Author name cluster

Lin Gao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

YNIMG Journal 2024 Journal Article

Differential neural representations of syntactic and semantic information across languages in Chinese-English bilinguals

Zeqi Hou
Hehui Li
Lin Gao
Jian Ou
Min Xu

Bilingual individuals manage multiple languages that align in conceptual meaning but differ in forms and structures. While prior research has established foundational insights into the neural mechanisms in bilingual processing, the extent to which the first (L1) and second language (L2) systems overlap or diverge across different linguistic components remains unclear. This study probed the neural underpinnings of syntactic and semantic processing for L1 and L2 in Chinese-English bilinguals (N = 44) who performed sentence comprehension tasks and an N-back working memory task during functional MRI scanning. We observed that the increased activation for L2 processing was within the verbal working memory network, suggesting a greater cognitive demand for processing L2. Crucially, we looked for brain regions showing adaptation to the repetition of semantic information and syntactic structure, and found more robust adaptation effects in L1 in the middle and superior temporal cortical areas. The differential adaptation effects between L1 and L2 were more pronounced for the semantic condition. Multivariate pattern analysis further revealed distinct neural sensitivities to syntactic and semantic representations between L1 and L2 across frontotemporal language regions. Our findings suggest that while L1 and L2 engage similar neural systems, finer representation analyses uncover distinct neural patterns for both semantic and syntactic aspects in the two languages. This study advances our understanding of neural representations involved in different language components in bilingual individuals.

Details DOI

NeurIPS Conference 2022 Conference Paper

HSDF: Hybrid Sign and Distance Field for Modeling Surfaces with Arbitrary Topologies

Li Wang
Jie Yang
Weikai Chen
Xiaoxu Meng
Bo Yang
Jintao Li
Lin Gao

Neural implicit function based on signed distance field (SDF) has achieved impressive progress in reconstructing 3D models with high fidelity. However, such approaches can only represent closed shapes. Recent works based on unsigned distance function (UDF) are proposed to handle both watertight and open surfaces. Nonetheless, as UDF is signless, its direct output is limited to point cloud, which imposes an additional challenge on extracting high-quality meshes from discrete points. To address this issue, we present a new learnable implicit representation, coded HSDF, that connects the good ends of SDF and UDF. In particular, HSDF is able to represent arbitrary topologies containing both closed and open surfaces while being compatible with existing iso-surface extraction techniques for easy field-to-mesh conversion. In addition to predicting a UDF, we propose to learn an additional sign field via a simple classifier. Unlike traditional SDF, HSDF is able to locate the surface of interest before level surface extraction by generating surface points following NDF~\cite{chibane2020ndf}. We are then able to obtain open surfaces via an adaptive meshing approach that only instantiates regions containing surface into a polygon mesh. We also propose HSDF-Net, a dedicated learning framework that factorizes the learning of HSDF into two easier problems. Experiments on multiple datasets show that HSDF outperforms state-of-the-art techniques both qualitatively and quantitatively.

PDF Details

NeurIPS Conference 2021 Conference Paper

OctField: Hierarchical Implicit Functions for 3D Modeling

Jia-Heng Tang
Weikai Chen
Jie Yang
Bo Wang
Songrun Liu
Bo Yang
Lin Gao

Recent advances in localized implicit functions have enabled neural implicit representation to be scalable to large scenes. However, the regular subdivision of 3D space employed by these approaches fails to take into account the sparsity of the surface occupancy and the varying granularities of geometric details. As a result, its memory footprint grows cubically with the input volume, leading to a prohibitive computational cost even at a moderately dense decomposition. In this work, we present a learnable hierarchical implicit representation for 3D surfaces, coded OctField, that allows high-precision encoding of intricate surfaces with low memory and computational budget. The key to our approach is an adaptive decomposition of 3D scenes that only distributes local implicit functions around the surface of interest. We achieve this goal by introducing a hierarchical octree structure to adaptively subdivide the 3D space according to the surface occupancy and the richness of part geometry. As octree is discrete and non-differentiable, we further propose a novel hierarchical network that models the subdivision of octree cells as a probabilistic process and recursively encodes and decodes both octree structure and surface geometry in a differentiable manner. We demonstrate the value of OctField for a range of shape modeling and reconstruction tasks, showing superiority over alternative approaches.

PDF Details

AAAI Conference 2019 Conference Paper

Graph CNNs with Motif and Variable Temporal Block for Skeleton-Based Action Recognition

Yu-Hui Wen
Lin Gao
Hongbo Fu
Fang-Lue Zhang
Shihong Xia

Hierarchical structure and different semantic roles of joints in human skeleton convey important information for action recognition. Conventional graph convolution methods for modeling skeleton structure consider only physically connected neighbors of each joint, and the joints of the same type, thus failing to capture highorder information. In this work, we propose a novel model with motif-based graph convolution to encode hierarchical spatial structure, and a variable temporal dense block to exploit local temporal information over different ranges of human skeleton sequences. Moreover, we employ a non-local block to capture global dependencies of temporal domain in an attention mechanism. Our model achieves improvements over the stateof-the-art methods on two large-scale datasets.

PDF Details

AAAI Conference 2018 Conference Paper

Mesh-Based Autoencoders for Localized Deformation Component Analysis

Qingyang Tan
Lin Gao
Yu-Kun Lai
Jie Yang
Shihong Xia

Spatially localized deformation components are very useful for shape analysis and synthesis in 3D geometry processing. Several methods have recently been developed, with an aim to extract intuitive and interpretable deformation components. However, these techniques suffer from fundamental limitations especially for meshes with noise or large-scale deformations, and may not always be able to identify important deformation components. In this paper we propose a novel mesh-based autoencoder architecture that is able to cope with meshes with irregular topology. We introduce sparse regularization in this framework, which along with convolutional operations, helps localize deformations. Our framework is capable of extracting localized deformation components from mesh data sets with large-scale deformations and is robust to noise. It also provides a nonlinear approach to reconstruction of meshes using the extracted basis, which is more effective than the current linear combination approach. Extensive experiments show that our method outperforms state-of-the-art methods in both qualitative and quantitative evaluations.

PDF Details

AIIM Journal 2017 Journal Article

Drug repositioning based on triangularly balanced structure for tissue-specific diseases in incomplete interactome

Liang Yu
Jin Zhao
Lin Gao

Finding new uses for existing drugs has become a new strategy for decades to treat more patients. Few traditional approaches consider the tissue specificities of diseases. Moreover, disease genes, drug targets and protein interaction (PPI) networks remain largely incomplete and the relationships between drugs and diseases conform to the triangularly balanced structure. Therefore, based on tissue specificities of diseases, we apply the triangularly balanced theory and the module distance defined for incomplete interaction networks to build drug-disease associations. Our method is named as TTMD (Tissue specificity, Triangle balance theory and Module Distance). Firstly, we combine three different drug similarity networks. Then, in the tissue-specific PPI network of a disease, we calculate its similarities with drugs using module distance. Finally, breast cancer and hepatocellular carcinoma (HCC) are taken as case studies. In the top-5% of predicted associations, 96. 9% and 90. 3% results match with known associations in Comparative Toxicogenomics Database (CTD) for breast cancer and hepatocellular carcinoma respectively. Clinical verification, literature mining and KEGG pathways enrichment analysis are further conducted for the top-5% newly predicted associations. Overall, TTMD is an effective approach for predicting new drug indications for tissue-specific diseases and provides potential values for the treatments of complex diseases.

Details DOI