# E-CaTCH: Event-Centric Cross-Modal Attention with Temporal Consistency and Class-Imbalance Handling for Misinformation Detection

arXiv: https://arxiv.org/abs/2508.11197 · HTML: https://mlsanity.com/paper/2508.11197/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 68 references that are in the map.
- First posted on arXiv 15 Aug 2025.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [High-Performance Large-Scale Image Recognition Without Normalization](https://mlsanity.com/paper/2102.06171/) (2021)
- [Fixup Initialization: Residual Learning Without Normalization](https://mlsanity.com/paper/1901.09321/) (2019)
- [Supervised Multimodal Bitransformers for Classifying Images and Text](https://mlsanity.com/paper/1909.02950/) (2019)
- [Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society](https://mlsanity.com/paper/2005.00033/) (2020)
- [Transformers without Normalization](https://mlsanity.com/paper/2503.10622/) (2025)
- [Fighting the COVID-19 Infodemic in Social Media: A Holistic Perspective and a Call to Arms](https://mlsanity.com/paper/2007.07996/) (2020)
- [A Survey on Truth Discovery](https://mlsanity.com/paper/1505.02463/) (2015)
- [LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation](https://mlsanity.com/paper/2402.11943/) (2024)
- [Bootstrapping Multi-view Representations for Fake News Detection](https://mlsanity.com/paper/2206.05741/) (2022)
- [Learn over Past, Evolve for Future: Forecasting Temporal Trends for Fake News Detection](https://mlsanity.com/paper/2306.14728/) (2023)
- [Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMs](https://mlsanity.com/paper/2409.19656/) (2024)
- [Unsupervised Cross-Domain Rumor Detection with Contrastive Learning and Cross-Attention](https://mlsanity.com/paper/2303.11945/) (2023)
- [GAMED: Knowledge Adaptive Multi-Experts Decoupling for Multimodal Fake News Detection](https://mlsanity.com/paper/2412.12164/) (2024)
- [A Dataset of Fact-Checked Images Shared on WhatsApp During the Brazilian and Indian Elections](https://mlsanity.com/paper/2005.02443/) (2020)
- [MetaAdapt: Domain Adaptive Few-Shot Misinformation Detection via Meta Learning](https://mlsanity.com/paper/2305.12692/) (2023)

## Built on by (most cited first, 1 of 1)

- [MOMENTA: Mixture-of-Experts Over Multimodal Embeddings with Neural Temporal Aggregation for Misinformation Detection](https://mlsanity.com/paper/2604.16172/) (2026)

## Abstract (arXiv)

Detecting multimodal misinformation on social media remains challenging due to inconsistencies between modalities, changes in temporal patterns, and substantial class imbalance. Many existing methods treat posts independently and fail to capture the event-level structure that connects them across time and modality. We propose E-CaTCH, an interpretable and scalable framework for robustly detecting misinformation. If needed, E-CaTCH clusters posts into pseudo-events based on textual similarity and temporal proximity, then processes each event independently. Within each event, textual and visual features are extracted using pre-trained BERT and ResNet encoders, refined via intra-modal self-attention, and aligned through bidirectional cross-modal attention. A soft gating mechanism fuses these representations to form contextualized, content-aware embeddings of each post. To model temporal evolution, E-CaTCH segments events into overlapping time windows and uses a trend-aware LSTM, enhanced with semantic shift and momentum signals, to encode narrative progression over time. Classification is performed at the event level, enabling better alignment with real-world misinformation dynamics. To address class imbalance and promote stable learning, the model integrates adaptive class weighting, temporal consistency regularization, and hard-example mining. The total loss is aggregated across all events. Extensive experiments on Fakeddit, IND, and COVID-19 MISINFOGRAPH demonstrate that E-CaTCH consistently outperforms state-of-the-art baselines. Cross-dataset evaluations further demonstrate its robustness, generalizability, and practical applicability across diverse misinformation scenarios.