Search Results for author:
Found 15 papers, 3 papers with code
Density-aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement
The key procedure of haze image translation through adversarial training lies in the disentanglement between the feature only involved in haze synthesis, i. e. style feature, and the feature representing the invariant semantic content, i. e. content feature.
How to Generate a Good Word Embedding?
We analyze three critical components of word embedding training: the model, the corpus, and the training parameters.
Knowledge Graph Embedding via Dynamic Mapping Matrix
Ranked #8 on
Link Prediction
on FB15k
(MR metric)
Recurrent Convolutional Neural Networks for Text Classification
The experimental results show that the proposed method outperforms the state-of-the-art methods on several datasets, particularly on document-level datasets.
Ranked #4 on
Emotion Recognition in Conversation
on CPED
