22 citations · 45 across the 11 of their papers we have counts for
11 papers
FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning
Haozheng Luo, Zhuolin Jiang, Md Zahid Hasan +2
We propose FROST, an attention-aware method for efficient reasoning. Unlike traditional approaches, FROST leverages attention weights to prune uncritical reasoning paths, yielding…
Speech Synthesis as Augmentation for Low-Resource ASR
Deblin Bagchi, Shannon Wotherspoon, Zhuolin Jiang +1
Speech synthesis might hold the key to low-resource speech recognition. Data augmentation techniques have become an essential part of modern speech recognition training. Yet, they…
Learning from Noisy Labels with Noise Modeling Network
Zhuolin Jiang, Jan Silovsky, Man-Hung Siu +3
Multi-label image classification has generated significant interest in recent years and the performance of such systems often suffers from the not so infrequent occurrence of incor…
Combining Word Embeddings and N-grams for Unsupervised Document Summarization
Zhuolin Jiang, Manaj Srivastava, Sanjay Krishna +2
Graph-based extractive document summarization relies on the quality of the sentence similarity graph. Bag-of-words or tf-idf based sentence similarity uses exact word matching, but…
Cross-lingual Information Retrieval with BERT
Zhuolin Jiang, Amro El-Jaroudi, William Hartmann +2
Multiple neural language models have been developed recently, e.g., BERT and XLNet, and achieved impressive results in various NLP tasks including sentence classification, question…
Towards a New Understanding of the Training of Neural Networks with Mislabeled Training Data
Herbert Gish, Jan Silovsky, Man-Ling Sung +3
We investigate the problem of machine learning with mislabeled training data. We try to make the effects of mislabeled training better understood through analysis of the basic mode…
Learning Spatiotemporal Features for Infrared Action Recognition with 3D Convolutional Neural Networks
Zhuolin Jiang, Viktor Rozgic, Sancar Adali
Infrared (IR) imaging has the potential to enable more robust action recognition systems compared to visible spectrum cameras due to lower sensitivity to lighting conditions and ap…
Learning Discriminative Features via Label Consistent Neural Network
Zhuolin Jiang, Yaming Wang, Larry Davis +2
Deep Convolutional Neural Networks (CNN) enforces supervised information only at the output layer, and hidden layers are trained by back propagating the prediction error from the o…
Collaborative Receptive Field Learning
Shu Kong, Zhuolin Jiang, Qiang Yang
The challenge of object categorization in images is largely due to arbitrary translations and scales of the foreground objects. To attack this difficulty, we propose a new approach…
Learning Mid-Level Features and Modeling Neuron Selectivity for Image Classification
Shu Kong, Zhuolin Jiang, Qiang Yang
We now know that mid-level features can greatly enhance the performance of image learning, but how to automatically learn the image features efficiently and in an unsupervised mann…
Sparse Dictionary-based Attributes for Action Recognition and Summarization
Qiang Qiu, Zhuolin Jiang, Rama Chellappa
We present an approach for dictionary learning of action attributes via information maximization. We unify the class distribution and appearance information into an objective funct…