23 citations · 31 across the 16 of their papers we have counts for
17 papers
MotionBeat: Motion-Aligned Music Representation via Embodied Contrastive Learning and Bar-Equivariant Contact-Aware Encoding
Xuanchen Wang, Heng Wang, Weidong Cai
Music is both an auditory and an embodied phenomenon, closely linked to human motion and naturally expressed through dance. However, most existing audio representations neglect thi…
MusicWeaver: Programmable Long-Form Music Generation with Provably Local Editing
Xuanchen Wang, Heng Wang, Weidong Cai
Music generation systems produce increasingly realistic audio, yet they expose no interface between a creator's structural intent and the rendered sound. Form can only be steered t…
ChoreoMuse: Robust Music-to-Dance Video Generation with Style Transfer and Beat-Adherent Motion
Xuanchen Wang, Heng Wang, Weidong Cai
Modern artistic productions increasingly demand automated choreography generation that adapts to diverse musical styles and individual dancer characteristics. Existing approaches o…
DINeuro: Distilling Knowledge from 2D Natural Images via Deformable Tubular Transferring Strategy for 3D Neuron Reconstruction
Yik San Cheng, Runkai Zhao, Heng Wang +5
Reconstructing neuron morphology from 3D light microscope imaging data is critical to aid neuroscientists in analyzing brain networks and neuroanatomy. With the boost from deep lea…
Enhancing Advanced Visual Reasoning Ability of Large Language Models
Zhiyuan Li, Dongnan Liu, Chaoyi Zhang +3
Recent advancements in Vision-Language (VL) research have sparked new benchmarks for complex visual reasoning, challenging models' advanced reasoning ability. Traditional Vision-La…
Multimodal Causal Reasoning Benchmark: Challenging Vision Large Language Models to Discern Causal Links Across Modalities
Zhiyuan Li, Heng Wang, Dongnan Liu +4
Multimodal Large Language Models (MLLMs) have showcased exceptional Chain-of-Thought (CoT) reasoning ability in complex textual inference tasks including causal reasoning. However,…
Boosting 3D Neuron Segmentation with 2D Vision Transformer Pre-trained on Natural Images
Yik San Cheng, Runkai Zhao, Heng Wang +2
Neuron reconstruction, one of the fundamental tasks in neuroscience, rebuilds neuronal morphology from 3D light microscope imaging data. It plays a critical role in analyzing the s…
Dance Any Beat: Blending Beats with Visuals in Dance Video Generation
Xuanchen Wang, Heng Wang, Dongnan Liu +1
Generating dance from music is crucial for advancing automated choreography. Current methods typically produce skeleton keypoint sequences instead of dance videos and lack the capa…
Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training
Lei Bai, Dongang Wang, Michael Barnett +13
Accurately measuring the evolution of Multiple Sclerosis (MS) with magnetic resonance imaging (MRI) critically informs understanding of disease progression and helps to direct ther…
Exploring Annotation-free Image Captioning with Retrieval-augmented Pseudo Sentence Generation
Zhiyuan Li, Dongnan Liu, Heng Wang +2
Recently, training an image captioner without annotated image-sentence pairs has gained traction. Previous methods have faced limitations due to either using mismatched corpora for…
PointNeuron: 3D Neuron Reconstruction via Geometry and Topology Learning of Point Clouds
Runkai Zhao, Heng Wang, Chaoyi Zhang +1
Digital neuron reconstruction from 3D microscopy images is an essential technique for investigating brain connectomics and neuron morphology. Existing reconstruction frameworks use…
Towards Generalisable Audio Representations for Audio-Visual Navigation
Shunqi Mao, Chaoyi Zhang, Heng Wang +1
In audio-visual navigation (AVN), an intelligent agent needs to navigate to a constantly sound-making object in complex 3D environments based on its audio and visual perceptions. W…
Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds
Heng Wang, Chaoyi Zhang, Jianhui Yu +1
Dense captioning in 3D point clouds is an emerging vision-and-language task involving object-level 3D scene understanding. Apart from coarse semantic class prediction and bounding…
3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysis
Jianhui Yu, Chaoyi Zhang, Heng Wang +5
General point clouds have been increasingly investigated for different tasks, and recently Transformer-based networks are proposed for point cloud analysis. However, there are bare…
Voxel-wise Cross-Volume Representation Learning for 3D Neuron Reconstruction
Heng Wang, Chaoyi Zhang, Jianhui Yu +4
Automatic 3D neuron reconstruction is critical for analysing the morphology and functionality of neurons in brain circuit activities. However, the performance of existing tracing a…
Single Neuron Segmentation using Graph-based Global Reasoning with Auxiliary Skeleton Loss from 3D Optical Microscope Images
Heng Wang, Yang Song, Chaoyi Zhang +4
One of the critical steps in improving accurate single neuron reconstruction from three-dimensional (3D) optical microscope images is the neuronal structure segmentation. However,…
Region and Object based Panoptic Image Synthesis through Conditional GANs
Heng Wang, Donghao Zhang, Yang Song +3
Image-to-image translation is significant to many computer vision and machine learning tasks such as image synthesis and video synthesis. It has primary applications in the graphic…