Search Results for author:
Found 67 papers, 16 papers with code
A Visually-grounded First-person Dialogue Dataset with Verbal and Non-verbal Responses
The results demonstrate that first-person vision helps neural network models correctly understand human intentions, and the production of non-verbal responses is a challenging task like that of verbal responses.
Weakly Supervised Formula Learner for Solving Mathematical Problems
Existing work suggested solving this task with a two-phase approach, where the model first predicts formulas from questions and then calculates answers from such formulas.
Neural Networks in a Product of Hyperbolic Spaces
Therefore, we propose a novel method to extend a given HNN in a single space to a product of hyperbolic spaces.
How do people talk about images? A study on open-domain conversations with images.
This paper explores how humans conduct conversations with images by investigating an open-domain image conversation dataset, ImageChat.
RNSum: A Large-Scale Dataset for Automatic Release Note Generation via Commit Logs Summarization
A release note is a technical document that describes the latest changes to a software product and is crucial in open source software development.
Overview of the 8th Workshop on Asian Translation
This paper presents the results of the shared tasks from the 8th workshop on Asian translation (WAT2021).
Overview of the 7th Workshop on Asian Translation
This paper presents the results of the shared tasks from the 7th workshop on Asian translation (WAT2020).
Balancing Reconstruction and Editing Quality of GAN Inversion for Real Image Editing with StyleGAN Prior Latent Space
The exploration of the latent space in StyleGANs and GAN inversion exemplify impressive real-world image editing, yet the trade-off between reconstruction quality and editing quality remains an open problem.
LED: A Dataset for Life Event Extraction from Dialogs
Our proposed life event dialog dataset and in-depth analysis of IE frameworks will facilitate future research on life event extraction from conversations.
A-CAP: Anticipation Captioning with Commonsense Knowledge
Humans possess the capacity to reason about the future based on a sparse collection of visual cues acquired over time.
Character-Centric Story Visualization via Visual Planning and Token Alignment
This task requires machines to 1) understand long text inputs and 2) produce a globally consistent image sequence that illustrates the contents of the story.
StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoning
Existing automatic story evaluation methods place a premium on story lexical level coherence, deviating from human preference.
Towards Parameter-Efficient Integration of Pre-Trained Language Models In Temporal Video Grounding
This paper explores the task of Temporal Video Grounding (TVG) where, given an untrimmed video and a natural language sentence query, the goal is to recognize and determine temporal boundaries of action instances in the video described by the query.
Pixel to Binary Embedding Towards Robustness for CNNs
There are approaches to replace pixel values with binary embeddings to tackle the problem of adversarial perturbations, which successfully improve robustness.
OSSGAN: Open-Set Semi-Supervised Image Generation
We introduce a challenging training scheme of conditional GANs, called open-set semi-supervised image generation, where the training dataset consists of two parts: (i) labeled data and (ii) unlabeled data with samples belonging to one of the labeled data classes, namely, a closed-set, and samples not belonging to any of the labeled data classes, namely, an open-set.
NOC-REK: Novel Object Captioning with Retrieved Vocabulary from External Knowledge
We propose an end-to-end Novel Object Captioning with Retrieved vocabulary from External Knowledge method (NOC-REK), which simultaneously learns vocabulary retrieval and caption generation, successfully describing novel objects outside of the training dataset.
PPCD-GAN: Progressive Pruning and Class-Aware Distillation for Large-Scale Conditional GANs Compression
We push forward neural network compression research by exploiting a novel challenging task of large-scale conditional generative adversarial networks (GANs) compression.
SciXGen: A Scientific Paper Dataset for Context-Aware Text Generation
Generating texts in scientific papers requires not only capturing the content contained within the given input but also frequently acquiring the external information called \textit{context}.
Gradient-based Hyperparameter Optimization without Validation Data for Learning fom Limited Labels
Optimizing hyperparameters of machine learning algorithms especially for limited labeled data is important but difficult, because then obtaining enough validation data is practically impossible.
Graph Energy-based Model for Molecular Graph Generation
We present Graph Energy-based Model (GEM), an energy-based model for molecular graph generation.
Graph Energy-based Model for Substructure Preserving Molecular Design
It is common practice for chemists to search chemical databases based on substructures of compounds for finding molecules with desired properties.
Commonsense Knowledge Aware Concept Selection For Diverse and Informative Visual Storytelling
To enrich the candidate concepts, a commonsense knowledge graph is created for each image sequence from which the concept candidates are proposed.
