Challenge: Existing work on phrase localization uses caption-image datasets as weak supervision . existing work on supervised phrase localisation uses a large-scale annotated dataset .
Approach: They develop a multimodal alignment framework to leverage more widely available caption-image datasets to model phrase relevance.
Outcome: The proposed model improves on the widely-adopted Flickr30k dataset . it also improves the previous best unsupervised result by 5.56% .

Similar Papers

Contrastive Learning with Expectation-Maximization for Weakly Supervised Phrase Grounding (2022.emnlp-main)

Copied to clipboard

Challenge: Weakly supervised phrase grounding aims to learn an alignment between phrases in a caption and objects in an image using only caption-image annotations.
Approach: They propose a novel contrastive learning framework that adaptively refines the target prediction by using only caption-image annotations.
Outcome: The proposed framework outperforms existing methods on two widely used benchmarks, Flickr30K Entities and RefCOCO+.
Weakly-Supervised Learning of Visual Relations in Multimodal Pretraining (2023.emnlp-main)

Copied to clipboard

Challenge: Recent work in vision-and-language pretraining has investigated supervised signals from object detection data to learn better, fine-grained multimodal representations.
Approach: They propose two approaches to contextualise visual entities in a multimodal setup by using verbalised scene graphs and masked relation prediction.
Outcome: The proposed models can learn better representations from weakly-supervised relations data.
Improving Pre-trained Vision-and-Language Embeddings for Phrase Grounding (2021.emnlp-main)

Copied to clipboard

Challenge: Existing studies have focused on the phrase grounding ability of pretrained vision-and-language models, but it is unclear how they can be used for phrase ground.
Approach: They propose to extract phrase-region pairs from pre-trained vision-and-language embeddings and propose four fine-tuning objectives to improve model phrase grounding ability using image-caption data without any supervised grounding signals.
Outcome: The proposed model outperforms baseline models in weakly-supervised and supervised phrase grounding settings on two representative datasets and shows that it is possible to achieve better phrase groundability without sacrificing representation generality.
Tag-grounded Visual Instruction Tuning with Retrieval Augmentation (2024.emnlp-main)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) have seen remarkable progress in providing general instruction-following ability, but struggle with critical problems when required to provide a detailed and accurate response to a visual instruction.
Approach: They propose to enhance the mapping process by using retrieval-augmented tag tokens, which contain rich object-aware information such as object names and attributes.
Outcome: The proposed model outperforms baselines that share the same language model and training data on 12 benchmarks and shows zero-shot capability when provided with specific datastores.
Fine-Grained Grounding for Multimodal Speech Recognition (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing models rely on global visual features that represent the entire image, but localizing the relevant regions of the image will make it possible to recover a larger set of words, such as adjectives and verbs.
Approach: They propose a multimodal automatic speech recognition system that uses visual information from different parts of the image to ground the speech in the visual context.
Outcome: The proposed model improves over approaches that use global visual features and localizes the correct proposals.
EFUF: Efficient Fine-Grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to eliminate hallucinations require expensive human annotation . hallucination in multimodal large language models poses unique challenges for current research .
Approach: They propose a fine-grained unlearning framework that performs gradient ascent to eliminate hallucinations without paired data.
Outcome: The proposed method reduces hallucinations while preserving quality with modest computational overhead.
That’s the Wrong Lung! Evaluating and Improving the Interpretability of Unsupervised Multimodal Encoders for Medical Data (2022.emnlp-main)

Copied to clipboard

Challenge: Recent multimodal models induce soft local alignments between image regions and sentences.
Approach: They compare alignments from a state-of-the-art multimodal model for EHR with human annotations that link image regions to sentences.
Outcome: The proposed models induce soft local alignments between image regions and sentences . the text has an often weak or unintuitive influence on attention, the authors found .
Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structures (2025.acl-long)

Copied to clipboard

Challenge: incorporating textual and multimodal reference resolution improves performance in visual-based reference resolution . Phrase grounding is a well-established task for understanding semantic relations between mentions and objects . ambiguities caused by pronouns and ellipses can arise in visually grounded dialogues .
Approach: They propose a framework that unifies textual and multimodal reference resolution by mapping mention embeddings to object embeddements and selecting mentions or objects based on their similarity.
Outcome: The proposed framework performs better in phrase grounding than other models for this task.
Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task (D19-66)

Copied to clipboard

Challenge: Existing methods to learn multimodal multilingual embeddings for text and image retrieval tasks are limited to English.
Approach: They propose a new approach to learn multimodal multilingual embeddings for matching images and captions in two languages by combing two existing objective functions and adapting alignment between existing languages.
Outcome: The proposed model achieves state-of-the-art in retrieval and caption-caption tasks while adapting existing language alignments.
Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task (D19-64)

Copied to clipboard

Challenge: Existing methods to learn multimodal multilingual embeddings for text and image retrieval tasks are limited to English.
Approach: They propose a new approach to learn multimodal multilingual embeddings for matching images and captions in two languages by combing two existing objective functions and adapting alignment between existing languages.
Outcome: The proposed model achieves state-of-the-art in retrieval and caption-caption tasks while adapting existing language alignments.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations