MINTIME: Multi-Identity Size-Invariant Video Deepfake Detection

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00379882" target="_blank" >RIV/68407700:21230/24:00379882 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/TIFS.2024.3409054" target="_blank" >https://doi.org/10.1109/TIFS.2024.3409054</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TIFS.2024.3409054" target="_blank" >10.1109/TIFS.2024.3409054</a>

Jazyk výsledku

angličtina

Název v původním jazyce

MINTIME: Multi-Identity Size-Invariant Video Deepfake Detection

Popis výsledku v původním jazyce

In this paper, we present MINTIME, a video deepfake detection method that effectively captures spatial and temporal inconsistencies in videos that depict multiple individuals and varying face sizes. Unlike previous approaches that either employ simplistic a-posteriori aggregation schemes, i.e., averaging or max operations, or only focus on the largest face in the video, our proposed method learns to accurately detect spatio-temporal inconsistencies across multiple identities in a video through a Spatio-Temporal Transformer combined with a Convolutional Neural Network backbone. This is achieved through an Identity-aware Attention mechanism that applies a masking operation on the face sequence to process each identity independently, which enables effective video-level aggregation. Furthermore, our system incorporates two novel embedding schemes: (i) the Temporal Coherent Positional Embedding, which encodes the temporal information of the face sequences of each identity, and (ii) the Size Embedding, which captures the relative sizes of the faces to the video frames. MINTIME achieves state-of-the-art performance on the ForgeryNet dataset, with a remarkable improvement of up to 14% AUC in videos containing multiple people. Moreover, it demonstrates very robust generalization capabilities in cross-forgery and cross-dataset settings. The code is publicly available at: https://github.com/davide-coccomini/MINTIME-Multi-Identity-size-iNvariant-TIMEsformer-for-Video-Deepfake-Detection.

Název v anglickém jazyce

MINTIME: Multi-Identity Size-Invariant Video Deepfake Detection

Popis výsledku anglicky

In this paper, we present MINTIME, a video deepfake detection method that effectively captures spatial and temporal inconsistencies in videos that depict multiple individuals and varying face sizes. Unlike previous approaches that either employ simplistic a-posteriori aggregation schemes, i.e., averaging or max operations, or only focus on the largest face in the video, our proposed method learns to accurately detect spatio-temporal inconsistencies across multiple identities in a video through a Spatio-Temporal Transformer combined with a Convolutional Neural Network backbone. This is achieved through an Identity-aware Attention mechanism that applies a masking operation on the face sequence to process each identity independently, which enables effective video-level aggregation. Furthermore, our system incorporates two novel embedding schemes: (i) the Temporal Coherent Positional Embedding, which encodes the temporal information of the face sequences of each identity, and (ii) the Size Embedding, which captures the relative sizes of the faces to the video frames. MINTIME achieves state-of-the-art performance on the ForgeryNet dataset, with a remarkable improvement of up to 14% AUC in videos containing multiple people. Moreover, it demonstrates very robust generalization capabilities in cross-forgery and cross-dataset settings. The code is publicly available at: https://github.com/davide-coccomini/MINTIME-Multi-Identity-size-iNvariant-TIMEsformer-for-Video-Deepfake-Detection.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GM21-28830M" target="_blank" >GM21-28830M: Učení Univerzální Vizuální Reprezentace s Omezenou Supervizí</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE Transactions on Information Forensics and Security

ISSN

1556-6013

e-ISSN

1556-6021

Svazek periodika

19

Číslo periodika v rámci svazku

June

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

13

Strana od-do

6084-6096

Kód UT WoS článku

001252656400004

EID výsledku v databázi Scopus

2-s2.0-85195382276