Temporal Forgery Localization
6 papers with code • 2 benchmarks • 4 datasets
Benchmarks
These leaderboards are used to track progress in Temporal Forgery Localization
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
LAV-DF
Most implemented papers
ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis
yinanhe/ForgeryNet
•
•
CVPR 2021
To counter this emerging threat, we construct the ForgeryNet dataset, an extremely large face forgery dataset with unified annotations in image- and video-level data across four tasks: 1) Image Forgery Classification, including two-way (real / fake), three-way (real / fake with identity-replaced forgery approaches / fake with identity-remained forgery approaches), and n-way (real and 15 respective forgery approaches) classification.
Not made for each other- Audio-Visual Dissonance-based Deepfake Detection and Localization
MDS is computed as an aggregate of dissimilarity scores between audio and visual segments in a video.
Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization
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.
Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization
The proposed baseline method, Boundary Aware Temporal Forgery Detection (BA-TFD), is a 3D Convolutional Neural Network-based architecture which effectively captures multimodal manipulations.
UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization
Our approach introduces a Temporal Feature Abnormal Attention (TFAA) module based on temporal feature reconstruction to enhance the detection of temporal differences.
AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset
The comprehensive benchmark of the proposed dataset utilizing state-of-the-art deepfake detection and localization methods indicates a significant drop in performance compared to previous datasets.
