Xuesong Niu

Boosting Latent Diffusion Models via Disentangled Representation Alignment

John Page, Xuesong Niu, Kai Wu, Kun Gai

Latent Diffusion Models (LDMs) rely heavily on the compressed latent space provided by Variational Autoencoders (VAEs) for high-quality image generation. Recent studies have attempted to obtain generation-friendly VAEs by directly adopting alignment strategies from LDM training, leveraging Vision Foundation Models (VFMs) as …

Boosting Latent Diffusion Models via Disentangled Representation Alignment

John Page, Xuesong Niu, Kai Wu, Kun Gai

Latent Diffusion Models (LDMs) rely heavily on the compressed latent space provided by Variational Autoencoders (VAEs) for high-quality image generation. Recent studies have attempted to obtain generation-friendly VAEs by directly adopting alignment strategies from LDM training, leveraging Vision Foundation Models (VFMs) as …

cn (code pays fourni par la source)

Beyond Overfitting: Doubly Adaptive Dropout for Generalizable AU Detection

Yong Li, Yi Ren, Xuesong Niu, Yi Ding et autres

Facial Action Units (AUs) are essential for conveying psychological states and emotional expressions. While automatic AU detection systems leveraging deep learning have progressed, they often overfit to specific datasets and individual features, limiting their cross-domain applicability. To overcome these limitations, we propose …

cn, sg (code pays fourni par la source)

F-HOI: Toward Fine-Grained Semantic-Aligned 3D Human-Object Interactions

Xuesong Niu, Nan Jiang, Ruimao Zhang, Siyuan Huang

cn (code pays fourni par la source)

SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding

Baoxiong Jia, Yixin Chen, Huangyue Yu, Yan Wang et autres

cn (code pays fourni par la source)

Unifying 3D Vision-Language Understanding via Promptable Queries

Ziyu Zhu, Xiaojian Ma, Xuesong Niu, Yixin Chen et autres

cn (code pays fourni par la source)

Multi-Scale Promoted Self-Adjusting Correlation Learning for Facial Action Unit Detection

Xin Liu, Kaishen Yuan, Xuesong Niu, Jingang Shi et autres

Facial Action Unit (AU) detection is a crucial task in affective computing and social robotics as it helps to identify emotions expressed through facial expressions. Anatomically, there are innumerable correlations between AUs, which contain rich information and are vital for AU detection. …

cn (code pays fourni par la source)

Multi-modal Situated Reasoning in 3D Scenes

Xiongkun Linghu, Jiangyong Huang, Xuesong Niu, Xiaojian Ma et autres

Situation awareness is essential for understanding and reasoning about 3D scenes in embodied AI agents. However, existing datasets and benchmarks for situated understanding are limited in data modality, diversity, scale, and task scope. To address these limitations, we propose Multi-modal Situated Question …

Unifying 3D Vision-Language Understanding via Promptable Queries

Ziyu Zhu, Zhuofan Zhang, Xiaojian Ma, Xuesong Niu et autres

A unified model for 3D vision-language (3D-VL) understanding is expected to take various scene representations and perform a wide range of tasks in a 3D scene. However, a considerable gap exists between existing methods and such a unified model, due to the …

SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding

Baoxiong Jia, Yixin Chen, Huangyue Yu, Yan Wang et autres

3D vision-language grounding, which focuses on aligning language with the 3D physical environment, stands as a cornerstone in the development of embodied agents. In comparison to recent advancements in the 2D domain, grounding language in 3D scenes faces several significant challenges: (i) …

Multi-scale Promoted Self-adjusting Correlation Learning for Facial Action Unit Detection

Xin Liu, Kaishen Yuan, Xuesong Niu, Jingang Shi et autres

Facial Action Unit (AU) detection is a crucial task in affective computing and social robotics as it helps to identify emotions expressed through facial expressions. Anatomically, there are innumerable correlations between AUs, which contain rich information and are vital for AU detection. …

Neuron Structure Modeling for Generalizable Remote Physiological Measurement

Hao Lu, Zitong Yu, Xuesong Niu, Ying-Cong Chen

Remote photoplethysmography (rPPG) technology has drawn increasing attention in recent years. It can extract Blood Volume Pulse (BVP) from facial videos, making many applications like health monitoring and emotional analysis more accessible. However, as the BVP signal is easily affected by environmental …

hk (code pays fourni par la source)