4 citations · 10 across the 13 of their papers we have counts for
13 papers
PATE-Forensics: Perception-as-Tool for Explainable Deepfake Forensics with General-Purpose MLLMs
Yaqi Li, Jielun Peng, Yabin Wang +2
Existing explainable deepfake forensic methods typically rely on task-adapted MLLM to jointly address detection, localization, and explanation. Inspired by agent-style tool use, we…
A Benchmark for Semi-supervised Multi-modal Crowd Counting
Haoliang Meng, Xiaopeng Hong, Yabin Wang +1
This paper constructs the first benchmark on semi-supervised multi-modal crowd counting. To lay the foundation for this unexplored task, we first formulate the semi-supervised mult…
Leave No Stone Unturned: Uncovering Holistic Audio-Visual Intrinsic Coherence for Deepfake Detection
Jielun Peng, Yabin Wang, Yaqi Li +2
The rapid progress of generative AI has enabled hyper-realistic audio-visual deepfakes, intensifying threats to personal security and social trust. Most existing deepfake detectors…
ComprehendEdit: A Comprehensive Dataset and Evaluation Framework for Multimodal Knowledge Editing
Yaohui Ma, Xiaopeng Hong, Shizhou Zhang +4
Large multimodal language models (MLLMs) have revolutionized natural language processing and visual understanding, but often contain outdated or inaccurate information. Current mul…
Penny-Wise and Pound-Foolish in Deepfake Detection
Yabin Wang, Zhiwu Huang, Su Zhou +2
The diffusion of deepfake technologies has sparked serious concerns about its potential misuse across various domains, prompting the urgent need for robust detection methods. Despi…
Multi-modal Crowd Counting via Modal Emulation
Chenhao Wang, Xiaopeng Hong, Zhiheng Ma +3
Multi-modal crowd counting is a crucial task that uses multi-modal cues to estimate the number of people in crowded scenes. To overcome the gap between different modalities, we pro…
Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation
Zhilin Zhu, Xiaopeng Hong, Zhiheng Ma +4
Continual Test-Time Adaptation (CTTA) involves adapting a pre-trained source model to continually changing unsupervised target domains. In this paper, we systematically analyze the…
SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding
Wenrui Li, Xiaopeng Hong, Ruiqin Xiong +1
Temporal video grounding (TVG) is a critical task in video content understanding, requiring precise alignment between video content and natural language instructions. Despite signi…
Prompt Customization for Continual Learning
Yong Dai, Xiaopeng Hong, Yabin Wang +3
Contemporary continual learning approaches typically select prompts from a pool, which function as supplementary inputs to a pre-trained model. However, this strategy is hindered b…
Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling
Hui Lin, Zhiheng Ma, Rongrong Ji +4
This paper focuses on semi-supervised crowd counting, where only a small portion of the training data are labeled. We formulate the pixel-wise density value to regress as a probabi…
Gramformer: Learning Crowd Counting via Graph-Modulated Transformer
Hui Lin, Zhiheng Ma, Xiaopeng Hong +2
Transformer has been popular in recent crowd counting work since it breaks the limited receptive field of traditional CNNs. However, since crowd images always contain a large numbe…
Linguistic Profiling of Deepfakes: An Open Database for Next-Generation Deepfake Detection
Yabin Wang, Zhiwu Huang, Zhiheng Ma +1
The emergence of text-to-image generative models has revolutionized the field of deepfakes, enabling the creation of realistic and convincing visual content directly from textual d…
Semi-Supervised Crowd Counting with Contextual Modeling: Facilitating Holistic Understanding of Crowd Scenes
Yifei Qian, Xiaopeng Hong, Zhongliang Guo +2
To alleviate the heavy annotation burden for training a reliable crowd counting model and thus make the model more practicable and accurate by being able to benefit from more data,…