# Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization

arXiv: https://arxiv.org/abs/2204.06228 · HTML: https://mlsanity.com/paper/2204.06228/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 58 of its 76 references that are in the map.
- First posted on arXiv 13 Apr 2022.

## Builds on (most cited first, 30 of 58)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics](https://mlsanity.com/paper/1909.12962/) (2019)
- [MoCoGAN: Decomposing Motion and Content for Video Generation](https://mlsanity.com/paper/1707.04993/) (2017)
- [Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues](https://mlsanity.com/paper/2007.09355/) (2020)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [MesoNet: a Compact Facial Video Forgery Detection Network](https://mlsanity.com/paper/1809.00888/) (2018)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis](https://mlsanity.com/paper/2103.11078/) (2021)
- [BMN: Boundary-Matching Network for Temporal Action Proposal Generation](https://mlsanity.com/paper/1907.09702/) (2019)
- [FSGAN: Subject Agnostic Face Swapping and Reenactment](https://mlsanity.com/paper/1908.05932/) (2019)
- [Exposing DeepFake Videos By Detecting Face Warping Artifacts](https://mlsanity.com/paper/1811.00656/) (2018)
- [Exposing Deep Fakes Using Inconsistent Head Poses](https://mlsanity.com/paper/1811.00661/) (2018)
- [Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis](https://mlsanity.com/paper/1806.04558/) (2018)
- [BSN: Boundary Sensitive Network for Temporal Action Proposal Generation](https://mlsanity.com/paper/1806.02964/) (2018)
- [Temporal Action Detection with Structured Segment Networks](https://mlsanity.com/paper/1704.06228/) (2017)
- [DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection](https://mlsanity.com/paper/2001.03024/) (2020)
- [Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss](https://mlsanity.com/paper/1905.03820/) (2019)
- [Neural Voice Puppetry: Audio-driven Facial Reenactment](https://mlsanity.com/paper/1912.05566/) (2019)
- [G-TAD: Sub-Graph Localization for Temporal Action Detection](https://mlsanity.com/paper/1911.11462/) (2019)
- [The Creation and Detection of Deepfakes: A Survey](https://mlsanity.com/paper/2004.11138/) (2020)
- [The THUMOS Challenge on Action Recognition for Videos "in the Wild"](https://mlsanity.com/paper/1604.06182/) (2016)
- [DeepFakes: a New Threat to Face Recognition? Assessment and Detection](https://mlsanity.com/paper/1812.08685/) (2018)
- [WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection](https://mlsanity.com/paper/2101.01456/) (2021)

## Abstract (arXiv)

Due to its high societal impact, deepfake detection is getting active attention in the computer vision community. Most deepfake detection methods rely on identity, facial attributes, and adversarial perturbation-based spatio-temporal modifications at the whole video or random locations while keeping the meaning of the content intact. However, a sophisticated deepfake may contain only a small segment of video/audio manipulation, through which the meaning of the content can be, for example, completely inverted from a sentiment perspective. We introduce a content-driven audio-visual deepfake dataset, termed Localized Audio Visual DeepFake (LAV-DF), explicitly designed for the task of learning temporal forgery localization. Specifically, the content-driven audio-visual manipulations are performed strategically to change the sentiment polarity of the whole video. Our baseline method for benchmarking the proposed dataset is a 3DCNN model, termed as Boundary Aware Temporal Forgery Detection (BA-TFD), which is guided via contrastive, boundary matching, and frame classification loss functions. Our extensive quantitative and qualitative analysis demonstrates the proposed method's strong performance for temporal forgery localization and deepfake detection tasks.