# Learning Two-Branch Neural Networks for Image-Text Matching Tasks

arXiv: https://arxiv.org/abs/1704.03470 · HTML: https://mlsanity.com/paper/1704.03470/

## Key facts

- Cited by 119 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2017.

## Built on by (most cited first, 30 of 119)

- [TransVG: End-to-End Visual Grounding with Transformers](https://mlsanity.com/paper/2104.08541/) (2021)
- [Unified Contrastive Learning in Image-Text-Label Space](https://mlsanity.com/paper/2204.03610/) (2022)
- [Referring Transformer: A One-step Approach to Multi-task Visual Grounding](https://mlsanity.com/paper/2106.03089/) (2021)
- [InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring](https://mlsanity.com/paper/2103.01128/) (2021)
- [SeqTR: A Simple yet Universal Network for Visual Grounding](https://mlsanity.com/paper/2203.16265/) (2022)
- [LAFITE: Towards Language-Free Training for Text-to-Image Generation](https://mlsanity.com/paper/2111.13792/) (2021)
- [SAT: 2D Semantics Assisted Training for 3D Visual Grounding](https://mlsanity.com/paper/2105.11450/) (2021)
- [Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark](https://mlsanity.com/paper/2202.06767/) (2022)
- [3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection](https://mlsanity.com/paper/2204.06272/) (2022)
- [Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers](https://mlsanity.com/paper/2103.16553/) (2021)
- [Open-vocabulary Object Segmentation with Diffusion Models](https://mlsanity.com/paper/2301.05221/) (2023)
- [Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning](https://mlsanity.com/paper/2205.00272/) (2022)
- [UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training](https://mlsanity.com/paper/2104.00332/) (2021)
- [Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answering](https://mlsanity.com/paper/2104.14085/) (2021)
- [Image-text Retrieval: A Survey on Recent Research and Development](https://mlsanity.com/paper/2203.14713/) (2022)
- [Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding](https://mlsanity.com/paper/2203.15442/) (2022)
- [Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding](https://mlsanity.com/paper/2104.04386/) (2021)
- [Toward Visual Grounding: A Survey](https://mlsanity.com/paper/2412.20206/) (2024)
- [Towards General Purpose Vision Systems](https://mlsanity.com/paper/2104.00743/) (2021)
- [LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval](https://mlsanity.com/paper/2103.08784/) (2021)
- [Visual Goal-Step Inference using wikiHow](https://mlsanity.com/paper/2104.05845/) (2021)
- [X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks](https://mlsanity.com/paper/2204.05626/) (2022)
- [TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformer](https://mlsanity.com/paper/2206.06619/) (2022)
- [Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Grounding](https://mlsanity.com/paper/2211.14241/) (2022)
- [Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos](https://mlsanity.com/paper/2203.11637/) (2022)
- [GPT-4 Enhanced Multimodal Grounding for Autonomous Driving: Leveraging Cross-Modal Attention with Large Language Models](https://mlsanity.com/paper/2312.03543/) (2023)
- [ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations](https://mlsanity.com/paper/2501.14607/) (2025)
- [Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding](https://mlsanity.com/paper/2209.13959/) (2022)
- [Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval](https://mlsanity.com/paper/2103.11920/) (2021)
- [Multimodal Entity Linking for Tweets](https://mlsanity.com/paper/2104.03236/) (2021)

## Abstract (arXiv)

Image-language matching tasks have recently attracted a lot of attention in the computer vision field. These tasks include image-sentence matching, i.e., given an image query, retrieving relevant sentences and vice versa, and region-phrase matching or visual grounding, i.e., matching a phrase to relevant regions. This paper investigates two-branch neural networks for learning the similarity between these two data modalities. We propose two network structures that produce different output representations. The first one, referred to as an embedding network, learns an explicit shared latent embedding space with a maximum-margin ranking loss and novel neighborhood constraints. Compared to standard triplet sampling, we perform improved neighborhood sampling that takes neighborhood information into consideration while constructing mini-batches. The second network structure, referred to as a similarity network, fuses the two branches via element-wise product and is trained with regression loss to directly predict a similarity score. Extensive experiments show that our networks achieve high accuracies for phrase localization on the Flickr30K Entities dataset and for bi-directional image-sentence retrieval on Flickr30K and MSCOCO datasets.