This work was supported by the Development Project of Jilin Province of China(20200801033GH,2020122328JC);the Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education,Jilin University(20180520017JH);the Fundamental Research Funds for the Central Universities,JLU.
Weakly supervised semantic segmentation using only image-level labels is critical since it alleviates the need for expensive pixel-level labels.Most cuttingedge methods adopt two-step solutions that learn to produce p...
supported by the National Natural Science Foundation of China(61976124,61976125,61773244,61772319,61772250).
To solve the problem of semantic loss in text representation,this paper proposes a new embedding method of word representation in semantic space called wt2svec based on supervised latent Dirichlet allocation(SLDA)and ...
supported by the Development Project of Jilin Province of China (No.20200801033GH, No.2020122328JC);Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education;Jilin University (No.20180520017JH);the Fundamental Research Funds for the Central Universities,JLU。
This paper studies semantic segmentation primarily under image-level weak-supervision. Most stateof-the-art technologies have recently used deep classification networks to create small and sparse discriminatory seed r...
supported by the National Natural Science Foundation of China(No.61772152);the National Key Research and Development Program of China(No.2018YFC0806800);the Technical Basic Research Project(No.JSQB2017206C002);the Project funded by China Postdoctoral Science Foundation(No.2019M651262);the Youth Fund Project of Humanities and Social Sciences Research of the Ministry of Education of China(No.20YJCZH172);the Postdoctoral Foundation of Heilongjiang Province(No.LBH-Z19015).
A classifier trained on the label-rich source dataset tends to perform poorly on the unlabeled target dataset because of the distribution discrepancy across different datasets.Unsupervised domain adaptation aims to tr...
supported by the National Natural Science Foundation of China(No.61572523,No.61873281,No.61572522)。
Text similarity measurements are the basis for measuring the degree of matching between two or more texts. Traditional large-scale similarity detection methods based on a digital fingerprint have the advantage of high...
supported by the National Natural Science Foundation of China(No.61772081,No.61602044);the Science and Technology Development Project of Beijing Municipal Education Commission(No.KM201711232014)
The major challenge that text sentiment classification modeling faces is how to capture the intrinsic semantic, emotional dependence information and the key part of the emotional expression of text. To solve this prob...
supported by National Grand Fundamental Research 973 Program of China(No.2009CB320706,No.2010CB32813);National Core-Hightech-Basic Project(No.2010ZX01045-001-008);the National Nature Science Foundation of China(No.61170001)
A program,when being executed,acts like a mirror that produces mirror images for objects in front of it.A mirror distinguishes itself from others by the way how it changes the shape of an object.A program can be chara...
supported by the Scientific Research Fund of Heilongjiang Provincial Education Department(No.12521055);the Youth Foundation of Northeast Petroleum University(No.2013NQ120,No.2012QN117)
Along with the explosive growth of images, automatic image annotation has attracted great interest of various research communities. However, despite the great progress achieved in the past two decades, automatic annot...
supported by the National Natural Science Foundation of China(No.60973040,No.61300148,No.60903098);the Key Scientific and Technological Break-through Program of Jilin Province(No.20130206051GX)
Measuring word semantic similarity is a generic problem with a broad range of applications such as ontology mapping, computational linguistics and artificial intelligence. Previous approaches to computing word semanti...
supported by the National Natural Science Foundation of China(No.61070205,No.61272520)
As the development of Internet of things (IOT), massive sensors have been deployed as the public infrastructure. With the development of in-depth applica- tions in IOT, service discovery and composition are chal- le...