Search Results for author:
Found 178 papers, 61 papers with code
Sparse Subspace Denoising for Image Manifolds
With the increasing availability of high dimensional data and demand in sophisticated data analysis algorithms, manifold learning becomes a critical technique to perform dimensionality reduction, unraveling the intrinsic data structure.
Gradient-based Laplacian Feature Selection
With $\ell_1$ relaxation, GLFS can find a sparse subset of features that is relevant to the Laplacian manifolds.
Deep Learning for Object Saliency Detection and Image Segmentation
In this work, we use the computed saliency maps for image segmentation.
Towards Real-Time, Country-Level Location Classification of Worldwide Tweets
In contrast to much previous work that has focused on location classification of tweets restricted to a specific country, here we undertake the task in a broader context by classifying global tweets at the country level, which is so far unexplored in a real-time scenario.
How priors of initial hyperparameters affect Gaussian process regression models
The hyperparameters in Gaussian process regression (GPR) model with a specified kernel are often estimated from the data via the maximum marginal likelihood.
SYSTRAN's Pure Neural Machine Translation Systems
Since the first online demonstration of Neural Machine Translation (NMT) by LISA, NMT development has recently moved from laboratory to production systems as demonstrated by several entities announcing roll-out of NMT engines to replace their existing technologies.
Measuring Asymmetric Opinions on Online Social Interrelationship with Language and Network Features
Instead of studying the properties of social relationship from an objective view, in this paper, we focus on individuals' subjective and asymmetric opinions on their interrelationships.
Structure vs. Language: Investigating the Multi-factors of Asymmetric Opinions on Online Social Interrelationship with a Case Study
With statistical analysis on Enron email dataset, we find that individuals' opinions (measured by interactive language features) on their interrelationship are related to some of their important structural context in social network.
Unsupervised Learning from Noisy Networks with Applications to Hi-C Data
In this paper, we propose an optimization framework to mine useful structures from noisy networks in an unsupervised manner.
Political Homophily in Independence Movements: Analysing and Classifying Social Media Users by National Identity
Independence movements occur in territories whose citizens have conflicting national identities; users with opposing national identities will then support or oppose the sense of being part of an independent nation that differs from the officially recognised country.
Multivariate Gaussian and Student$-t$ Process Regression for Multi-output Prediction
Gaussian process model for vector-valued function has been shown to be useful for multi-output prediction.
SIMLR: A Tool for Large-Scale Genomic Analyses by Multi-Kernel Learning
We here present SIMLR (Single-cell Interpretation via Multi-kernel LeaRning), an open-source tool that implements a novel framework to learn a sample-to-sample similarity measure from expression data observed for heterogenous samples.
TDParse: Multi-target-specific sentiment recognition on Twitter
Existing target-specific sentiment recognition methods consider only a single target per tweet, and have been shown to miss nearly half of the actual targets mentioned.
SYSTRAN Purely Neural MT Engines for WMT2017
This paper describes SYSTRAN's systems submitted to the WMT 2017 shared news translation task for English-German, in both translation directions.
TOTEMSS: Topic-based, Temporal Sentiment Summarisation for Twitter
We present a system for time sensitive, topic based summarisation of the sentiment around target entities and topics in collections of tweets.
Gradually Updated Neural Networks for Large-Scale Image Recognition
Our method is by introducing computation orderings to the channels within convolutional layers or blocks, based on which we gradually compute the outputs in a channel-wise manner.
Single-Shot Object Detection with Enriched Semantics
Our motivation is to enrich the semantics of object detection features within a typical deep detector, by a semantic segmentation branch and a global activation module.
Deep Regression Forests for Age Estimation
Age estimation from facial images is typically cast as a nonlinear regression problem.
Ranked #6 on
Age Estimation
on FGNET
Deep Co-Training for Semi-Supervised Image Recognition
We present Deep Co-Training, a deep learning based method inspired by the Co-Training framework.
