Explanipedia

Social Context-Aware Community-Level Propagation Prediction Open

J. Gao, Xiao Wang, Tian Gan, Jianhua Yin, Chuanchen Luo , et al. · 2025

A hybrid framework for classifying and detecting aircraft cabin anomalous sounds under heavy background noise Open

Jiaan Chen, Tian Gan, Chenyi Zhao, Huayong Zhao, Ci Song , et al. · 2025

Anomalous sounds produced in an aircraft cabin are early warnings of potential safety hazards, yet they are hard to label and detect when masked by heavy background noise. A two-stage hybrid framework is introduced to tackle both challenge…

A Hybrid Framework for Classifying and Detecting Aircraft Cabin Anomalous Sounds Under Heavy Background Noise Open

Jiaan Chen, Tian Gan, Chenyi Zhao, Huayong Zhao, Ci Song , et al. · 2025

Experimental and Numerical Investigation on Stress Corrosion Behavior of Defective 2195-T8 Al-Li Alloys in Acid Solutions Open

Dejun Liu, Tian Gan, Xinzhi Yang, Mengqing Liu, Biyun Ren , et al. · 2025

Evaluation of renal allograft function by diffusion tensor imaging and diffusion weighted imaging Open

Wenxin Li, Shiliang Ge, Feng Gao, Jun Zhang, Xiaolu Liu , et al. · 2024

Objective: To investigate the value of diffusion tensor imaging (DTI), diffusion-weighted imaging (DWI), and arterial spin labeling (ASL) imaging techniques in allograft kidneys. Materials and Methods: This study was approved by the instit…

Social Debiasing for Fair Multi-modal LLMs Open

Harry H. Cheng, Yangyang Guo, Qingpei Guo, Ming Yang, Tian Gan , et al. · 2024

Multi-modal Large Language Models (MLLMs) have dramatically advanced the research field and delivered powerful vision-language understanding capabilities. However, these models often inherit deep-rooted social biases from their training da…

Knowledge-enhanced Multi-perspective Video Representation Learning for Scene Recognition Open

Xuzheng Yu, Chen Jiang, Wei Zhang, Tian Gan, Linlin Chao , et al. · 2024

With the explosive growth of video data in real-world applications, a comprehensive representation of videos becomes increasingly important. In this paper, we address the problem of video scene recognition, whose goal is to learn a high-le…

Shock Wave and Highly Turbulent Boundary Layer Interaction Controlled by Surface Arc Plasma Actuation Open

Qiong Wang, Tian Gan, xiaoyue Xie · 2024

RTQ: Rethinking Video-language Understanding Based on Image-text Model Open

Xiao Wang, Yaoyu Li, Tian Gan, Zheng Zhang, Jingjing Lv , et al. · 2023

Recent advancements in video-language understanding have been established on\nthe foundation of image-text models, resulting in promising outcomes due to the\nshared knowledge between images and videos. However, video-language\nunderstandi…

Temporal Sentence Grounding in Streaming Videos Open

Tian Gan, Xiao Wang, Yan Sun, Jianlong Wu, Qingpei Guo , et al. · 2023

This paper aims to tackle a novel task - Temporal Sentence Grounding in\nStreaming Videos (TSGSV). The goal of TSGSV is to evaluate the relevance\nbetween a video stream and a given sentence query. Unlike regular videos,\nstreaming videos …

EVE: Efficient zero-shot text-based Video Editing with Depth Map Guidance and Temporal Consistency Constraints Open

Yutao Chen, Xingning Dong, Tian Gan, Chunluan Zhou, Ming–Hsuan Yang , et al. · 2023

Motivated by the superior performance of image diffusion models, more and more researchers strive to extend these models to the text-based video editing task. Nevertheless, current video editing tasks mainly suffer from the dilemma between…

SNP-S<sup>3</sup>: Shared Network Pre-Training and Significant Semantic Strengthening for Various Video-Text Tasks Open

Xingning Dong, Qingpei Guo, Tian Gan, Qing Wang, Jianlong Wu , et al. · 2023

We present a framework for learning cross-modal video representations by\ndirectly pre-training on raw data to facilitate various downstream video-text\ntasks. Our main contributions lie in the pre-training framework and proxy\ntasks. Firs…

Research on Parameter Optimization of the Optimal Schedule Model of Water Resources for the Jiaodong Water Transfer Project Based on the ICCP Model Open

Ranhang Zhao, Tian Gan, Xingju Wang, Haofang Wang · 2023

Establishing an optimal operation model of water resources is a crucial mean to promote the social and economic development in the Jiaodong area, where water resources are seriously deficient. Constraints of the optimal operation model mai…

Active flow control and its applications in supersonic boundary layer Open

Tian Gan · 2023

Boundary layer transition is a typical aerodynamic phenomenon in supersonic flow that refers to the transition of the boundary layer from laminar flow to turbulent flow. The instabilities and transition mechanisms are complicated. A turbul…

Self-adaptive Context and Modal-interaction Modeling For Multimodal Emotion Recognition Open

Haozhe Yang, Xianqiang Gao, Jianlong Wu, Tian Gan, Ning Ding , et al. · 2023

The multimodal emotion recognition in conversation task aims to predict the emotion label for a given utterance with its context and multiple modalities. Existing approaches achieve good results but also suffer from the following two limit…

