic Segmentation](https://mlsanity.com/paper/2303.14651/) (2023)
- [Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval](https://mlsanity.com/paper/2108.02417/) (2021)

## Built on by (most cited first, 6 of 6)

- [RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation](https://mlsanity.com/paper/2412.02402/) (2024)
- [Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendation](https://mlsanity.com/paper/2411.02992/) (2024)
- [Diffusion Augmented Retrieval: A Training-Free Approach to Interactive Text-to-Image Retrieval](https://mlsanity.com/paper/2501.15379/) (2025)
- [A Unified Graph Transformer for Overcoming Isolations in Multi-modal Recommendation](https://mlsanity.com/paper/2407.19886/) (2024)
- [Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval](https://mlsanity.com/paper/2506.21538/) (2025)
- [Hire: Hybrid-modal Interaction with Multiple Relational Enhancements for Image-Text Matching](https://mlsanity.com/paper/2406.18579/) (2024)

## Abstract (arXiv)

In this paper, we propose a novel visual Semantic-Spatial Self-Highlighting Network (termed 3SHNet) for high-precision, high-efficiency and high-generalization image-sentence retrieval. 3SHNet highlights the salient identification of prominent objects and their spatial locations within the visual modality, thus allowing the integration of visual semantics-spatial interactions and maintaining independence between two modalities. This integration effectively combines object regions with the corresponding semantic and position layouts derived from segmentation to enhance the visual representation. And the modality-independence guarantees efficiency and generalization. Additionally, 3SHNet utilizes the structured contextual visual scene information from segmentation to conduct the local (region-based) or global (grid-based) guidance and achieve accurate hybrid-level retrieval. Extensive experiments conducted on MS-COCO and Flickr30K benchmarks substantiate the superior performances, inference efficiency and generalization of the proposed 3SHNet when juxtaposed with contemporary state-of-the-art methodologies. Specifically, on the larger MS-COCO 5K test set, we achieve 16.3%, 24.8%, and 18.3% improvements in terms of rSum score, respectively, compared with the state-of-the-art methods using different image representations, while maintaining optimal retrieval efficiency. Moreover, our performance on cross-dataset generalization improves by 18.6%. Data and code are available at https://github.com/XuriGe1995/3SHNet.