Movie Question Answering: Remembering the Textual Cues for Layered Visual Contents
Movies provide us with a mass of visual content as well as attracting stories.
Network Enhancement: a general method to denoise weighted biological networks
Networks are ubiquitous in biology where they encode connectivity patterns at all scales of organization, from molecular to the biome.
Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities
In this Review, we describe the principles of data integration and discuss current methods and available implementations.
OpenNMT System Description for WNMT 2018: 800 words/sec on a single-core CPU
We present a system description of the OpenNMT Neural Machine Translation entry for the WNMT 2018 evaluation.
Image Captioning based on Deep Reinforcement Learning
However, in this paper, we propose a novel architecture for image captioning with deep reinforcement learning to optimize image captioning tasks.
Robust Face Detection via Learning Small Faces on Hard Images
In this paper, we propose that the robustness of a face detector against hard faces can be improved by learning small faces on hard images.
Ranked #8 on
Face Detection
on WIDER Face (Hard)
Moment Matching for Multi-Source Domain Adaptation
Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain.
Geometric Interpretation of side-sharing and point-sharing solutions in the P3P Problem
In this work, we provide some new geometric interpretations on the multi-solution phenomenon in the P3P problem, our main results include: (1): The necessary and sufficient condition for the P3P problem to have a pair of side-sharing solutions is the two optical centers of the solutions both lie on one of the 3 vertical planes to the base plane of control points; (2): The necessary and sufficient condition for the P3P problem to have a pair of point-sharing solutions is the two optical centers of the solutions both lie on one of the 3 so-called skewed danger cylinders;(3): If the P3P problem has other solutions in addition to a pair of side-sharing ( point-sharing) solutions, these remaining solutions must be a point-sharing ( side-sharing ) pair.
New insights on Multi-Solution Distribution of the P3P Problem
In this work, we show that when the optical center is outside of all the 6 toroids defined by the control point triangle, each positive root of the Grunert's quartic equation must correspond to a true solution of the P3P problem, and the corresponding P3P problem cannot have a unique solution, it must have either 2 positive solutions or 4 positive solutions.
Can We Derive Explicit and Implicit Bias from Corpus?
Inspired by psychological measurements of explicit and implicit bias, we develop an automatic language-based technique to reproduce psychological measurements on large population.
Companion Surface of Danger Cylinder and its Role in Solution Variation of P3P Problem
And when the optical center moves on the danger cylinder, accordingly the optical centers of the two other solutions of the corresponding P3P problem form a new surface, characterized by a polynomial equation of degree 12 in the optical center coordinates, called the Companion Surface of Danger Cylinder (CSDC).
A Minimax Game for Instance based Selective Transfer Learning
To the best of our knowledge, this is the first to build a minimax game based model for selective transfer learning.
Deep Differentiable Random Forests for Age Estimation
Both of them connect split nodes to the top layer of convolutional neural networks (CNNs) and deal with inhomogeneous data by jointly learning input-dependent data partitions at the split nodes and age distributions at the leaf nodes.
Learning from Label Proportions with Generative Adversarial Networks
In this paper, we leverage generative adversarial networks (GANs) to derive an effective algorithm LLP-GAN for learning from label proportions (LLP), where only the bag-level proportional information in labels is available.
Interpretable Biomanufacturing Process Risk and Sensitivity Analyses for Quality-by-Design and Stability Control
While biomanufacturing plays a significant role in supporting the economy and ensuring public health, it faces critical challenges, including complexity, high variability, lengthy lead time, and very limited process data, especially for personalized new cell and gene biotherapeutics.
s-LWSR: Super Lightweight Super-Resolution Network
Deep learning (DL) architectures for superresolution (SR) normally contain tremendous parameters, which has been regarded as the crucial advantage for obtaining satisfying performance.