Visualization study of perturbations induced by plasma actuators and its effect on shock wave/boundary-layer interaction Open

Tian Gan, Qiong Wang, Wenjun Gan, Jieming Zhang · 2022

Surface arc plasma actuator array is used to control the shock wave/boundary-layer interaction in a Ma = 2 flow. Two types of interaction are examined. The flow topology of Surface arc plasma actuator array operating at high-frequency is f…

Micro-video Tagging via Jointly Modeling Social Influence and Tag Relation Open

Xiao Wang, Tian Gan, Yinwei Wei, Jianlong Wu, Meng Dai , et al. · 2022

The last decade has witnessed the proliferation of micro-videos on various user-generated content platforms. According to our statistics, around 85.7\% of micro-videos lack annotation. In this paper, we focus on annotating micro-videos wit…

Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation Open

Xingning Dong, Tian Gan, Xuemeng Song, Jianlong Wu, Yuan Cheng , et al. · 2022

Scene Graph Generation, which generally follows a regular encoder-decoder pipeline, aims to first encode the visual contents within the given image and then parse them into a compact summary graph. Existing SGG approaches generally not onl…

Experimental Study on Boundary Layer Transition Using Surface Arc Plasma Actuators Open

Tian Gan · 2022

Experimental Study on Boundary Layer Transition Using Surface Arc Plasma Actuators Open

Tian Gan, Qiong Wang · 2022

Editorial Open

Meng Liu, Yan Yan, Tian Gan, Hua Huang, Mohan Kankanhalli · 2021

Effects of copy number variations on brain structure and risk for psychiatric illness: Large-scale studies from the ENIGMA Working Groups on CNVs Open

Ida E. Sønderby, Christopher R. K. Ching, Sophia I. Thomopoulos, Dennis van der Meer, Julio E. Villalón‐Reina , et al. · 2021

The Enhancing Neuroimaging Genetics through Meta-Analysis copy number variant (ENIGMA-CNV) and 22q11.2 Deletion Syndrome Working Groups (22q-ENIGMA WGs) were created to gain insight into the involvement of genetic factors in human brain de…

The Effect of Fixing Method on the Result of Ultrasonic Infrared Thermography Testing Open

Tian Gan, Fazhong Li, Shuaixing Feng, Haohao Wan, Guangjie Kou · 2021

Considering the influence of the fixing method of the component in the system on its results in ultrasonic infrared thermography testing, the detection experiments of the cracked plat structure with fixing at one end and fixing at two ends…

Comprehensive Exploration and three-dimensional construction technology of water plug based on directional horizontal drilling caved column Open

Tian Gan · 2021

The ordovician limestone water inrush accident occurred during the excavation of 8228 working face in Tashan Coal Mine, Tongmei Group. On the basis of comprehensive geophysical exploration above and below the well, in order to find out the…

Re-examining the Role of Schema Linking in Text-to-SQL Open

Wenqiang Lei, Weixin Wang, Zhixin Ma, Tian Gan, Wei Lu , et al. · 2020

In existing sophisticated text-to-SQL models, schema linking is often considered as a simple, minor component, belying its importance. By providing a schema linking corpus based on the Spider text-to-SQL dataset, we systematically study th…

Shock-Wave/Boundary-Layer Interactions at Compression Ramps Studied by High-Speed Schlieren Open

Zhengzhong Sun, Tian Gan, Yun Wu · 2019

The shock wave boundary layer interactions (SWBLIs) at compression ramps (ramp angle α=20o -30o ) are studied at Ma=2.0 and under two Reynolds numbers (Re1=18,600 and Re2=35,600, Re based on boundary layer thickness). High-speed schlieren …

Explicit Interaction Model towards Text Classification Open

Cunxiao Du, Zhaozheng Chen, Fuli Feng, Lei Zhu, Tian Gan , et al. · 2019

Text classification is one of the fundamental tasks in natural language processing. Recently, deep neural networks have achieved promising performance in the text classification task compared to shallow models. Despite of the significance …

Numerical Analysis of Influencing Factors and Capability for Line Laser Scanning Thermography Nondestructive Testing Technology in Chemicals Corrosion Defect Detection Open

Zhengwei Yang, Xie Xingyu, Yin Li, Tian Gan · 2019

A new Infrared Thermal Wave Nondestructive Testing (IR TWNDT) technology—line laser scanning thermography nondestructive testing (LLST NDT) technology is applied to detect the defect that caused by chemicals corrosion. The heat conduction …

Study on Mechanism of In-Situ Stress Control on the Coal Floor Damage During Deep Coal Seam Mining Open

Tian Gan · 2019

In order to study on mechanism of in-situ stress control on the coal floor damage during deep coal seam mining, the internal relationship among ground stress, mine pressure and floor water inrush was analyzed base on the increasing distrib…

Inspection Detectability Improvement for Metal Defects Detected by Pulsed Infrared Thermography Open

Zhengwei Yang, Guangjie Kou, Yin Li, Tian Gan, Wei Zhang , et al. · 2019

Tian Gan YOU? Author Swipe