# CAST: Cross-Attentive Spatio-Temporal feature fusion for deepfake detection

arXiv: https://arxiv.org/abs/2506.21711 · HTML: https://mlsanity.com/paper/2506.21711/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 52 references that are in the map.
- First posted on arXiv 26 Jun 2025.

## Builds on (most cited first, 27 of 27)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics](https://mlsanity.com/paper/1909.12962/) (2019)
- [Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues](https://mlsanity.com/paper/2007.09355/) (2020)
- [Face X-ray for More General Face Forgery Detection](https://mlsanity.com/paper/1912.13458/) (2019)
- [SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation](https://mlsanity.com/paper/2211.12194/) (2022)
- [Multi-attentional Deepfake Detection](https://mlsanity.com/paper/2103.02406/) (2021)
- [Generalizing Face Forgery Detection with High-frequency Features](https://mlsanity.com/paper/2103.12376/) (2021)
- [Deferred Neural Rendering: Image Synthesis using Neural Textures](https://mlsanity.com/paper/1904.12356/) (2019)
- [DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection](https://mlsanity.com/paper/2001.00179/) (2020)
- [Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection](https://mlsanity.com/paper/2203.12208/) (2022)
- [Exploring Temporal Coherence for More General Video Face Forgery Detection](https://mlsanity.com/paper/2108.06693/) (2021)
- [ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis](https://mlsanity.com/paper/2103.05630/) (2021)
- [Fast Face-swap Using Convolutional Neural Networks](https://mlsanity.com/paper/1611.09577/) (2016)
- [M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection](https://mlsanity.com/paper/2104.09770/) (2021)
- [Dual Contrastive Learning for General Face Forgery Detection](https://mlsanity.com/paper/2112.13522/) (2021)
- [Exploiting Style Latent Flows for Generalizing Deepfake Video Detection](https://mlsanity.com/paper/2403.06592/) (2024)
- [Deep Convolutional Pooling Transformer for Deepfake Detection](https://mlsanity.com/paper/2209.05299/) (2022)
- [D2Fusion: Dual-domain Fusion with Feature Superposition for Deepfake Detection](https://mlsanity.com/paper/2503.17184/) (2025)

## Abstract (arXiv)

Deepfakes have emerged as a significant threat to digital media authenticity, increasing the need for advanced detection techniques that can identify subtle and time-dependent manipulations. CNNs are effective at capturing spatial artifacts and Transformers excel at modeling temporal inconsistencies. However, many existing CNN-Transformer models process spatial and temporal features independently. In particular, attention based methods often use independent attention mechanisms for spatial and temporal features and combine them using naive approaches like averaging, addition or concatenation, limiting the depth of spatio-temporal interaction. To address this challenge, we propose a unified CAST model that leverages cross-attention to effectively fuse spatial and temporal features in a more integrated manner. Our approach allows temporal features to dynamically attend to relevant spatial regions, enhancing the model's ability to detect fine-grained, time-evolving artifacts such as flickering eyes or warped lips. This design enables more precise localization and deeper contextual understanding, leading to improved performance across diverse and challenging scenarios. We evaluate the performance of our model using the FaceForensics++, Celeb-DF, DeepfakeDetection and Deepfake Detection Challenge (DFDC) datasets in both intra and cross dataset settings to affirm the superiority of our approach. Our model achieves strong performance with an Area Under the Curve (AUC) of 99.49% and an accuracy of 97.57% in intra-dataset evaluations. In cross-dataset testing, the model achieves AUC scores of 93.31% and 81.25% on the unseen DeepFakeDetection and DFDC datasets, respectively. These results highlight the effectiveness of cross-attention-based feature fusion in enhancing the robustness of deepfake video detection.