DeepGeneMD: A Joint Deep Learning Model for Extracting Gene Mutation-Disease Knowledge from PubMed Literature
Understanding the pathogenesis of genetic diseases through different gene activities and their relations to relevant diseases is important for new drug discovery and drug repositioning.
Progressive Feature Polishing Network for Salient Object Detection
Feature matters for salient object detection.
Shenjing: A low power reconfigurable neuromorphic accelerator with partial-sum and spike networks-on-chip
We show that conventional artificial neural networks (ANN) such as multilayer perceptron, convolutional neural networks, as well as the latest residual neural networks can be mapped successfully onto Shenjing, realizing ANNs with SNN's energy efficiency.
End-to-end Named Entity Recognition and Relation Extraction using Pre-trained Language Models
In this paper, we propose a neural, end-to-end model for jointly extracting entities and their relations which does not rely on external NLP tools and which integrates a large, pre-trained language model.
Diversity Transfer Network for Few-Shot Learning
The learning problem of the sample generation (i. e., diversity transfer) is solved via minimizing an effective meta-classification loss in a single-stage network, instead of the generative loss in previous works.
LOSSLESS SINGLE IMAGE SUPER RESOLUTION FROM LOW-QUALITY JPG IMAGES
Super Resolution (SR) is a fundamental and important low-level computer vision (CV) task.
Learning Global and Local Consistent Representations for Unsupervised Image Retrieval via Deep Graph Diffusion Networks
Diffusion has shown great success in improving accuracy of unsupervised image retrieval systems by utilizing high-order structures of image manifold.
SAUNet: Shape Attentive U-Net for Interpretable Medical Image Segmentation
Despite the progress of deep learning in medical image segmentation, standard CNNs are still not fully adopted in clinical settings as they lack robustness and interpretability.
Ranked #1 on
Left Ventricle Segmentation
on SUN09
The importance of transparency and reproducibility in artificial intelligence research
In their study, McKinney et al. showed the high potential of artificial intelligence for breast cancer screening.
Applications
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training
Estimating 3D poses from a monocular video is still a challenging task, despite the significant progress that has been made in recent years.
Ranked #3 on
3D Human Pose Estimation
on HumanEva-I
A Novel CNN-based Method for Accurate Ship Detection in HR Optical Remote Sensing Images via Rotated Bounding Box
By contrast, we are able to predict the orientation and other variables independently, and yet more effectively, with a novel dual-branch regression network, based on the observation that the ship targets are nearly rotation-invariant in remote sensing images.
COVID-19 Chest CT Image Segmentation -- A Deep Convolutional Neural Network Solution
Inspired by the observation that the boundary of the infected lung can be enhanced by adjusting the global intensity, in the proposed deep CNN, we introduce a feature variation block which adaptively adjusts the global properties of the features for segmenting COVID-19 infection.
Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion
In experiments, we achieve state-of-the-art performance on three benchmarks and a zero-shot dataset for link prediction, with highlights of inference costs reduced by 1-2 orders of magnitude compared to a textual encoding method.
Ranked #4 on
Link Prediction
on UMLS
DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations
Inspired by recent advances in deep metric learning (DML), we carefully design a self-supervised objective for learning universal sentence embeddings that does not require labelled training data.
Ranked #4 on
Linear-Probe Classification
on SentEval
Integrated Longitudinal Speed Decision-Making and Energy Efficiency Control for Connected Electrified Vehicles
As the core of this study, model predictive control and reinforcement learning are combined to improve the powertrain mobility and fuel economy for a group of automated vehicles.
Learning to Detect Bipolar Disorder and Borderline Personality Disorder with Language and Speech in Non-Clinical Interviews
Bipolar disorder (BD) and borderline personality disorder (BPD) are both chronic psychiatric disorders.
Sound speed resonance of the stochastic gravitational wave background
We propose a novel mechanism to amplify the primordial gravitational waves (GWs) at the scale which can be detected by current or near future gravitational wave detectors.
