Differential Attention for Multimodal Crisis Event Analysis

• URL: http://arxiv.org/abs/2507.05165v1
• Date: Mon, 07 Jul 2025 16:20:35 GMT
• Title: Differential Attention for Multimodal Crisis Event Analysis
• Authors: Nusrat Munia, Junfeng Zhu, Olfa Nasraoui, Abdullah-Al-Zubaer Imran,
• Abstract summary: Social networks can be a valuable source of information during crisis events.<n>We explore vision language models (VLMs) and advanced fusion strategies to enhance the classification of crisis data.<n>Our results show that the combination of pretrained VLMs, enriched textual descriptions, and adaptive fusion strategies consistently outperforms state-of-the-art models in classification accuracy.
• Score: 1.5030693386126894
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Social networks can be a valuable source of information during crisis events. In particular, users can post a stream of multimodal data that can be critical for real-time humanitarian response. However, effectively extracting meaningful information from this large and noisy data stream and effectively integrating heterogeneous data remains a formidable challenge. In this work, we explore vision language models (VLMs) and advanced fusion strategies to enhance the classification of crisis data in three different tasks. We incorporate LLaVA-generated text to improve text-image alignment. Additionally, we leverage Contrastive Language-Image Pretraining (CLIP)-based vision and text embeddings, which, without task-specific fine-tuning, outperform traditional models. To further refine multimodal fusion, we employ Guided Cross Attention (Guided CA) and combine it with the Differential Attention mechanism to enhance feature alignment by emphasizing critical information while filtering out irrelevant content. Our results show that while Differential Attention improves classification performance, Guided CA remains highly effective in aligning multimodal features. Extensive experiments on the CrisisMMD benchmark data set demonstrate that the combination of pretrained VLMs, enriched textual descriptions, and adaptive fusion strategies consistently outperforms state-of-the-art models in classification accuracy, contributing to more reliable and interpretable models for three different tasks that are crucial for disaster response. Our code is available at https://github.com/Munia03/Multimodal_Crisis_Event.

Related papers

• Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting [70.83781268763215]
  Vision-language models (VLMs) have achieved impressive performance across diverse multimodal tasks by leveraging large-scale pre-training.<n>VLMs face unique challenges such as cross-modal feature drift, parameter interference due to shared architectures, and zero-shot capability erosion.<n>This survey aims to serve as a comprehensive and diagnostic reference for researchers developing lifelong vision-language systems.
  arXiv  Detail & Related papers  (2025-08-06T09:03:10Z)
• MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings [75.0617088717528]
  MoCa is a framework for transforming pre-trained VLM backbones into effective bidirectional embedding models.<n>MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2025-06-29T06:41:00Z)
• Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation [88.78166077081912]
  We introduce a multimodal unlearning benchmark, UnLOK-VQA, and an attack-and-defense framework to evaluate methods for deleting specific multimodal knowledge from MLLMs.<n>Our results show multimodal attacks outperform text- or image-only ones, and that the most effective defense removes answer information from internal model states.
  arXiv  Detail & Related papers  (2025-05-01T01:54:00Z)
• mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data [71.352883755806]
  Multimodal embedding models have gained significant attention for their ability to map data from different modalities, such as text and images, into a unified representation space.<n>However, the limited labeled multimodal data often hinders embedding performance.<n>Recent approaches have leveraged data synthesis to address this problem, yet the quality of synthetic data remains a critical bottleneck.
  arXiv  Detail & Related papers  (2025-02-12T15:03:33Z)
• GAMED: Knowledge Adaptive Multi-Experts Decoupling for Multimodal Fake News Detection [18.157900272828602]
  Multimodal fake news detection often involves modelling heterogeneous data sources, such as vision and language.<n>This paper develops a significantly novel approach, GAMED, for multimodal modelling.<n>It focuses on generating distinctive and discriminative features through modal decoupling to enhance cross-modal synergies.
  arXiv  Detail & Related papers  (2024-12-11T19:12:22Z)
• Multimodal Remote Sensing Scene Classification Using VLMs and Dual-Cross Attention Networks [0.8999666725996978]
  We propose a novel RSSC framework that integrates text descriptions generated by large vision-language models (VLMs) as an auxiliary modality without incurring expensive manual annotation costs.<n>Experiments with both quantitative and qualitative evaluation across five RSSC datasets demonstrate that our framework consistently outperforms baseline models.
  arXiv  Detail & Related papers  (2024-12-03T16:24:16Z)
• Multimodal Prompt Transformer with Hybrid Contrastive Learning for Emotion Recognition in Conversation [9.817888267356716]
  multimodal Emotion Recognition in Conversation (ERC) faces two problems. Deep emotion cues extraction was performed on modalities with strong representation ability. Feature filters were designed as multimodal prompt information for modalities with weak representation ability. MPT embeds multimodal fusion information into each attention layer of the Transformer.
  arXiv  Detail & Related papers  (2023-10-04T13:54:46Z)
• Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding [54.49214267905562]
  We construct a transformer-based framework for multi-modal manipulation detection and grounding tasks. Our framework simultaneously explores modality-specific features while preserving the capability for multi-modal alignment. We propose an implicit manipulation query (IMQ) that adaptively aggregates global contextual cues within each modality.
  arXiv  Detail & Related papers  (2023-09-22T06:55:41Z)
• SCMM: Calibrating Cross-modal Representations for Text-Based Person Search [45.24784242117999]
  Text-Based Person Search (TBPS) faces critical challenges in cross-modal information fusion.<n>We propose SCMM (Sew and Masked Modeling), a novel framework addressing these fusion challenges through two complementary mechanisms.
  arXiv  Detail & Related papers  (2023-04-05T07:50:16Z)
• Enhancing Crisis-Related Tweet Classification with Entity-Masked Language Modeling and Multi-Task Learning [0.30458514384586394]
  We propose a combination of entity-masked language modeling and hierarchical multi-label classification as a multi-task learning problem. We evaluate our method on tweets from the TREC-IS dataset and show an absolute performance gain w.r.t. F1-score of up to 10% for actionable information types.
  arXiv  Detail & Related papers  (2022-11-21T13:54:10Z)
• Multimodal Categorization of Crisis Events in Social Media [81.07061295887172]
  We present a new multimodal fusion method that leverages both images and texts as input. In particular, we introduce a cross-attention module that can filter uninformative and misleading components from weak modalities. We show that our method outperforms the unimodal approaches and strong multimodal baselines by a large margin on three crisis-related tasks.
  arXiv  Detail & Related papers  (2020-04-10T06:31:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.