Ke Sun

Ke Sun, Shen Chen, Taiping Yao et al.

Face manipulation techniques have achieved significant advances, presenting serious challenges to security and social trust. Recent works demonstrate that leveraging multimodal models can enhance the generalization and interpretability of face forgery detection. However, existing annotation approaches, whether through human labeling or direct Multimodal Large Language Model (MLLM) generation, often suffer from hallucination issues, leading to inaccurate text descriptions, especially for high-quality forgeries. To address this, we propose Face Forgery Text Generator (FFTG), a novel annotation pipeline that generates accurate text descriptions by leveraging forgery masks for initial region and type identification, followed by a comprehensive prompting strategy to guide MLLMs in reducing hallucination. We validate our approach through fine-tuning both CLIP with a three-branch training framework combining unimodal and multimodal objectives, and MLLMs with our structured annotations. Experimental results demonstrate that our method not only achieves more accurate annotations with higher region identification accuracy, but also leads to improvements in model performance across various forgery detection benchmarks. Our Codes are available in https://github.com/skJack/VLFFD.git.

Ke Sun, Tieyun Qian

The context information such as product category plays a critical role in sequential recommendation. Recent years have witnessed a growing interest in context-aware sequential recommender systems. Existing studies often treat the contexts as auxiliary feature vectors without considering the sequential dependency in contexts. However, such a dependency provides valuable clues to predict the user's future behavior. For example, a user might buy electronic accessories after he/she buy an electronic product. In this paper, we propose a novel seq2seq translation architecture to highlight the importance of sequential dependency in contexts for sequential recommendation. Specifically, we first construct a collateral context sequence in addition to the main interaction sequence. We then generalize recent advancements in translation model from sequences of words in two languages to sequences of items and contexts in recommender systems. Taking the category information as an item's context, we develop a basic coupled and an extended tripled seq2seq translation models to encode the category-item and item-category-item relations between the item and context sequences. We conduct extensive experiments on three real world datasets. The results demonstrate the superior performance of the proposed model compared with the state-of-the-art baselines.