General Relativity and Quantum Cosmology Cosmology and Nongalactic Astrophysics High Energy Physics - Phenomenology High Energy Physics - Theory
Information Extraction from Swedish Medical Prescriptions with Sig-Transformer Encoder
Relying on large pretrained language models such as Bidirectional Encoder Representations from Transformers (BERT) for encoding and adding a simple prediction layer has led to impressive performance in many clinical natural language processing (NLP) tasks.
Multi-Scale Networks for 3D Human Pose Estimation with Inference Stage Optimization
Addressing these problems, we introduce a spatio-temporal network for robust 3D human pose estimation.
w-Net: Dual Supervised Medical Image Segmentation Model with Multi-Dimensional Attention and Cascade Multi-Scale Convolution
Non-local attention and feature learning by multi-scale methods are widely used to model network, which drives progress in medical image segmentation.
Predicting the $\bar{D}_s^{(*)} D_s^{(*)}$ bound states as the partners of $X(3872)$
We prove the existence of the $[\bar{D}_{s}^{*}D_{s}^{*}]^{0^{++}}$, $[\bar{D}_{s}^{*}D_{s}/\bar{D}_{s}^{}D_{s}^*]^{1^{+-}}$, and $[\bar{D}_{s}^{*}D_{s}^{*}]^{1^{+-}}$ bound states as the consequence of two prerequisites in the SU(3) flavor symmetry and heavy quark spin symmetry.
High Energy Physics - Phenomenology High Energy Physics - Experiment High Energy Physics - Lattice
Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos
To tackle this problem, we propose a novel framework integrating graph convolutional networks (GCNs) and temporal convolutional networks (TCNs) to robustly estimate camera-centric multi-person 3D poses that do not require camera parameters.
Ranked #1 on
Root Joint Localization
on Human3.6M
3D Absolute Human Pose Estimation
3D Multi-Person Pose Estimation (absolute)
+5
OT-LLP: Optimal Transport for Learning from Label Proportions
Learning from label proportions (LLP), where the training data are arranged in form of groups with only label proportions provided instead of the exact labels, is an important weakly supervised learning paradigm in machine learning.
Optimizing Biomanufacturing Harvesting Decisions under Limited Historical Data
We adopt a Bayesian approach to update the unknown parameters of the growth-rate distributions, and use the resulting posterior distributions to characterize the impact of model risk on fermentation output variability.
Adversarial Active Learning based Heterogeneous Graph Neural Network for Fake News Detection
AA-HGNN utilizes an active learning framework to enhance learning performance, especially when facing the paucity of labeled data.
Spectrum of the doubly charmed molecular pentaquarks in chiral effective field theory
We perform a systematic study on the interactions of the $\Sigma_c^{(*)}D^{(*)}$ systems within the framework of chiral effective field theory.
High Energy Physics - Phenomenology High Energy Physics - Experiment High Energy Physics - Lattice Nuclear Theory
Multipopulation mortality modelling and forecasting: The multivariate functional principal component with time weightings approaches
The first model extends the independent functional data model to a multi-population modelling setting.
The effect of aspherical stellar wind of giant stars on the symbiotic channel of type Ia supernovae
The progenitor systems accounting for explosions of type Ia supernovae (SNe Ia) is still under debate.
Solar and Stellar Astrophysics
Robust non-parametric mortality and fertility modelling and forecasting: Gaussian process regression approaches
A rapid decline in mortality and fertility has become major issues in many developed countries over the past few decades.
Modelling Paralinguistic Properties in Conversational Speech to Detect Bipolar Disorder and Borderline Personality Disorder
Bipolar disorder (BD) and borderline personality disorder (BPD) are two chronic mental health conditions that clinicians find challenging to distinguish based on clinical interviews, due to their overlapping symptoms.
Continuous quantum light from a dark atom
Cycling processes are important in many areas of physics ranging from lasers to topological insulators, often offering surprising insights into dynamical and structural aspects of the respective system.
