Search Results for author:
Found 25 papers, 10 papers with code
HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization
To capture the semantic graph structure from raw text, most existing summarization approaches are built on GNNs with a pre-trained model.
Enriching Non-Autoregressive Transformer with Syntactic and SemanticStructures for Neural Machine Translation
In this paper, we claim that the syntactic and semantic structures among natural language are critical for non-autoregressive machine translation and can further improve the performance.
Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference
Intent detection is one of the core components of goal-oriented dialog systems, and detecting out-of-scope (OOS) intents is also a practically important skill.
Generalisable Cardiac Structure Segmentation via Attentional and Stacked Image Adaptation
Tackling domain shifts in multi-centre and multi-vendor data sets remains challenging for cardiac image segmentation.
MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines
We also benchmark a few state of the art dialogue state tracking models on the corrected dataset to facilitate comparison for future work.
TEA: Temporal Excitation and Aggregation for Action Recognition
Temporal modeling is key for action recognition in videos.
Domain Adaptive Medical Image Segmentation via Adversarial Learning of Disease-Specific Spatial Patterns
In medical imaging, the heterogeneity of multi-centre data impedes the applicability of deep learning-based methods and results in significant performance degradation when applying models in an unseen data domain, e. g. a new centreor a new scanner.
Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking
Dialog state tracking (DST) is a core component in task-oriented dialog systems.
Ranked #4 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.0
dialog state tracking
Multi-domain Dialogue State Tracking
+1
Adversarial Convolutional Networks with Weak Domain-Transfer for Multi-Sequence Cardiac MR Images Segmentation
Manual delineation of those tissues in cardiac MR (CMR) scans is laborious and time-consuming.
DiamondGAN: Unified Multi-Modal Generative Adversarial Networks for MRI Sequences Synthesis
Synthesizing MR imaging sequences is highly relevant in clinical practice, as single sequences are often missing or are of poor quality (e. g. due to motion).
Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce
To address this discrepancy, previous studies mainly consider textual information of long product titles and lacks of human-like view during training and evaluation process.
Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge
Segmentation methods had to be containerized and submitted to the challenge organizers.
Product Title Refinement via Multi-Modal Generative Adversarial Learning
Nowadays, an increasing number of customers are in favor of using E-commerce Apps to browse and purchase products.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Layerwise Perturbation-Based Adversarial Training for Hard Drive Health Degree Prediction
Then, it is possible to utilize unlabeled data that have a potential of failure to further improve the performance of the model.
Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloud
To benefit from the cloud data center without the privacy risk, we design, evaluate, and implement a cloud-based framework ARDEN which partitions the DNN across mobile devices and cloud data centers.
Deep Bilinear Learning for RGB-D Action Recognition
In this paper, we focus on exploring modality-temporal mutual information for RGB-D action recognition.
Early action prediction by soft regression
Our formulation of soft regression framework 1) overcomes a usual assumption in existing early action prediction systems that the progress level of on-going sequence is given in the testing stage; and 2) presents a theoretical framework to better resolve the ambiguity and uncertainty of subsequences at early performing stage.
Ranked #48 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Multi-Scale Convolutional-Stack Aggregation for Robust White Matter Hyperintensities Segmentation
Secondly, we aggregate multi-scale Stack-Nets with different receptive fields to learn multi-scale contextual information of both large and small lesions.
Discriminative Learning of Latent Features for Zero-Shot Recognition
In this work, we retrospect existing methods and demonstrate the necessity to learn discriminative representations for both visual and semantic instances of ZSL.
Mixed Supervised Object Detection with Robust Objectness Transfer
Different from previous MSD methods that directly transfer the pre-trained object detectors from existing categories to new categories, we propose a more reasonable and robust objectness transfer approach for MSD.
Fully Convolutional Network Ensembles for White Matter Hyperintensities Segmentation in MR Images
In this paper, we present a study using deep fully convolutional network and ensemble models to automatically detect such WMH using fluid attenuation inversion recovery (FLAIR) and T1 magnetic resonance (MR) scans.
Beyond triplet loss: a deep quadruplet network for person re-identification
In particular, a quadruplet deep network using a margin-based online hard negative mining is proposed based on the quadruplet loss for the person ReID.
Jointly learning heterogeneous features for rgb-d activity recognition
The proposed model formed in a unified framework is capable of: 1) jointly mining a set of subspaces with the same dimensionality to exploit latent shared features across different feature channels, 2) meanwhile, quantifying the shared and feature-specific components of features in the subspaces, and 3) transferring feature-specific intermediate transforms (i-transforms) for learning fusion of heterogeneous features across datasets.
Ranked #8 on
Skeleton Based Action Recognition
on SYSU 3D
A Multi-task Deep Network for Person Re-identification
Person re-identification (ReID) focuses on identifying people across different scenes in video surveillance, which is usually formulated as a binary classification task or a ranking task in current person ReID approaches.
