Search Results for author:
Found 78 papers, 25 papers with code
The Shape Part Slot Machine: Contact-based Reasoning for Generating 3D Shapes from Parts
We present the Shape Part Slot Machine, a new method for assembling novel 3D shapes from existing parts by performing contact-based reasoning.
Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image Recognition
We propose an approach to IML, which we call Episodic Replay Distillation (ERD), that mixes classes from the current task with class exemplars from previous tasks when sampling episodes for meta-learning.
MutFormer: A context-dependent transformer-based model to predict pathogenic missense mutations
MutFormer and pre-computed variant scores are publicly available on GitHub at https://github. com/WGLab/mutformer.
HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification
To overcome forgetting in this benchmark, we propose Hierarchy-Consistency Verification (HCV) as an enhancement to existing continual learning methods.
RL4RS: A Real-World Benchmark for Reinforcement Learning based Recommender System
Reinforcement learning based recommender systems (RL-based RS) aims at learning a good policy from a batch of collected data, with casting sequential recommendation to multi-step decision-making tasks.
Feudal Reinforcement Learning by Reading Manuals
The manager agent is a multi-hop plan generator dealing with high-level abstract information and generating a series of sub-goals in a backward manner.
CRAFTING BETTER CONTRASTIVE VIEWS FOR SIAMESE REPRESENTATION LEARNING
Thus, a center-suppressed sampling is further designed to enlarge the variance of crops.
Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms
In this framework, the environment can be easily configured to realize all kinds of RL tasks in the mainstream research.
Harnessing Heterogeneity: Learning from Decomposed Feedback in Bayesian Modeling
We introduce a novel decomposed GP regression to incorporate the subgroup decomposed feedback.
Align Yourself: Self-supervised Pre-training for Fine-grained Recognition via Saliency Alignment
In this paper, we first point out that current contrastive methods are prone to memorizing background/foreground texture and therefore have a limitation in localizing the foreground object.
Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning
In the predict-then-optimize framework, the objective is to train a predictive model, mapping from environment features to parameters of an optimization problem, which maximizes decision quality when the optimization is subsequently solved.
Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Making by Reinforcement Learning
In the predict-then-optimize framework, the objective is to train a predictive model, mapping from environment features to parameters of an optimization problem, which maximizes decision quality when the optimization is subsequently solved.
An Efficient Training Approach for Very Large Scale Face Recognition
After that, to reduce the training time and hardware costs of the FC layer, we propose a Dynamic Class Pool (DCP) that stores the features from Gallery Net and calculates the inner product (logits) with positive samples (whose identities are in the DCP) in each mini-batch.
ACAE-REMIND for Online Continual Learning with Compressed Feature Replay
Methods are typically allowed to use a limited buffer to store some of the images in the stream.
Learning to Cluster Faces via Transformer
In this paper, we repurpose the well-known Transformer and introduce a Face Transformer for supervised face clustering.
Continual learning in cross-modal retrieval
We found that the indexing stage pays an important role and that simply avoiding reindexing the database with updated embedding networks can lead to significant gains.
Personalized Bundle Recommendation in Online Games
In business domains, \textit{bundling} is one of the most important marketing strategies to conduct product promotions, which is commonly used in online e-commerce and offline retailers.
Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation
As a part of the value function, free from the sparse and high-variance reward signals, a high-capacity reward-independent world model is trained to simulate complex environmental dynamics under a certain goal.
Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddings
Recent knowledge graph embedding (KGE) models based on hyperbolic geometry have shown great potential in a low-dimensional embedding space.
TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain
In this paper, we propose a transformer-based architecture, called two-stage transformer neural network (TSTNN) for end-to-end speech denoising in the time domain.
On Implicit Attribute Localization for Generalized Zero-Shot Learning
Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their attribute-based descriptions.
A Benchmark of Ocular Disease Intelligent Recognition: One Shot for Multi-disease Detection
In ophthalmology, early fundus screening is an economic and effective way to prevent blindness caused by ophthalmic diseases.