Quantum Physics
Auditory Attention Decoding from EEG using Convolutional Recurrent Neural Network
In this paper, we proposed novel convolutional recurrent neural network (CRNN) based regression model and classification model, and compared them with both the linear model and the state-of-the-art DNN models.
Eye-gaze Estimation with HEOG and Neck EMG using Deep Neural Networks
These results indicated the feasibility to estimate eye-gaze with HEOG and NEMG.
Onfocus Detection: Identifying Individual-Camera Eye Contact from Unconstrained Images
Onfocus detection aims at identifying whether the focus of the individual captured by a camera is on the camera or not.
Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks
Besides the integration of top-down and bottom-up networks, unlike existing pose discriminators that are designed solely for single person, and consequently cannot assess natural inter-person interactions, we propose a two-person pose discriminator that enforces natural two-person interactions.
3D Multi-Person Pose Estimation (absolute)
3D Multi-Person Pose Estimation (root-relative)
+2
Two-stage Training for Learning from Label Proportions
Learning from label proportions (LLP) aims at learning an instance-level classifier with label proportions in grouped training data.
Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function
Numerous detection problems in computer vision, including road crack detection, suffer from exceedingly foreground-background imbalance.
Evaluation of Thematic Coherence in Microblogs
Here we create a corpus of microblog clusters from three different domains and time windows and define the task of evaluating thematic coherence.
Transferring Knowledge Distillation for Multilingual Social Event Detection
Experiments on both synthetic and real-world datasets show the framework to be highly effective at detection in both multilingual data and in languages where training samples are scarce.
A Longitudinal Multi-modal Dataset for Dementia Monitoring and Diagnosis
The corpus consists of spoken conversations, a subset of which are transcribed, as well as typed and written thoughts and associated extra-linguistic information such as pen strokes and keystrokes.
Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction
Aspect-level sentiment classification (ALSC) aims at identifying the sentiment polarity of a specified aspect in a sentence.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
Rethinking Lightweight Convolutional Neural Networks for Efficient and High-quality Pavement Crack Detection
For the second issue, we reconsider how to improve detection efficiency with excellent performance, and then propose our lightweight encoder-decoder architecture termed CarNet.
OctField: Hierarchical Implicit Functions for 3D Modeling
We achieve this goal by introducing a hierarchical octree structure to adaptively subdivide the 3D space according to the surface occupancy and the richness of part geometry.
MassFormer: Tandem Mass Spectrum Prediction for Small Molecules using Graph Transformers
MassFormer outperforms competing approaches for spectrum prediction on multiple datasets, and is able to recover prior knowledge about the effect of collision energy on the spectrum.
Traffic4cast -- Large-scale Traffic Prediction using 3DResNet and Sparse-UNet
The aim is to build a machine learning model for predicting the normalized average traffic speed and flow of the subregions of multiple large-scale cities using historical data points.
Comparison between Time Shifting Deviation and Cross-correlation Methods
It stands in clear contrast to the result of cross-correlation method, whose localization error is 70 m and the standard deviation is 208. 4 m. Compared with cross-correlation method, TSDEV has the same resistance to white noise, but has fewer boundary conditions and better suppression on linear drift or common noise, which leads to more precise TDE results.
High-Fidelity Point Cloud Completion with Low-Resolution Recovery and Noise-Aware Upsampling
Instead of decoding a whole shape, we propose to decode and refine a low-resolution (low-res) point cloud first, and then performs a patch-wise noise-aware upsampling rather than interpolating the whole sparse point cloud at once, which tends to lose details.
Random cohort effects and age groups dependency structure for mortality modelling and forecasting: Mixed-effects time-series model approach
There have been significant efforts devoted to solving the longevity risk given that a continuous growth in population ageing has become a severe issue for many developed countries over the past few decades.
Neural-FST Class Language Model for End-to-End Speech Recognition
We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech recognition, a novel method that combines neural network language models (NNLMs) and finite state transducers (FSTs) in a mathematically consistent framework.
