Human Action CLIPs: Detecting AI-generated Human Motion
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915354268139520 |
|---|---|
| author | Bohacek, Matyas Farid, Hany |
| author_facet | Bohacek, Matyas Farid, Hany |
| contents | AI-generated video generation continues its journey through the uncanny valley to produce content that is increasingly perceptually indistinguishable from reality. To better protect individuals, organizations, and societies from its malicious applications, we describe an effective and robust technique for distinguishing real from AI-generated human motion using multi-modal semantic embeddings. Our method is robust to the types of laundering that typically confound more low- to mid-level approaches, including resolution and compression attacks. This method is evaluated against DeepAction, a custom-built, open-sourced dataset of video clips with human actions generated by seven text-to-video AI models and matching real footage. The dataset is available under an academic license at https://www.huggingface.co/datasets/faridlab/deepaction_v1. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_00526 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Human Action CLIPs: Detecting AI-generated Human Motion Bohacek, Matyas Farid, Hany Computer Vision and Pattern Recognition Artificial Intelligence Graphics AI-generated video generation continues its journey through the uncanny valley to produce content that is increasingly perceptually indistinguishable from reality. To better protect individuals, organizations, and societies from its malicious applications, we describe an effective and robust technique for distinguishing real from AI-generated human motion using multi-modal semantic embeddings. Our method is robust to the types of laundering that typically confound more low- to mid-level approaches, including resolution and compression attacks. This method is evaluated against DeepAction, a custom-built, open-sourced dataset of video clips with human actions generated by seven text-to-video AI models and matching real footage. The dataset is available under an academic license at https://www.huggingface.co/datasets/faridlab/deepaction_v1. |
| title | Human Action CLIPs: Detecting AI-generated Human Motion |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics |
| url | https://arxiv.org/abs/2412.00526 |