Related papers: MIMAFace: Face Animation via Motion-Identity Modul…
Recent advances in video diffusion models have unlocked new potential for realistic audio-driven talking video generation. However, achieving seamless audio-lip synchronization, maintaining long-term identity consistency, and producing…
Face animation deals with controlling and generating facial features with a wide range of applications. The methods based on unsupervised keypoint positioning can produce realistic and detailed virtual portraits. However, they cannot…
Masked autoencoders (MAEs) have emerged recently as art self-supervised spatiotemporal representation learners. Inheriting from the image counterparts, however, existing video MAEs still focus largely on static appearance learning whilst…
Action quality assessment (AQA) aims to automatically quantify the execution quality of human actions in videos and is valuable for applications such as competitive sports judging. In multimodal AQA, quality evidence from different…
Over recent years, diffusion models have facilitated significant advancements in video generation. Yet, the creation of face-related videos still confronts issues such as low facial fidelity, lack of frame consistency, limited editability…
Multimodal Sentiment Analysis is an active area of research that leverages multimodal signals for affective understanding of user-generated videos. The predominant approach, addressing this task, has been to develop sophisticated fusion…
Multimodal emotion recognition (MER) extracts emotions from multimodal data, including visual, speech, and text inputs, playing a key role in human-computer interaction. Attention-based fusion methods dominate MER research, achieving strong…
Text attribute person search aims to find specific pedestrians through given textual attributes, which is very meaningful in the scene of searching for designated pedestrians through witness descriptions. The key challenge is the…
We propose X-Portrait, an innovative conditional diffusion model tailored for generating expressive and temporally coherent portrait animation. Specifically, given a single portrait as appearance reference, we aim to animate it with motion…
We present MOFA-Video, an advanced controllable image animation method that generates video from the given image using various additional controllable signals (such as human landmarks reference, manual trajectories, and another even…
Motion customization aims to adapt the diffusion model (DM) to generate videos with the motion specified by a set of video clips with the same motion concept. To realize this goal, the adaptation of DM should be possible to model the…
This paper presents MMA-MRNNet, a novel deep learning architecture for dynamic multi-output Facial Expression Intensity Estimation (FEIE) from video data. Traditional approaches to this task often rely on complex 3-D CNNs, which require…
As a critical psychological stress response, micro-expressions (MEs) are fleeting and subtle facial movements revealing genuine emotions. Automatic ME recognition (MER) holds valuable applications in fields such as criminal investigation…
With the rise of deep learning in various applications, privacy concerns around the protection of training data have become a critical area of research. Whereas prior studies have focused on privacy risks in single-modal models, we…
Multimodal fake news detection has garnered significant attention due to its profound implications for social security. While existing approaches have contributed to understanding cross-modal consistency, they often fail to leverage…
Facial Appearance Editing (FAE) aims to modify physical attributes, such as pose, expression and lighting, of human facial images while preserving attributes like identity and background, showing great importance in photograph. In spite of…
Membership inference attacks (MIAs) aim to infer whether a data point has been used to train a machine learning model. These attacks can be employed to identify potential privacy vulnerabilities and detect unauthorized use of personal data.…
Video identity customization seeks to synthesize realistic, temporally coherent videos of a specific subject, given a single reference image and a text prompt. This task presents two core challenges: (1) maintaining identity consistency…
Most existing cross-modality person re-identification works rely on discriminative modality-shared features for reducing cross-modality variations and intra-modality variations. Despite some initial success, such modality-shared appearance…
Modern Web systems such as social media and e-commerce contain rich contents expressed in images and text. Leveraging information from multi-modalities can improve the performance of machine learning tasks such as classification and…