We propose DialoGen, a novel framework for generating realistic gestures for both interlocutors in dialog scenarios, conditioned on conversational audios. Unlike most existing methods that focus solely on a single speaker, DialoGen simultaneously generates synchronized gestures for both participants while also embedding identity-decoupled style into generated gestures that enhance realism and expressiveness. To ensure precise synchronization between interlocutors, DialoGen adopts an interactive dual-diffusion model with mutual interaction estimation, which integrates interaction correlation into the diffusion process. More importantly, by leveraging supervised contrastive learning, we develop the identity-decoupled style guidance to adaptively decompose the identity-specific style of interlocutors into latent space, enabling multi-style dialog gesture generation. Extensive experimental results demonstrate that our model significantly outperforms existing methods in generating realistic, speech-aligned, identity-specific gestures, offering a high-quality solution for various dialog scenarios.

Semantic scene completion aims to simultaneously infer voxel occupancy and semantic categories of a 3D scene from a single depth and/or RGB image. Most existing methods usually use lossy projection operations (such as MaxPool and AvgPool) to deal with the many-to-one problem in the 2D-3D mapping process, which may lead to a loss of crucial 2D information due to the inherent compression effect. To address this, we propose a novel framework that incorporates Geometric-Aware Mapping (GAM) and Voxel-Wise Uncertainty Modeling (VWUM) to improve the accuracy and robustness. Specifically, GAM introduces a distance-weighted mapping strategy to preserve fine-grained 2D details during 2D-to-3D mapping, which ensures that features closer to the voxel center make a greater contribution. Furthermore, VWUM models voxel predictions as Gaussian distributions to explicitly quantify uncertainty, allowing the framework to adaptively estimate confidence levels and mitigate the effects of noisy or ambiguous data. Experimental results on the NYU and NYUCAD datasets show significant improvements in both geometric accuracy and semantic quality.

Listening head generation aims to synthesize realistic and responsive non-verbal listener head motions that respond to speakers in conversational scenarios. Existing methods typically rely on fixed audio-visual input modalities and predefined emotion labels, limiting their adaptability and expressiveness in real-world scenarios. In this paper, we propose a novel real-time framework, REA-Listener, to generate high-fidelity listening head videos with flexible modality adaptation and dynamic emotion modeling. Specifically, we first propose a Modality-Adaptive Mixture of Experts (MA-MoE) module to encode arbitrary combinations of speaker audio and visual signals into a unified embedding space, ensuring robustness under partial modality conditions. To further enhance the temporal consistency of listener emotion, we present a lightweight emotional head dynamics generator with a multi-modal emotion predictor, which infers listener emotions dynamically from speaker context alongside head motion coefficient prediction. Finally, we employ a 3D-aware renderer based on 3D Gaussian Splatting to produce high-quality listener head videos in real time. With these components, our approach achieves efficient head motion generation at 30fps on a single NVIDIA RTX 3090 GPU, supporting real-time interaction. Extensive evaluations and applications demonstrate that our method outperforms state-of-the-art methods in listening head generation.

Outsourcing data services to the public cloud will help data owners save administrative costs, while it may bring privacy concerns. To guarantee the confidentiality of sensitive data against the untrusted cloud and unauthorized users, one way is to have the cloud perform the query processing with encrypted query requests over outsourced encrypted data. However, it is of great challenge to support various types of query processing, especially those of answering why-not questions, under data encryption settings without sensitive information leakage. In this paper, we define and solve the problem of answering why-not questions on top-$k$queries with privacy protection. To address the problem, we propose two Secure Why-Not top$k$Query (SWN$k$Q) processing approaches. In the basic approach, we adopt the Paillier cryptosystem to guarantee the semantic security of data and queries and propose two new secure protocols to support computations on ciphertext in SWN$k$Q processing. Then, we propose a secure weighing space generation method for obtaining the best approximate refined query. To solve the efficiency problem of the basic approach, we further propose an optimized approach, in which dominance-based secure data pruning and early stopping conditions are presented to improve the query efficiency by pruning searching space in the retrieval of refined queries. Thorough analysis shows the security and computational complexity of our approaches, and extensive experimental results on real datasets further demonstrate the query performance of our approaches.