# EVAS: Efficient Multimodal Temporal Forgery Localization via Audio-Visual Synergy and Steered Boundary Calibration

arXiv: https://arxiv.org/abs/2607.04472 · HTML: https://mlsanity.com/paper/2607.04472/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 52 references that are in the map.
- First posted on arXiv 5 Jul 2026.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression](https://mlsanity.com/paper/1911.08287/) (2019)
- [MesoNet: a Compact Facial Video Forgery Detection Network](https://mlsanity.com/paper/1809.00888/) (2018)
- [BMN: Boundary-Matching Network for Temporal Action Proposal Generation](https://mlsanity.com/paper/1907.09702/) (2019)
- [Exposing DeepFake Videos By Detecting Face Warping Artifacts](https://mlsanity.com/paper/1811.00656/) (2018)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [G-TAD: Sub-Graph Localization for Temporal Action Detection](https://mlsanity.com/paper/1911.11462/) (2019)
- [Learning Self-Consistency for Deepfake Detection](https://mlsanity.com/paper/2012.09311/) (2020)
- [TriDet: Temporal Action Detection with Relative Boundary Modeling](https://mlsanity.com/paper/2303.07347/) (2023)
- [SOFT: Softmax-free Transformer with Linear Complexity](https://mlsanity.com/paper/2110.11945/) (2021)
- [BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation](https://mlsanity.com/paper/2103.06695/) (2021)
- [Local Relation Learning for Face Forgery Detection](https://mlsanity.com/paper/2105.02577/) (2021)
- [Not made for each other- Audio-Visual Dissonance-based Deepfake Detection and Localization](https://mlsanity.com/paper/2005.14405/) (2020)
- [AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset](https://mlsanity.com/paper/2311.15308/) (2023)
- [AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection](https://mlsanity.com/paper/2406.02951/) (2024)
- [Detecting Photoshopped Faces by Scripting Photoshop](https://mlsanity.com/paper/1906.05856/) (2019)
- [Activity Graph Transformer for Temporal Action Localization](https://mlsanity.com/paper/2101.08540/) (2021)
- [End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames](https://mlsanity.com/paper/2311.17241/) (2023)
- [DCAN: Improving Temporal Action Detection via Dual Context Aggregation](https://mlsanity.com/paper/2112.03612/) (2021)
- [UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization](https://mlsanity.com/paper/2308.14395/) (2023)
- [Deep Learning-based Action Detection in Untrimmed Videos: A Survey](https://mlsanity.com/paper/2110.00111/) (2021)
- [Zooming In on Fakes: A Novel Dataset for Localized AI-Generated Image Detection with Forgery Amplification Approach](https://mlsanity.com/paper/2504.11922/) (2025)
- [Delocate: Detection and Localization for Deepfake Videos with Randomly-Located Tampered Traces](https://mlsanity.com/paper/2401.13516/) (2024)
- [Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer](https://mlsanity.com/paper/2504.14860/) (2025)

## Abstract (arXiv)

The rapid proliferation of artificial intelligence-generated content necessitates reliable multimodal forensics. Beyond video-level binary classification, precisely localizing sparsely distributed forged segments in long-form videos remains a critical challenge. This task is particularly difficult when manipulations are subtly embedded and cross-modal signals are weak and temporally diffuse. To address these challenges, we propose EVAS, an end-to-end multimodal framework for temporal forgery localization. At its core, a Multi-Stage Audio-Visual Synergy mechanism facilitates progressive cross-modal interaction to learn deep multimodal forensic representations and capture high-order semantic traces of sparse manipulations. Furthermore, we introduce a Boundary-Aware Refinement strategy to achieve steered boundary calibration. By incorporating invalid-frame masking, this strategy suppresses ambiguous regions and sharpens transition predictions. We adopt a decoupled training paradigm with auxiliary heads to disentangle representation learning from inference objectives, enhancing model generalization and stability. Additionally, a lightweight HourglassFFN is incorporated to reduce computational overhead. Extensive experiments demonstrate that EVAS achieves state-of-the-art average localization accuracy and average recall across three benchmark datasets, validating its effectiveness for fine-grained temporal forgery localization.