相关论文: PoseGuard: Pose-Guided Generation with Safety Guar…

In this paper, we present StyleLipSync, a style-based personalized lip-sync video generative model that can generate identity-agnostic lip-synchronizing video from arbitrary audio. To generate a video of arbitrary identities, we leverage…

Generating high-quality 360{\deg} panoramic videos remains a significant challenge due to the fundamental differences between panoramic and traditional perspective-view projections. While perspective videos rely on a single viewpoint with a…

One-shot talking head generation produces lip-sync talking heads based on arbitrary audio and one source face. To guarantee the naturalness and realness, recent methods propose to achieve free pose control instead of simply editing mouth…

We introduce a lightweight yet highly effective safety guardrail framework for language models, demonstrating that small-scale language models can achieve, and even surpass, the performance of larger counterparts in content moderation…

Flow-based frame interpolation methods ensure motion stability through estimated intermediate flow but often introduce severe artifacts in complex motion regions. Recent generative approaches, boosted by large-scale pre-trained video…

Human image generation is a very challenging task since it is affected by many factors. Many human image generation methods focus on generating human images conditioned on a given pose, while the generated backgrounds are often blurred.In…

Improper sitting posture during prolonged computer use has become a significant public health concern. Traditional posture monitoring solutions face substantial barriers, including privacy concerns with camera-based systems and user…

AI safety is a rapidly growing area of research that seeks to prevent the harm and misuse of frontier AI technology, particularly with respect to generative AI (GenAI) tools that are capable of creating realistic and high-quality content…

Generation of high-quality person images is challenging, due to the sophisticated entanglements among image factors, e.g., appearance, pose, foreground, background, local details, global structures, etc. In this paper, we present a novel…

Truly multilingual safety moderation efforts for Large Language Models (LLMs) have been hindered by a narrow focus on a small set of languages (e.g., English, Chinese) as well as a limited scope of safety definition, resulting in…

Deep learning models are susceptible to {\em backdoor attacks} involving malicious attackers perturbing a small subset of training data with a {\em trigger} to causes misclassifications. Various triggers have been used, including semantic…

Video-based person re-identification deals with the inherent difficulty of matching unregulated sequences with different length and with incomplete target pose/viewpoint structure. Common approaches operate either by reducing the problem to…

Although 2D generative models have made great progress in face image generation and animation, they often suffer from undesirable artifacts such as 3D inconsistency when rendering images from different camera viewpoints. This prevents them…

Generative models are increasingly paired with safety classifiers that filter harmful or undesirable outputs. A common strategy is to fine-tune the generator to reduce the probability of being filtered, but this can be suboptimal: it often…

Classical techniques for protecting facial image privacy typically fall into two categories: data-poisoning methods, exemplified by Fawkes, which introduce subtle perturbations to images, or anonymization methods that generate images…

In the era where AI-generated content (AIGC) models can produce stunning and lifelike images, the lingering shadow of unauthorized reproductions and malicious tampering poses imminent threats to copyright integrity and information security.…

Human dance generation (HDG) aims to synthesize realistic videos from images and sequences of driving poses. Despite great success, existing methods are limited to generating videos of a single person with specific backgrounds, while the…

Recent advancements in customized video generation have led to significant improvements in the simultaneous adaptation of appearance and motion. Typically, decoupling the appearance and motion training, prior methods often introduce concept…

Although significant progress has been made in synthesizing high-quality and visually realistic face images by unconditional Generative Adversarial Networks (GANs), there still lacks of control over the generation process in order to…

Prevailing defense mechanisms against adversarial face images tend to overfit to the adversarial perturbations in the training set and fail to generalize to unseen adversarial attacks. We propose a new self-supervised adversarial defense…