L
Long Chen
Researcher at Columbia University
Publications - 68
Citations - 4080
Long Chen is an academic researcher from Columbia University. The author has contributed to research in topics: Computer science & Question answering. The author has an hindex of 14, co-authored 55 publications receiving 2553 citations. Previous affiliations of Long Chen include Tencent & Northwestern University.
Papers
More filters
Proceedings ArticleDOI
SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks for Image Captioning
TL;DR: This paper introduces a novel convolutional neural network dubbed SCA-CNN that incorporates Spatial and Channel-wise Attentions in a CNN that significantly outperforms state-of-the-art visual attention-based image captioning methods.
Posted Content
SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning
TL;DR: SCA-CNN as mentioned in this paper incorporates spatial and channel-wise attentions in a CNN to dynamically modulate the sentence generation context in multi-layer feature maps, encoding where attentive spatial locations at multiple layers and what (i.e., attentive channels) the visual attention is.
Proceedings ArticleDOI
Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding Networks
TL;DR: Through adversarial learning of the two subspaces, SP-AEN can transfer the semantics from the reconstructive subspace to the discriminative one, accomplishing the improved zero-shot recognition of unseen classes.
Proceedings ArticleDOI
Counterfactual Samples Synthesizing for Robust Visual Question Answering
TL;DR: A model-agnostic Counterfactual Samples Synthesizing (CSS) training scheme that significantly improves both visual-explainable and question-sensitive abilities of VQA models and, in return, the performance of these models is further boosted.
Journal ArticleDOI
Weakly-Supervised Deep Embedding for Product Review Sentiment Analysis
TL;DR: A novel deep learning framework for product review sentiment classification which employs prevalently available ratings as weak supervision signals and explores two kinds of low level network structure for modeling review sentences, namely, convolutional feature extractors and long short-term memory.