Youjian Zhao

Jiazhi Guan, Hang Zhou, Zhibin Hong et al.

Recent advances in face forgery techniques produce nearly visually untraceable deepfake videos, which could be leveraged with malicious intentions. As a result, researchers have been devoted to deepfake detection. Previous studies have identified the importance of local low-level cues and temporal information in pursuit to generalize well across deepfake methods, however, they still suffer from robustness problem against post-processings. In this work, we propose the Local- & Temporal-aware Transformer-based Deepfake Detection (LTTD) framework, which adopts a local-to-global learning protocol with a particular focus on the valuable temporal information within local sequences. Specifically, we propose a Local Sequence Transformer (LST), which models the temporal consistency on sequences of restricted spatial regions, where low-level information is hierarchically enhanced with shallow layers of learned 3D filters. Based on the local temporal embeddings, we then achieve the final classification in a global contrastive way. Extensive experiments on popular datasets validate that our approach effectively spots local forgery cues and achieves state-of-the-art performance.

Jiazhi Guan, Hang Zhou, Mingming Gong et al.

Despite encouraging progress in deepfake detection, generalization to unseen forgery types remains a significant challenge due to the limited forgery clues explored during training. In contrast, we notice a common phenomenon in deepfake: fake video creation inevitably disrupts the statistical regularity in original videos. Inspired by this observation, we propose to boost the generalization of deepfake detection by distinguishing the "regularity disruption" that does not appear in real videos. Specifically, by carefully examining the spatial and temporal properties, we propose to disrupt a real video through a Pseudo-fake Generator and create a wide range of pseudo-fake videos for training. Such practice allows us to achieve deepfake detection without using fake videos and improves the generalization ability in a simple and efficient manner. To jointly capture the spatial and temporal disruptions, we propose a Spatio-Temporal Enhancement block to learn the regularity disruption across space and time on our self-created videos. Through comprehensive experiments, our method exhibits excellent performance on several datasets.

Yunsheng Ni, Depu Meng, Changqian Yu et al.

Face manipulation techniques develop rapidly and arouse widespread public concerns. Despite that vanilla convolutional neural networks achieve acceptable performance, they suffer from the overfitting issue. To relieve this issue, there is a trend to introduce some erasing-based augmentations. We find that these methods indeed attempt to implicitly induce more consistent representations for different augmentations via assigning the same label for different augmented images. However, due to the lack of explicit regularization, the consistency between different representations is less satisfactory. Therefore, we constrain the consistency of different representations explicitly and propose a simple yet effective framework, COnsistent REpresentation Learning (CORE). Specifically, we first capture the different representations with different augmentations, then regularize the cosine distance of the representations to enhance the consistency. Extensive experiments (in-dataset and cross-dataset) demonstrate that CORE performs favorably against state-of-the-art face forgery detection methods.

Jiazhi Guan, Zhiliang Xu, Hang Zhou et al.

Lip-syncing videos with given audio is the foundation for various applications including the creation of virtual presenters or performers. While recent studies explore high-fidelity lip-sync with different techniques, their task-orientated models either require long-term videos for clip-specific training or retain visible artifacts. In this paper, we propose a unified and effective framework ReSyncer, that synchronizes generalized audio-visual facial information. The key design is revisiting and rewiring the Style-based generator to efficiently adopt 3D facial dynamics predicted by a principled style-injected Transformer. By simply re-configuring the information insertion mechanisms within the noise and style space, our framework fuses motion and appearance with unified training. Extensive experiments demonstrate that ReSyncer not only produces high-fidelity lip-synced videos according to audio, but also supports multiple appealing properties that are suitable for creating virtual presenters and performers, including fast personalized fine-tuning, video-driven lip-syncing, the transfer of speaking styles, and even face swapping. Resources can be found at https://guanjz20.github.io/projects/ReSyncer.

Bo Zou, Chao Yang, Yu Qiao et al.