GraphPlan: Story Generation by Planning with Event Graph
In this paper, we focus on planning a sequence of events assisted by event graphs, and use the events to guide the generator.
DJMix: Unsupervised Task-agnostic Augmentation for Improving Robustness
Convolutional Neural Networks (CNNs) are vulnerable to unseen noise on input images at the test time, and thus improving the robustness is crucial.
Supervised Visual Attention for Multimodal Neural Machine Translation
This paper proposed a supervised visual attention mechanism for multimodal neural machine translation (MNMT), trained with constraints based on manual alignments between words in a sentence and their corresponding regions of an image.
Graph-based Heuristic Search for Module Selection Procedure in Neural Module Network
To overcome this problem, existing work either included ground-truth program into training data or applied reinforcement learning to explore the program.
MADGAN: unsupervised Medical Anomaly Detection GAN using multiple adjacent brain MRI slice reconstruction
Therefore, we propose unsupervised Medical Anomaly Detection Generative Adversarial Network (MADGAN), a novel two-step method using GAN-based multiple adjacent brain MRI slice reconstruction to detect brain anomalies at different stages on multi-sequence structural MRI: (Reconstruction) Wasserstein loss with Gradient Penalty + 100 L1 loss-trained on 3 healthy brain axial MRI slices to reconstruct the next 3 ones-reconstructs unseen healthy/abnormal scans; (Diagnosis) Average L2 loss per scan discriminates them, comparing the ground truth/reconstructed slices.
Meta Approach to Data Augmentation Optimization
Data augmentation policies drastically improve the performance of image recognition tasks, especially when the policies are optimized for the target data and tasks.
Single Model Ensemble using Pseudo-Tags and Distinct Vectors
Model ensemble techniques often increase task performance in neural networks; however, they require increased time, memory, and management effort.
A Visually-Grounded Parallel Corpus with Phrase-to-Region Linking
To verify our dataset, we performed phrase localization experiments in both languages and investigated the effectiveness of our Japanese annotations as well as multilingual learning realized by our dataset.
Bridging the gap between AI and Healthcare sides: towards developing clinically relevant AI-powered diagnosis systems
Then, a questionnaire survey for physicians evaluates our pathology-aware Generative Adversarial Network (GAN)-based image augmentation projects in terms of Data Augmentation and physician training.
Unsupervised Discourse Constituency Parsing Using Viterbi EM
In this paper, we introduce an unsupervised discourse constituency parsing algorithm.
Incorporating Horizontal Connections in Convolution by Spatial Shuffling
In the view of the regular convolution's RF, the outputs of neurons in lower layers with smaller RF are bundled to create neurons in higher layers with larger RF.
Empirical Study of Easy and Hard Examples in CNN Training
In this work, we study the similarities of easy and hard examples respectively for different Convolutional Neural Network (CNN) architectures, assessing how those examples contribute to generalization.
Faster AutoAugment: Learning Augmentation Strategies using Backpropagation
In this paper, we propose a differentiable policy search pipeline for data augmentation, which is much faster than previous methods.
Ranked #1 on
Data Augmentation
on CIFAR-10
Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posterior
By decoding multiple initial latent variables in parallel and rescore using a teacher model, the proposed model further brings the gap down to 1. 0 BLEU point on WMT'14 En-De task with 6. 8x speedup.
Generating Diverse Translations with Sentence Codes
In this work, we attempt to obtain diverse translations by using sentence codes to condition the sentence generation.
GAN-based Multiple Adjacent Brain MRI Slice Reconstruction for Unsupervised Alzheimer's Disease Diagnosis
Unsupervised learning can discover various unseen diseases, relying on large-scale unannotated medical images of healthy subjects.
Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-based CT Image Augmentation for Object Detection
Accurate Computer-Assisted Diagnosis, relying on large-scale annotated pathological images, can alleviate the risk of overlooking the diagnosis.
Enabling Real-time Neural IME with Incremental Vocabulary Selection
Input method editor (IME) converts sequential alphabet key inputs to words in a target language.
Combining Noise-to-Image and Image-to-Image GANs: Brain MR Image Augmentation for Tumor Detection
In this context, Generative Adversarial Networks (GANs) can synthesize realistic/diverse additional training images to fill the data lack in the real image distribution; researchers have improved classification by augmenting data with noise-to-image (e. g., random noise samples to diverse pathological images) or image-to-image GANs (e. g., a benign image to a malignant one).