Applications of Deep Learning in Fundus Images: A Review
The use of fundus images for the early screening of eye diseases is of great clinical importance.
Exploring Emotion Features and Fusion Strategies for Audio-Video Emotion Recognition
The audio-video based emotion recognition aims to classify a given video into basic emotions.
AdnFM: An Attentive DenseNet based Factorization Machine for CTR Prediction
In this paper, we consider the Click-Through-Rate (CTR) prediction problem.
AU-Guided Unsupervised Domain Adaptive Facial Expression Recognition
The domain diversities including inconsistent annotation and varied image collection conditions inevitably exist among different facial expression recognition (FER) datasets, which pose an evident challenge for adapting the FER model trained on one dataset to another one.
Takagi topological insulator with odd $\mathcal P\mathcal T$ pairs of corner states
Particularly, the global Takagi's factorization can (cannot) be done on a $3$D ($2$D) sphere.
Mesoscale and Nanoscale Physics
Interpretable Visual Reasoning via Induced Symbolic Space
Finally, we achieve a higher level of interpretability by imposing OCCAM on the objects represented in the induced symbolic concept space.
Ranked #3 on
Visual Question Answering
on CLEVR
Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning
When we want to learn a node set representation involving multiple nodes, a common practice in previous works is to directly aggregate the multiple node representations learned by a GNN into a joint representation of the node set.
Ranked #1 on
Link Property Prediction
on ogbl-citation2
Suppressing Mislabeled Data via Grouping and Self-Attention
Specifically, this plug-and-play AFM first leverages a \textit{group-to-attend} module to construct groups and assign attention weights for group-wise samples, and then uses a \textit{mixup} module with the attention weights to interpolate massive noisy-suppressed samples.
MulDE: Multi-teacher Knowledge Distillation for Low-dimensional Knowledge Graph Embeddings
Link prediction based on knowledge graph embeddings (KGE) aims to predict new triples to automatically construct knowledge graphs (KGs).
A Comprehensive Review for MRF and CRF Approaches in Pathology Image Analysis
In this review, we present a comprehensive overview of pathology image analysis based on the markov random fields (MRFs) and conditional random fields (CRFs), which are two popular random field models.
Revisiting Graph Neural Networks for Link Prediction
Graph neural networks (GNNs) have achieved great success in recent years.
ShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesis
The program captures the subset of variability that is interpretable and editable.
Dual-Mandate Patrols: Multi-Armed Bandits for Green Security
Conservation efforts in green security domains to protect wildlife and forests are constrained by the limited availability of defenders (i. e., patrollers), who must patrol vast areas to protect from attackers (e. g., poachers or illegal loggers).
Measuring galaxy abundance and clustering at high redshift from incomplete spectroscopic data: Tests on mock catalogs and application to zCOSMOS
Using realistic mock catalogs we show that target selection and redshift incompleteness can lead to significantly biased results.
Astrophysics of Galaxies
CardioLearn: A Cloud Deep Learning Service for Cardiac Disease Detection from Electrocardiogram
Electrocardiogram (ECG) is one of the most convenient and non-invasive tools for monitoring peoples' heart condition, which can use for diagnosing a wide range of heart diseases, including Cardiac Arrhythmia, Acute Coronary Syndrome, et al.
Low-Resource Generation of Multi-hop Reasoning Questions
Specifically, we first build a multi-hop generation model and guide it to satisfy the logical rationality by the reasoning chain extracted from a given text.
Bookworm continual learning: beyond zero-shot learning and continual learning
We propose bookworm continual learning(BCL), a flexible setting where unseen classes can be inferred via a semantic model, and the visual model can be updated continually.
Automatically Learning Compact Quality-aware Surrogates for Optimization Problems
Solving optimization problems with unknown parameters often requires learning a predictive model to predict the values of the unknown parameters and then solving the problem using these values.
