A5115621122- Topic Modeling
- Plant Water Relations and Carbon Dynamics
- Natural Language Processing Techniques
- Remote Sensing in Agriculture
- Tree-ring climate responses
- Probabilistic and Robust Engineering Design
- Sentiment Analysis and Opinion Mining
- Land Use and Ecosystem Services
- Speech Recognition and Synthesis
- Seismic Imaging and Inversion Techniques
- Statistical Distribution Estimation and Applications
- Web Data Mining and Analysis
- Cooperative Communication and Network Coding
- Ideological and Political Education
- Semantic Web and Ontologies
- Mechanical Engineering and Vibrations Research
- Hate Speech and Cyberbullying Detection
- Higher Education and Teaching Methods
- Coal Properties and Utilization
- Advanced Text Analysis Techniques
- Educational Technology and Pedagogy
- Climate variability and models
- Optimization and Variational Analysis
- Translation Studies and Practices
- Video Surveillance and Tracking Methods
Jingdong (China)
2019-2025
China University of Petroleum, East China
2025
Institute of Software
2025
Beijing Normal University
2022-2024
Jishou University
2021-2024
State Key Laboratory of Remote Sensing Science
2022-2023
National Institute of Metrology
2021
Taizhou Vocational and Technical College
2010
The significance of visual emotion distribution learning (VEDL) has surged, particularly with the growing inclination to convey emotions through images. key VEDL lies in capturing both low- and high-level features within same content, thus promoting model for salient subtle awareness. To learn involved images, most previous works coarse semantic knowledge unbiased filtering. Consequently, they focus on entire scene suffer from redundancy semantic-irrelevant information, which diminishes...
Maximum ranked set sampling with unequal samples is a procedure used to reduce the error of ranking observations and increase efficiency statistical inference. It for maximum likelihood estimation location shape parameters inverse Gaussian distribution. Its asymptotic at least 1.4 times higher than those estimators based on simple random sampling. useful in reliability studies Bayesian statistics involving
Quick and accurate extraction of un-collapsed buildings from post-disaster High-resolution Remote Sensing Images (HRSIs) is imperative for emergency response. Pre-disaster HRSIs could serve as auxiliary data training models to expedite this process. However, the effectiveness trained directly on pre-disaster tends diminish when applied scenarios, mainly due notable discrepancies between these datasets. The current popular approach mitigate issue involves aligning features pre- images using...
Accurate knowledge of urban forest patterns contributes to well-managed urbanization, but accurate tree canopy mapping is still a challenging task because the complexity structure. In this paper, new method that combines double-branch U-NET with multi-temporal satellite images containing phenological information introduced accurately map canopies. Based on constructed GF-2 image dataset, we developed based feature fusion strategy using obtain an accuracy improvement IOU (intersection over...
Supplementing product attribute information is a critical step for E-commerce platforms, which further benefits various downstream tasks, including recommendation, search, and knowledge graph construction. Intuitively, the visual available on e-commerce platforms can effectively function as primary source certain attributes. However, existing works either extract values solely from textual descriptions or leverage limited (e.g., image features optical character recognition tokens) to assist...
One of the major difficulties in processing and interpreting seismic data is contamination signals by noise from numerous sources. Conventional denoising methods are mostly used for 2D data, but also exists 3D space, resulting poor results using conventional methods. Consequently, here, denoising, a multiscale multidirectional curvelet transform was adopted. Our study combined core principle approach with threshold iteration method to denoise simulated actual varying signal-to-noise ratios,...
Due to the complex reservoir conditions and rapid changes in lithological facies seismic exploration, predicting coalbed methane (CBM) reservoirs is quite challenging. Conventional inversion methods are not highly effective at thickness, cannot keep up with current demands. Our aim demonstrate how data can be used forecast coal as well distribution orientation of subtle structures that may linked enhanced permeability zones. In this study, we a nonlinear stochastic method based on making...
Building Spoken Language Understanding (SLU) robust to Automatic Speech Recognition (ASR) errors is an essential issue for various voice-enabled virtual assistants. Considering that most ASR are caused by phonetic confusion between similar-sounding expressions, intuitively, leveraging the phoneme sequence of speech can complement hypothesis and enhance robustness SLU. This paper proposes a novel model with Cross Attention SLU (denoted as CASLU). The cross attention block devised catch...
Span-level masked language modeling (MLM) has shown to be advantageous pre-trained models over the original single-token MLM, as entities/phrases and their dependencies are critical understanding. Previous works only consider span length with some discrete distributions, while among spans ignored, i.e., assuming that positions of uniformly distributed. In this paper, we present POSPAN, a general framework allow diverse position-constrained masking strategies via combination distribution...
In this paper, the influence of reversibility on uncertainty torque measurement is studied. The distribution standard sensor not a known common distribution, so its coverage factor k cannot be determined like other well-defined distribution. order to explore characteristics sensor, original definition will used for calculation and analysis. By using discrete continuous analysis methods, we discuss actual applied in increasing decreasing steps, then calculate interval, finally determine k....