5 papers
UniSkip-Mamba: A Frequency-Aware State Space Model for Audio-Visual Temporal Forgery Localization
Cangjin Yu, Cangjin Qiu, Quan Zhang +2
With the proliferation of AI-generated content, sophisticated multimedia manipulation has raised critical concerns about malicious applications such as opinion manipulation and evi…
EVAS: Efficient Multimodal Temporal Forgery Localization via Audio-Visual Synergy and Steered Boundary Calibration
Shen Shen, Quan Zhang, Dan Jiang +1
The rapid proliferation of artificial intelligence-generated content necessitates reliable multimodal forensics. Beyond video-level binary classification, precisely localizing spar…
MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization
Jingchen Ni, Cangjin Yu, Dan Jiang +6
Driven by Artificial Intelligence-Generated Content (AIGC), the authenticity of audio-visual content is facing severe challenges. Temporal Forgery Localization (TFL) aims to precis…
FCL-COD: Weakly Supervised Camouflaged Object Detection with Frequency-aware and Contrastive Learning
Jingchen Ni, Quan Zhang, Dan Jiang +3
Existing camouflage object detection (COD) methods typically rely on fully-supervised learning guided by mask annotations. However, obtaining mask annotations is time-consuming and…
CLIP-AE: CLIP-assisted Cross-view Audio-Visual Enhancement for Unsupervised Temporal Action Localization
Rui Xia, Dan Jiang, Quan Zhang +2
Temporal Action Localization (TAL) has garnered significant attention in information retrieval. Existing supervised or weakly supervised methods heavily rely on labeled temporal bo…