Existing methods to fine-tune LLMs, like Adapter, Prefix-tuning, and LoRA, which introduce extra modules or additional input sequences to inject new skills or knowledge, may compromise the innate abilities of LLMs. In this paper, we propose LLaMA-Excitor, a lightweight method that stimulates the LLMs' potential to better follow instructions by gradually paying more attention to worthwhile information. Specifically, the LLaMA-Excitor does not directly change the intermediate hidden state during the self-attention calculation of the transformer structure. We designed the Excitor block as a bypass module for the similarity score computation in LLMs' self-attention to reconstruct keys and change the importance of values by learnable prompts. LLaMA-Excitor ensures a self-adaptive allocation of additional attention to input instructions, thus effectively preserving LLMs' pre-trained knowledge when fine-tuning LLMs on low-quality instruction-following datasets. Furthermore, we unify the modeling of multi-modal tuning and language-only tuning, extending LLaMA-Excitor to a powerful visual instruction follower without the need for complex multi-modal alignment. Our proposed approach is evaluated in language-only and multi-modal tuning experimental scenarios. Notably, LLaMA-Excitor is the only method that maintains basic capabilities while achieving a significant improvement (+6%) on the MMLU benchmark. In the visual instruction tuning, we achieve a new state-of-the-art image captioning performance of 157.5 CIDEr on MSCOCO, and a comparable performance (88.39%) on ScienceQA to cutting-edge models with more parameters and extensive vision-language pertaining.

Bo Zou, Chao Yang, Yu Qiao et al.

Significant advancements in video question answering (VideoQA) have been made thanks to thriving large image-language pretraining frameworks. Although these image-language models can efficiently represent both video and language branches, they typically employ a goal-free vision perception process and do not interact vision with language well during the answer generation, thus omitting crucial visual cues. In this paper, we are inspired by the human recognition and learning pattern and propose VideoDistill, a framework with language-aware (i.e., goal-driven) behavior in both vision perception and answer generation process. VideoDistill generates answers only from question-related visual embeddings and follows a thinking-observing-answering approach that closely resembles human behavior, distinguishing it from previous research. Specifically, we develop a language-aware gating mechanism to replace the standard cross-attention, avoiding language's direct fusion into visual representations. We incorporate this mechanism into two key components of the entire framework. The first component is a differentiable sparse sampling module, which selects frames containing the necessary dynamics and semantics relevant to the questions. The second component is a vision refinement module that merges existing spatial-temporal attention layers to ensure the extraction of multi-grained visual semantics associated with the questions. We conduct experimental evaluations on various challenging video question-answering benchmarks, and VideoDistill achieves state-of-the-art performance in both general and long-form VideoQA datasets. In Addition, we verify that VideoDistill can effectively alleviate the utilization of language shortcut solutions in the EgoTaskQA dataset.

Jiazhi Guan, Tianshu Hu, Hang Zhou et al.

The issue of detecting deepfakes has garnered significant attention in the research community, with the goal of identifying facial manipulations for abuse prevention. Although recent studies have focused on developing generalized models that can detect various types of deepfakes, their performance is not always be reliable and stable, which poses limitations in real-world applications. Instead of learning a forgery detector, in this paper, we propose a novel framework - Integrity Encryptor, aiming to protect portraits in a proactive strategy. Our methodology involves covertly encoding messages that are closely associated with key facial attributes into authentic images prior to their public release. Unlike authentic images, where the hidden messages can be extracted with precision, manipulating the facial attributes through deepfake techniques can disrupt the decoding process. Consequently, the modified facial attributes serve as a mean of detecting manipulated images through a comparison of the decoded messages. Our encryption approach is characterized by its brevity and efficiency, and the resulting method exhibits a good robustness against typical image processing traces, such as image degradation and noise. When compared to baselines that struggle to detect deepfakes in a black-box setting, our method utilizing conditional encryption showcases superior performance when presented with a range of different types of forgeries. In experiments conducted on our protected data, our approach outperforms existing state-of-the-art methods by a significant margin.

Haowen Xu, Wenxiao Chen, Jinlin Lai et al.

Using powerful posterior distributions is a popular approach to achieving better variational inference. However, recent works showed that the aggregated posterior may fail to match unit Gaussian prior, thus learning the prior becomes an alternative way to improve the lower-bound. In this paper, for the first time in the literature, we prove the necessity and effectiveness of learning the prior when aggregated posterior does not match unit Gaussian prior, analyze why this situation may happen, and propose a hypothesis that learning the prior may improve reconstruction loss, all of which are supported by our extensive experiment results. We show that using learned Real NVP prior and just one latent variable in VAE, we can achieve test NLL comparable to very deep state-of-the-art hierarchical VAE, outperforming many previous works with complex hierarchical VAE architectures.