Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleOctober 2024
TVNeRF: Improving few-view neural volume rendering with total variation maximization
AbstractNeural Radiance Fields (NeRF) has profoundly impacted few-shot novel view synthesis and 3D reconstruction with its innovative rendering techniques and high-quality output. However, synthesizing novel views from sparse inputs remains challenging ...
Highlights- Defined the total variation noise of rays.
- Proposed the total variation regularization method to understand 3D geometric information.
- Proposed two opacity regularization methods of rays to remove floater.
- Enhancing the ...
- ArticleOctober 2024
SimTxtSeg: Weakly-Supervised Medical Image Segmentation with Simple Text Cues
Medical Image Computing and Computer Assisted Intervention – MICCAI 2024Pages 634–644https://doi.org/10.1007/978-3-031-72111-3_60AbstractWeakly-supervised medical image segmentation is a challenging task that aims to reduce the annotation cost while keep the segmentation performance. In this paper, we present a novel framework, SimTxtSeg, that leverages simple text cues to generate ...
- ArticleOctober 2024
KDProR: A Knowledge-Decoupling Probabilistic Framework for Video-Text Retrieval
AbstractExisting video-text retrieval methods predominantly focus on designing diverse cross-modal interaction mechanisms between captions and videos. However, those approaches diverge from human learning paradigms, where humans possess the capability to ...
- research-articleJanuary 2025
T2TNet: Tree-to-Transformer Neural Network for High-precision Prediction of Ship Machinery Noise
CFIMA '24: Proceedings of the 2024 2nd International Conference on Frontiers of Intelligent Manufacturing and AutomationPages 472–477https://doi.org/10.1145/3704558.3707659Traditional ship machinery noise prediction methods face many challenges, including cumbersome data processing procedures, numerous complex coupling factors, and poor generalization capabilities. In response to these issues, this paper proposes an ...
- research-articleJanuary 2024
Spatiotemporal prediction of carbon emissions using a hybrid deep learning model considering temporal and spatial correlations
Environmental Modelling & Software (ENMS), Volume 172, Issue Chttps://doi.org/10.1016/j.envsoft.2023.105937AbstractAccurate prediction of carbon emissions plays a crucial role in enabling government decision-makers to formulate appropriate policies and plan necessary response measures in a timely manner. This study explored the spatiotemporal prediction ...
Highlights- We propose a deep learning-based hybrid prediction model for carbon emissions.
- The model considers temporal and spatial correlations.
- The model enables one- and multi-step spatiotemporal prediction of carbon emissions.
- The ...
- research-articleDecember 2023
The association between adult attachment and problematic Internet use: A three-level meta-analysis
Abstract Background and aimsProblematic Internet use (PIU; generalized PIU and specific PIU) is an emerging public health issue associated with various negative mental health indicators. Adult attachment, which refers to individuals' views of the self ...
Highlights- The association between adult attachment and PIU was identified using a three-level meta-analysis approach.
- Insecure attachment was positively correlated with PIU, while secure attachment was negatively correlated with PIU.
- ...
- research-articleAugust 2023
Learning Balanced Tree Indexes for Large-Scale Vector Retrieval
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 1353–1362https://doi.org/10.1145/3580305.3599406Vector retrieval focuses on finding the k-nearest neighbors from a bunch of data points, and is widely used in a diverse set of areas such as information retrieval and recommender system. The current state-of-the-art methods represented by HNSW usually ...
- rapid-communicationSeptember 2021
Bio-inspired adaptive formation tracking control for swarm systems with application to UAV swarm systems
Neurocomputing (NEUROC), Volume 453, Issue CPages 272–285https://doi.org/10.1016/j.neucom.2021.05.015AbstractAdaptive formation tracking problems for swarm systems with multiple leaders and switching topologies are studied in this paper. It is required that the followers form time-varying formations and track the positions of the leaders ...
- research-articleJanuary 2020
Prediction method of cyanobacterial blooms spatial-temporal sequence based on deep belief network and fuzzy expert system
- Li Wang,
- Yuxin Xie,
- Jiping Xu,
- Huiyan Zhang,
- Xiaoyi Wang,
- Jiabin Yu,
- Qian Sun,
- Zhiyao Zhao,
- Mohamed Elhoseny,
- X. Yuan
Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology (JIFS), Volume 38, Issue 2Pages 1487–1498https://doi.org/10.3233/JIFS-179512The process of cyanobacteria bloom in rivers and lakes is a highly non-stationary and non-linear process. The existing cyanobacterial bloom prediction method mainly uses time series model and single intelligent model, but time series model and single ...
- research-articleJanuary 2020
An approach of recursive timing deep belief network for algal bloom forecasting
- Li Wang,
- Tianrui Zhang,
- Xuebo Jin,
- Jiping Xu,
- Xiaoyi Wang,
- Huiyan Zhang,
- Jiabin Yu,
- Qian Sun,
- Zhiyao Zhao,
- Yuxin Xie
Neural Computing and Applications (NCAA), Volume 32, Issue 1Pages 163–171https://doi.org/10.1007/s00521-018-3790-9AbstractThe forecasting methods of water bloom in existence are hard to reflect nonlinear dynamic change in algal bloom formation mechanism, leading to poor forecasting accuracy of bloom. To solve this problem, this paper deeply analyzes the generation ...
- ArticleAugust 2007
A Modified PSVM and its Application to Unbalanced Data Classification
ICNC '07: Proceedings of the Third International Conference on Natural Computation - Volume 01Pages 488–490https://doi.org/10.1109/ICNC.2007.68A modified proximal support vector machine (MPSVM) is presented for the case of unbalanced data classification in many applications. The algorithm assigns different penalty coefficients to the positive and negative samples respectively by adding a new ...