Zobrazeno 1 - 10
of 2 087
pro vyhledávání: '"The Tran, Hung"'
Content-based Recommender Systems (CRSs) play a crucial role in shaping user experiences in e-commerce, online advertising, and personalized recommendations. However, due to the vast amount of categorical features, the embedding tables used in CRS mo
Externí odkaz:
http://arxiv.org/abs/2411.13052
Autor:
Geis, Lukas, Allendorf, Daniel, Bläsius, Thomas, Leonhardt, Alexander, Meyer, Ulrich, Penschuck, Manuel, Tran, Hung
We consider a maximum entropy edge weight model for shortest path networks that allows for negative weights. Given a graph $G$ and possible weights $\mathcal{W}$ typically consisting of positive and negative values, the model selects edge weights $w
Externí odkaz:
http://arxiv.org/abs/2410.22717
Unsupervised domain adaptation (UDA) has become increasingly prevalent in scene text recognition (STR), especially where training and testing data reside in different domains. The efficacy of existing UDA approaches tends to degrade when there is a l
Externí odkaz:
http://arxiv.org/abs/2410.09913
Autor:
Jang, Jiwoong, Tran, Hung V.
Here, we study a discrete Coagulation-Fragmentation equation with a multiplicative coagulation kernel and a constant fragmentation kernel, which is critical. We apply the discrete Bernstein transform to the original Coagulation-Fragmentation equation
Externí odkaz:
http://arxiv.org/abs/2409.17974
Autor:
Cao, Xiaodong, Tran, Hung
[Dedicated to Richard S. Hamilton on forty years of Ricci flow] Gradient Ricci solitons have garnered significant attention both as self-similar solutions and singularity models of the Ricci flow. This survey article starts with a list of examples; i
Externí odkaz:
http://arxiv.org/abs/2409.13123
Recognizing human activities in videos is challenging due to the spatio-temporal complexity and context-dependence of human interactions. Prior studies often rely on single input modalities, such as RGB or skeletal data, limiting their ability to exp
Externí odkaz:
http://arxiv.org/abs/2409.02385
This paper reviews, analyzes, and proposes a new perspective on the bi-encoder architecture for neural search. While the bi-encoder architecture is widely used due to its simplicity and scalability at test time, it has some notable issues such as low
Externí odkaz:
http://arxiv.org/abs/2408.01094
Since the creation of the Web, recommender systems (RSs) have been an indispensable mechanism in information filtering. State-of-the-art RSs primarily depend on categorical features, which ecoded by embedding vectors, resulting in excessively large e
Externí odkaz:
http://arxiv.org/abs/2406.17335
The cosmological dynamics of multiple scalar/pseudoscalar fields are difficult to solve, especially when the field-space metric is curved. This presents a challenge in determining whether a given model can support cosmic acceleration, without solving
Externí odkaz:
http://arxiv.org/abs/2406.17030
Autor:
Le-Duc, Khai, Thulke, David, Tran, Hung-Phong, Vo-Dang, Long, Nguyen, Khai-Nguyen, Hy, Truong-Son, Schlüter, Ralf
Spoken Named Entity Recognition (NER) aims to extracting named entities from speech and categorizing them into types like person, location, organization, etc. In this work, we present VietMed-NER - the first spoken NER dataset in the medical domain.
Externí odkaz:
http://arxiv.org/abs/2406.13337