Papers with cross-modal retrieval
Learning Relation Alignment for Calibrated Cross-modal Retrieval (2021.acl-long)
Copied to clipboard
| Challenge: | despite advances in multimodal pre-training, cross-modal retrieval remains challenging . lack of relation consistency impairs contextualized representation of image-text pairs . |
| Approach: | They propose a new metric to quantify the relation consistency by measuring the semantic distance between linguistic and visual relations. |
| Outcome: | The proposed method boosts the performance of prevailing models on Flickr30k and MS COCO datasets by a considerable margin. |
InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution (2023.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study shows that multi-modal data representations tend to cluster within a limited convex cone, hindering retrieval performance. |
| Approach: | They propose a method that uses graph convolution and average pooling to separate representations by increasing distances between data points. |
| Outcome: | The proposed method reduces representation degeneration problem by increasing distances between data points. |
Compressing then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding (2026.acl-long)
Copied to clipboard
Da Li, Yuxiao Luo, Keping Bi, Jiafeng Guo, Wei Yuan, Biao Yang, Yan Wang, Fan Yang, Tingting Gao, Guorui Zhou
| Challenge: | Recent approaches demonstrate that MLLMs can be adapted into competitive embedding models via large-scale contrastive learning. |
| Approach: | They propose a compressed pre-training phase which serves as a warm-up stage for contrastive learning. |
| Outcome: | The proposed model achieves state-of-the-art among MLLMs of comparable size on the MMEB, realizing optimization in both efficiency and effectiveness. |
Learning Visual-Semantic Embeddings for Reporting Abnormal Findings on Chest X-rays (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on report generation often trains encoder-decoder networks to generate complete reports, but such models are affected by data bias and face common issues inherent in text generation models. |
| Approach: | They propose a method to identify abnormal findings from radiology images and group them with unsupervised clustering and minimal rules. |
| Outcome: | The proposed method outperforms existing generation models on correctness and text generation metrics. |
End-to-end Knowledge Retrieval with Multi-modal Queries (2023.acl-long)
Copied to clipboard
| Challenge: | a new task is proposed to learn knowledge retrieval with multimodal queries . a vision-language model can retrieve knowledge using images and text inputs . |
| Approach: | They propose a task for vision-language models to retrieve knowledge with multi-modal queries . they propose reViz, a model that integrates content from both text and image queries based on a multimodal query task . |
| Outcome: | The proposed task performs better under zero-shot settings than previous work on cross-modal retrieval. |
Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks (2023.emnlp-main)
Copied to clipboard
| Challenge: | a small number of gallery data points are frequently retrieved, resulting in a decline in retrieval performance. |
| Approach: | They propose a framework that leverages both gallery and query data to address hubness . they propose dual inverted softmax and dual dynamic inverted hardmax methods to normalize similarity . |
| Outcome: | The proposed framework reduces the occurrence of hubs during inference while improving similarity between non-hubs and queries. |
FaD-VLP: Fashion Vision-and-Language Pre-training towards Unified Retrieval and Captioning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Prior work on multimodal fashion tasks has been limited by the data in individual benchmarks or has leveraged generic vision-and-language pre-training but have not taken advantage of the characteristics of fashion data. |
| Approach: | They propose a fashion-specific pre-training framework based on weakly-supervised triplets constructed from fashion image-text pairs. |
| Outcome: | The proposed framework is based on weakly-supervised triplets constructed from fashion image-text pairs and is competitive on a diverse set of fashion tasks. |
MEDIAPI-SKEL - A 2D-Skeleton Video Database of French Sign Language With Aligned French Subtitles (2020.lrec-1)
Copied to clipboard
| Challenge: | MEDIAPI-SKEL is a 2D-skeleton database of french Sign Language videos aligned with French subtitles. |
| Approach: | They propose a 2D-skeleton database of french Sign Language videos aligned with French subtitles and a vocabulary size of 17k tokens. |
| Outcome: | The proposed corpus contains 27 hours of video of body, face and hand keypoints, aligned to subtitles with a vocabulary size of 17k tokens. |
M3Retrieve: Benchmarking Multimodal Retrieval for Medicine (2025.emnlp-main)
Copied to clipboard
| Challenge: | Strong retrieval models are increasingly important in knowledge-intensive domains. |
| Approach: | They propose a benchmark to evaluate multimodal retrieval models in medical settings . they examine 1.2 million text documents and 164K multimodal queries . |
| Outcome: | The proposed model spans 5 domains,16 medical fields, and 4 distinct tasks with over 1.2 Million text documents and 164K multimodal queries. |
Inflate and Shrink:Enriching and Reducing Interactions for Fast Text-Image Retrieval (2021.emnlp-main)
Copied to clipboard
| Challenge: | a recent study shows that late-interaction methods trade off retrieval accuracy and efficiency by exploiting cross-modal interactions only in the late stage. |
| Approach: | They propose an inflating and shrinking approach to exploit cross-modal interactions . they inflate code inputs and shrink code outputs to exploit interactions progressively . |
| Outcome: | The proposed method exploits cross-modal interactions in the late stage to achieve retrieval speed. |
Pre-training Cross-Modal Retrieval by Expansive Lexicon-Patch Alignment (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent large-scale vision-language pre-training relies on image-text global alignment by contrastive learning and is further boosted by fine-grained alignment in a weakly contrastive manner for cross-modal retrieval. |
| Approach: | They propose expansive lexicon-patch alignment (ELA) to align image patches with a vocabulary rather than only the words explicitly in the text for annotation-free alignment and information augmentation. |
| Outcome: | The proposed method outperforms state-of-the-art methods on cross-modal retrieval and can learn representative fine-grained information. |
OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for Knowledge-Based Visual Question Answering lack multimodal retrieval . large language models (LLMs) have demonstrated remarkable generalization and reasoning capabilities in text-based systems. |
| Approach: | They propose a multimodal vision-language retrieval-augmented generation system that harmonizes multiple modalities and modality to enhance retrieval. |
| Outcome: | The proposed system achieves state-of-the-art retrieval performance and competitive answers on InfoSeek and Encyclopedic-VQA benchmarks. |
GLA: Grounding Large Language Models in Molecular Hierarchy for Chemical Understanding (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing molecule-language models obscure the hierarchical organization of chemical semantics . Existing models rely on linear or uniform encodings, causing structural distortion . |
| Approach: | They propose a framework that integrates intrinsic molecular topology into large language models. |
| Outcome: | The proposed framework improves on cross-modal retrieval, captioning, and property prediction benchmarks. |