GenLie: A Global-Enhanced Lie Detection Network under Sparsity and Semantic Interference
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915870731665408 |
|---|---|
| author | Zhang, Zongshun Liu, Yao Liu, Qiao Peng, Xuefeng Jiang, Peiyuan Yang, Jiaye Yao, Daibing Lin, Wei |
| author_facet | Zhang, Zongshun Liu, Yao Liu, Qiao Peng, Xuefeng Jiang, Peiyuan Yang, Jiaye Yao, Daibing Lin, Wei |
| contents | Video-based lie detection aims to identify deceptive behaviors from visual cues. Despite recent progress, its core challenge lies in learning sparse yet discriminative representations. Deceptive signals are typically subtle and short-lived, easily overwhelmed by redundant information, while individual and contextual variations introduce strong identity-related noise. To address this issue, we propose GenLie, a Global-Enhanced Lie Detection Network that performs local feature modeling under global supervision. Specifically, sparse and subtle deceptive cues are captured at the local level, while global supervision and optimization ensure robust and discriminative representations by suppressing identity-related noise. Experiments on three public datasets, covering both high- and low-stakes scenarios, show that GenLie consistently outperforms state-of-the-art methods. Source code is available at https://github.com/AliasDictusZ1/GenLie. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16935 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GenLie: A Global-Enhanced Lie Detection Network under Sparsity and Semantic Interference Zhang, Zongshun Liu, Yao Liu, Qiao Peng, Xuefeng Jiang, Peiyuan Yang, Jiaye Yao, Daibing Lin, Wei Computer Vision and Pattern Recognition Artificial Intelligence Video-based lie detection aims to identify deceptive behaviors from visual cues. Despite recent progress, its core challenge lies in learning sparse yet discriminative representations. Deceptive signals are typically subtle and short-lived, easily overwhelmed by redundant information, while individual and contextual variations introduce strong identity-related noise. To address this issue, we propose GenLie, a Global-Enhanced Lie Detection Network that performs local feature modeling under global supervision. Specifically, sparse and subtle deceptive cues are captured at the local level, while global supervision and optimization ensure robust and discriminative representations by suppressing identity-related noise. Experiments on three public datasets, covering both high- and low-stakes scenarios, show that GenLie consistently outperforms state-of-the-art methods. Source code is available at https://github.com/AliasDictusZ1/GenLie. |
| title | GenLie: A Global-Enhanced Lie Detection Network under Sparsity and Semantic Interference |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.16935 |