Investigating CNNs' Learning Representation under label noise
Deep convolutional neural networks (CNNs) are known to be robust against label noise on extensive datasets.
USE-Net: incorporating Squeeze-and-Excitation blocks into U-Net for prostate zonal segmentation of multi-institutional MRI datasets
The following mixed scheme is used for training/testing: (i) training on either each individual dataset or multiple prostate MRI datasets and (ii) testing on all three datasets with all possible training/testing combinations.
Learning More with Less: GAN-based Medical Image Augmentation
Convolutional Neural Network (CNN)-based accurate prediction typically requires large-scale annotated training data.
Infinite Brain MR Images: PGGAN-based Data Augmentation for Tumor Detection
Due to the lack of available annotated medical images, accurate computer-assisted diagnosis requires intensive Data Augmentation (DA) techniques, such as geometric/intensity transformations of original images; however, those transformed images intrinsically have a similar distribution to the original ones, leading to limited performance improvement.
CNN-based Prostate Zonal Segmentation on T2-weighted MR Images: A Cross-dataset Study
Prostate cancer is the most common cancer among US men.
Unifying semi-supervised and robust learning by mixup
In this study, we consider learning from bi-quality data as a generalization of these studies, in which a small portion of data is cleanly labeled, and the rest is corrupt.
Learning More with Less: Conditional PGGAN-based Data Augmentation for Brain Metastases Detection Using Highly-Rough Annotation on MR Images
Accurate Computer-Assisted Diagnosis, associated with proper data wrangling, can alleviate the risk of overlooking the diagnosis in a clinical environment.
Real-time Neural-based Input Method
The input method is an essential service on every mobile and desktop devices that provides text suggestions.
Semantic Aware Attention Based Deep Object Co-segmentation
Object co-segmentation is the task of segmenting the same objects from multiple images.
Discrete Structural Planning for Generating Diverse Translations
Planning is important for humans when producing complex languages, which is a missing part in current language generation models.
Discrete Structural Planning for Neural Machine Translation
Structural planning is important for producing long sentences, which is a missing part in current language generation models.
Improving Beam Search by Removing Monotonic Constraint for Neural Machine Translation
However, as the algorithm produces hypotheses in a monotonic left-to-right order, a hypothesis can not be revisited once it is discarded.
Coherence Modeling Improves Implicit Discourse Relation Recognition
The research described in this paper examines how to learn linguistic knowledge associated with discourse relations from unlabeled corpora.
Implicit Discourse Relation Classification
Transfer Learning
Deep Learning for Forecasting Stock Returns in the Cross-Section
Many studies have been undertaken by using machine learning techniques, including neural networks, to predict stock returns.
Parameter Reference Loss for Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) aims to utilize labeled data from a source domain to learn a model that generalizes to a target domain of unlabeled data.
Compressing Word Embeddings via Deep Compositional Code Learning
For each word, the composition of basis vectors is determined by a hash code.
Ranked #10 on
Machine Translation
on IWSLT2015 German-English
Word Ordering as Unsupervised Learning Towards Syntactically Plausible Word Representations
The research question we explore in this study is how to obtain syntactically plausible word representations without using human annotations.
Single-Queue Decoding for Neural Machine Translation
Neural machine translation models rely on the beam search algorithm for decoding.
Later-stage Minimum Bayes-Risk Decoding for Neural Machine Translation
For extended periods of time, sequence generation models rely on beam search algorithm to generate output sequence.
An Empirical Study of Adequate Vision Span for Attention-Based Neural Machine Translation
Recently, the attention mechanism plays a key role to achieve high performance for Neural Machine Translation models.
Generating Video Description using Sequence-to-sequence Model with Temporal Attention
Automatic video description generation has recently been getting attention after rapid advancement in image caption generation.
Zero-resource Machine Translation by Multimodal Encoder-decoder Network with Multimedia Pivot
We propose an approach to build a neural machine translation system with no supervised resources (i. e., no parallel corpora) using multimodal embedded representation over texts and images.
Annotation Order Matters: Recurrent Image Annotator for Arbitrary Length Image Tagging
In addition to comparing our model with existing methods using the conventional top-k evaluation measures, we also provide our model as a high quality baseline for the arbitrary length image tagging task.