Simple and effective localized attribute representations for zero-shot learning
Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their semantic descriptions.
Multi-Domain Dialogue Acts and Response Co-Generation
Unlike those pipeline approaches, our act generation module preserves the semantic structures of multi-domain dialogue acts and our response generation module dynamically attends to different acts as needed.
Relational Graph Attention Network for Aspect-based Sentiment Analysis
Then, we propose a relational graph attention network (R-GAT) to encode the new tree structure for sentiment prediction.
The 1st Agriculture-Vision Challenge: Methods and Results
The first Agriculture-Vision Challenge aims to encourage research in developing novel and effective algorithms for agricultural pattern recognition from aerial images, especially for the semantic segmentation task associated with our challenge dataset.
Semantic Drift Compensation for Class-Incremental Learning
The vast majority of methods have studied this scenario for classification networks, where for each new task the classification layer of the network must be augmented with additional weights to make room for the newly added classes.
Axis Learning for Orientated Objects Detection in Aerial Images
Arbitrary orientated objects are detected by predicting the axis of the object, which is the line connecting the head and tail of the object, and the width of the object is vertical to the axis.
Ranked #1 on
One-stage Anchor-free Oriented Object Detection
on HRSC2016
( mAP metric)
Object Detection In Aerial Images
One-stage Anchor-free Oriented Object Detection
Relating the structure of dark matter halos to their assembly and environment
Using decision trees built with the random ensemble method, we find that the correlation between halo concentration and assembly history is tight: more than 60% of the variance in halo concentration can be explained by assembly history alone.
Astrophysics of Galaxies Cosmology and Nongalactic Astrophysics
Suppressing Uncertainties for Large-Scale Facial Expression Recognition
Annotating a qualitative large-scale facial expression dataset is extremely difficult due to the uncertainties caused by ambiguous facial expressions, low-quality facial images, and the subjectiveness of annotators.
PA-Cache: Evolving Learning-Based Popularity-Aware Content Caching in Edge Networks
Compared to the conventional content delivery networks, caches in edge networks with smaller sizes usually have to accommodate more bursty requests.
Aesthetic Quality Assessment for Group photograph
Image aesthetic quality assessment has got much attention in recent years, but not many works have been done on a specific genre of photos: Group photograph.
A Realistic Face-to-Face Conversation System based on Deep Neural Networks
Based on the models' output, the synthesizer uses the Pixel2Pixel model to generate realistic facial images.
CBOWRA: A Representation Learning Approach for Medication Anomaly Detection
Electronic health record is an important source for clinical researches and applications, and errors inevitably occur in the data, which could lead to severe damages to both patients and hospital services.
Video synthesis of human upper body with realistic face
This paper presents a generative adversarial learning-based human upper body video synthesis approach to generate an upper body video of target person that is consistent with the body motion, face expression, and pose of the person in source video.
Deep Learning based Wearable Assistive System for Visually Impaired People
In this paper, we propose a deep learning based assistive system to improve the environment perception experience of visually impaired (VI).
Coupled-Projection Residual Network for MRI Super-Resolution
The deep sub-network learns from the residuals of the high-frequency image information, where multiple residual blocks are cascaded to magnify the MRI images at the last network layer.
Bootstrap Model Ensemble and Rank Loss for Engagement Intensity Regression
Based on our winner solution last year, we mainly explore head features and body features with a bootstrap strategy and two novel loss functions in this paper.
Frame attention networks for facial expression recognition in videos
The feature embedding module is a deep Convolutional Neural Network (CNN) which embeds face images into feature vectors.
Ranked #2 on
Facial Expression Recognition
on CK+
(Accuracy (7 emotion) metric)
BiSET: Bi-directional Selective Encoding with Template for Abstractive Summarization
The success of neural summarization models stems from the meticulous encodings of source articles.
