[WACV 2026] AuViRe: Audio-visual Speech Representation Reconstruction for Deepfake Temporal Localization (with Model Checkpoints)
Fuente:
Zenodo
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Recurso digital |
| Published: |
Zenodo
2025
|
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866902129825808384 |
|---|---|
| author | Koutlis, Christos Papadopoulos, Symeon |
| author_facet | Koutlis, Christos Papadopoulos, Symeon |
| contents | <p><em><strong>Model checkpoints</strong></em> of the WACV 2026 paper "AuViRe: Audio-visual Speech Representation Reconstruction for Deepfake Temporal Localization".</p> <p><strong>Abstract</strong>. With the rapid advancement of sophisticated synthetic audio-visual content, e.g., for subtle malicious manipulations, ensuring the integrity of digital media has become paramount. This work presents a novel approach to temporal localization of deepfakes by leveraging Audio-Visual Speech Representation Reconstruction (AuViRe). Specifically, our approach reconstructs speech representations from one modality (e.g., lip movements) based on the other (e.g., audio waveform). Cross-modal reconstruction is significantly more challenging in manipulated video segments, leading to amplified discrepancies, thereby providing robust discriminative cues for precise temporal forgery localization. AuViRe outperforms the state of the art by +8.9 AP@0.95 on LAV-DF, +9.6 AP@0.5 on AV-Deepfake1M, and +5.1 AUC on an in-the-wild experiment. Code available at https://github.com/mever-team/auvire.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17701536 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | [WACV 2026] AuViRe: Audio-visual Speech Representation Reconstruction for Deepfake Temporal Localization (with Model Checkpoints) Koutlis, Christos Papadopoulos, Symeon <p><em><strong>Model checkpoints</strong></em> of the WACV 2026 paper "AuViRe: Audio-visual Speech Representation Reconstruction for Deepfake Temporal Localization".</p> <p><strong>Abstract</strong>. With the rapid advancement of sophisticated synthetic audio-visual content, e.g., for subtle malicious manipulations, ensuring the integrity of digital media has become paramount. This work presents a novel approach to temporal localization of deepfakes by leveraging Audio-Visual Speech Representation Reconstruction (AuViRe). Specifically, our approach reconstructs speech representations from one modality (e.g., lip movements) based on the other (e.g., audio waveform). Cross-modal reconstruction is significantly more challenging in manipulated video segments, leading to amplified discrepancies, thereby providing robust discriminative cues for precise temporal forgery localization. AuViRe outperforms the state of the art by +8.9 AP@0.95 on LAV-DF, +9.6 AP@0.5 on AV-Deepfake1M, and +5.1 AUC on an in-the-wild experiment. Code available at https://github.com/mever-team/auvire.</p> |
| title | [WACV 2026] AuViRe: Audio-visual Speech Representation Reconstruction for Deepfake Temporal Localization (with Model Checkpoints) |
| url | https://doi.org/10.5281/zenodo.17701536 |