Contextual lstm (clstm) models for large scale nlp tasks

S Ghosh, O Vinyals, B Strope, S Roy, T Dean… - arxiv preprint arxiv …, 2016 - arxiv.org
Documents exhibit sequential structure at multiple levels of abstraction (eg, sentences,
paragraphs, sections). These abstractions constitute a natural hierarchy for representing the …

Mitigating test-time bias for fair image retrieval

F Kong, S Yuan, W Hao… - Advances in Neural …, 2024 - proceedings.neurips.cc
We address the challenge of generating fair and unbiased image retrieval results given
neutral textual queries (with no explicit gender or race connotations), while maintaining the …

Unsupervised deep feature learning for remote sensing image retrieval

X Tang, X Zhang, F Liu, L Jiao - Remote Sensing, 2018 - mdpi.com
Due to the specific characteristics and complicated contents of remote sensing (RS) images,
remote sensing image retrieval (RSIR) is always an open and tough research topic in the RS …

Aggregated deep local features for remote sensing image retrieval

R Imbriaco, C Sebastian, E Bondarev, PHN de With - Remote Sensing, 2019 - mdpi.com
Remote Sensing Image Retrieval remains a challenging topic due to the special nature of
Remote Sensing imagery. Such images contain various different semantic objects, which …

Understanding and predicting cross-cultural food preferences with online recipe images

Q Zhang, D Elsweiler, C Trattner - Information Processing & Management, 2023 - Elsevier
Predicting food preferences is challenging due to the numerous factors that can influence
individual taste. Cultural influences are one such factor that can significantly impact food …

Deep neural network approaches for detecting gastric polyps in endoscopic images

S Durak, B Bayram, T Bakırman, M Erkut… - Medical & Biological …, 2021 - Springer
Gastrointestinal endoscopy is the primary method used for the diagnosis and treatment of
gastric polyps. The early detection and removal of polyps is vitally important in preventing …

Utilizing a digital canvas to conduct a spatial-semantic search for digital visual media

Z Lin, M Long, J Brandt, H **, C Fang - US Patent 10,346,727, 2019 - Google Patents
The present disclosure includes methods and systems for searching for digital visual media
based on semantic and spatial information. In particular, one or more embodiments of the …

Learning of multimodal representations with random walks on the click graph

F Wu, X Lu, J Song, S Yan, ZM Zhang… - … on Image Processing, 2015 - ieeexplore.ieee.org
In multimedia information retrieval, most classic approaches tend to represent different
modalities of media in the same feature space. With the click data collected from the users' …

Localizing pedestrians in indoor environments using magnetic field data with term frequency paradigm and deep neural networks

I Ashraf, YB Zikria, S Hur, AK Bashir… - International Journal of …, 2021 - Springer
Indoor environments are challenging for global navigation satellite systems and cripple its
performance. Magnetic field data-based positioning and localization has emerged as a …

Deep learning based decomposition for visual navigation in industrial platforms

Y Djenouri, J Hatleskog, J Hjelmervik, E Bjorne… - Applied …, 2022 - Springer
In the heavy asset industry, such as oil & gas, offshore personnel need to locate various
equipment on the installation on a daily basis for inspection and maintenance purposes …