Ranked #9 on
Text Summarization
on GigaWord
Vision-based Robotic Grasping From Object Localization, Object Pose Estimation to Grasp Estimation for Parallel Grippers: A Review
We conclude three key tasks during vision-based robotic grasping, which are object localization, object pose estimation and grasp estimation.
LSANet: Feature Learning on Point Sets by Local Spatial Aware Layer
We design a novel Local Spatial Aware (LSA) layer, which can learn to generate Spatial Distribution Weights (SDWs) hierarchically based on the spatial relationship in local region for spatial independent operations, to establish the relationship between these operations and spatial distribution, thus capturing the local geometric structure sensitively. We further propose the LSANet, which is based on LSA layer, aggregating the spatial information with associated features in each layer of the network better in network design. The experiments show that our LSANet can achieve on par or better performance than the state-of-the-art methods when evaluating on the challenging benchmark datasets.
Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition
Extensive experiments show that our RAN and region biased loss largely improve the performance of FER with occlusion and variant pose.
Ranked #2 on
Facial Expression Recognition
on SFEW
Towards More Realistic Human-Robot Conversation: A Seq2Seq-based Body Gesture Interaction System
This paper presents a novel system that enables intelligent robots to exhibit realistic body gestures while communicating with humans.
Virtual-Blind-Road Following Based Wearable Navigation Device for Blind People
To help the blind people walk to the destination efficiently and safely in indoor environment, a novel wearable navigation device is presented in this paper.
Deep Learning Based Robot for Automatically Picking up Garbage on the Grass
In addition, with the ground segmentation using a deep neural network, a novel navigation strategy is proposed to guide the robot to move around.
Synthetic Data Generation and Adaption for Object Detection in Smart Vending Machines
This paper presents an improved scheme for the generation and adaption of synthetic images for the training of deep Convolutional Neural Networks(CNNs) to perform the object detection task in smart vending machines.
FluidC+: A novel community detection algorithm based on fluid propagation
In recent years, community detection has gradually become a hot topic in the complex network data mining field.
A Survey on Face Data Augmentation
The quality and size of training set have great impact on the results of deep learning-based face related tasks.
Detecting Colorized Images via Convolutional Neural Networks: Toward High Accuracy and Good Generalization
First, we design and implement a base network, which can attain better performance in terms of classification accuracy and generalization (in most cases) compared with state-of-the-art methods.
A Unified Framework for Mutual Improvement of SLAM and Semantic Segmentation
This paper presents a novel framework for simultaneously implementing localization and segmentation, which are two of the most important vision-based tasks for robotics.
Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models
We present a new, fast and flexible pipeline for indoor scene synthesis that is based on deep convolutional generative models.
On the Generation of Medical Question-Answer Pairs
Question answering (QA) has achieved promising progress recently.
Sub-GAN: An Unsupervised Generative Model via Subspaces
The recent years have witnessed significant growth in constructing robust generative models to capture informative distributions of natural data.
LIUM-CVC Submissions for WMT18 Multimodal Translation Task
This paper describes the multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT18 Shared Task on Multimodal Translation.
Knowledge Graph Embedding with Entity Neighbors and Deep Memory Network
Knowledge Graph Embedding (KGE) aims to represent entities and relations of knowledge graph in a low-dimensional continuous vector space.
Deep Learning Analysis of Defect and Phase Evolution During Electron Beam Induced Transformations in WS2
Understanding elementary mechanisms behind solid-state phase transformations and reactions is the key to optimizing desired functional properties of many technologically relevant materials.
Materials Science
BTS-DSN: Deeply Supervised Neural Network with Short Connections for Retinal Vessel Segmentation
Results: The proposed BTS-DSN has been verified on DRIVE, STARE and CHASE_DB1 datasets, and showed competitive performance over other state-of-the-art methods.
Richer Convolutional Features for Edge Detection
Using VGG16 network, we achieve \sArt results on several available datasets.
Ranked #2 on
Edge Detection
on BIPED
