• Publications
  • Influence
Semantic Structure and Interpretability of Word Embeddings
TLDR
Dense word embeddings are substantially successful in capturing semantic relations among words, so a meaningful semantic structure must be present in the respective vector spaces. Expand
  • 43
  • 3
  • PDF
MARVEL: A Large-Scale Image Dataset for Maritime Vessels
TLDR
We introduce a large-scale image dataset for maritime vessels, consisting of 2 million user uploaded images and their attributes including vessel identity, type, photograph category and year of built, collected from a community website. Expand
  • 28
  • 3
Generic and attribute-specific deep representations for maritime vessels
TLDR
We introduced MARVEL, a large-scale image dataset for maritime vessels, consisting of 2 million user-uploaded images and their various attributes, including vessel identity, type, category, year built, length, and tonnage, collected from a community website. Expand
  • 10
Deep distance metric learning for maritime vessel identification
TLDR
This paper addresses the problem of maritime vessel identification by exploiting the state-of-the-art techniques of distance metric learning and deep convolutional neural networks since vessels are the key constituents of marine surveillance. Expand
  • 5
Measuring cross-lingual semantic similarity across European languages
TLDR
This paper studies cross-lingual semantic similarity (CLSS) between five European languages (i.e. English, French, German, Spanish and Italian) via unsupervised word embeddings from a cross- lingual lexicon. Expand
  • 8
Deep learning-based fine-grained car make/model classification for visual surveillance
TLDR
Fine-grained object recognition is a potential computer vision problem that has been recently addressed by utilizing deep Convolutional Neural Networks (CNNs). Expand
  • 3
Learning traffic congestion by contextual bandit problems for optimum localization
TLDR
A contextual multi-armed bandit learner tries to determine the underlying traffic with simple assumptions of the optimum localization problem. Expand
  • 4
Generating Semantic Similarity Atlas for Natural Languages
TLDR
We leverage a recently proposed word embedding based method to generate a language similarity atlas for 76 different languages around the world. Expand
  • 3
Semantic similarity between Turkish and European languages using word embeddings
TLDR
In this study, semantic similarity between Turkish (two different corpora) and five basic European languages is calculated using word embeddings over a fixed vocabulary, obtained results are verified using statistical testing. Expand
  • 3
Fine-grained recognition of maritime vessels and land vehicles by deep feature embedding
TLDR
A multi-task learning framework for fine-grained visual recognition of maritime vessels and land vehicles using publicly available data sets. Expand
  • 6
...
1
2
3
...