MHSnet: Multi-head and Spatial Attention Network with False-Positive Reduction for Pulmonary Nodules Detection
The false positive reduction module significantly decreases the average number of candidates generated per scan by 68. 11% and the false discovery rate by 13. 48%, which is promising to reduce distracted proposals for the downstream tasks based on the detection results.
A Coarse-to-fine Morphological Approach With Knowledge-based Rules and Self-adapting Correction for Lung Nodules Segmentation
The segmentation module which precisely outlines the nodules is a crucial step in a computer-aided diagnosis(CAD) system.
Interactive Image Synthesis with Panoptic Layout Generation
In particular, the stuff layouts can take amorphous shapes and fill up the missing regions left out by the instance layouts.
Ranked #2 on
Layout-to-Image Generation
on Visual Genome 128x128
Hybrid Routing Transformer for Zero-Shot Learning
This design makes the presented transformer model a hybrid of 1) top-down and bottom-up attention pathways and 2) dynamic and static routing pathways.
Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes
The IARAI Traffic4cast competitions at NeurIPS 2019 and 2020 showed that neural networks can successfully predict future traffic conditions 1 hour into the future on simply aggregated GPS probe data in time and space bins.
A sequence-to-sequence approach for document-level relation extraction
In this paper, we develop a sequence-to-sequence approach, seq2rel, that can learn the subtasks of DocRE (entity extraction, coreference resolution and relation extraction) end-to-end, replacing a pipeline of task-specific components.
Ranked #1 on
Joint Entity and Relation Extraction
on CDR
coreference-resolution
Document-level Relation Extraction
+3
Dual networks based 3D Multi-Person Pose Estimation from Monocular Video
Most of the methods focus on single persons, which estimate the poses in the person-centric coordinates, i. e., the coordinates based on the center of the target person.
Ranked #1 on
3D Human Pose Estimation
on JTA
3D Multi-Person Pose Estimation (absolute)
3D Multi-Person Pose Estimation (root-relative)
+4
Underactuated Source Seeking by Surge Force Tuning: Theory and Boat Experiments
We extend source seeking algorithms, in the absence of position and velocity measurements, and with tuning of the surge input, from velocity-actuated (unicycle) kinematic models to force-actuated generic Euler-Lagrange dynamic underactuated models.
Dynamic Prefix-Tuning for Generative Template-based Event Extraction
We consider event extraction in a generative manner with template-based conditional generation.
BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing
Training and evaluating language models increasingly requires the construction of meta-datasets --diverse collections of curated data with clear provenance.
Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting
To address the coupling problem, we propose a Cycle Self-Training (CST) framework for SSOD, which consists of two teachers T1 and T2, two students S1 and S2.
Model-Aware Contrastive Learning: Towards Escaping the Dilemmas
Contrastive learning (CL) continuously achieves significant breakthroughs across multiple domains.
Template-based Abstractive Microblog Opinion Summarisation
We introduce the task of microblog opinion summarisation (MOS) and share a dataset of 3100 gold-standard opinion summaries to facilitate research in this domain.
Fisher Matrix Based Fault Detection for PMUs Data in Power Grids
Firstly, the fault detection matrix is constructed and the event detection problem is reformatted as a two-sample covariance matrices test problem.
CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation
Empathetic conversation is psychologically supposed to be the result of conscious alignment and interaction between the cognition and affection of empathy.
Bottom-Up 2D Pose Estimation via Dual Anatomical Centers for Small-Scale Persons
In multi-person 2D pose estimation, the bottom-up methods simultaneously predict poses for all persons, and unlike the top-down methods, do not rely on human detection.
GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs
First, unlike previous methods, we leverage convolution neural networks as well as graph neural networks in a complementary way for geometric representation learning.
OSIC: A New One-Stage Image Captioner Coined
To obtain rich features, we use the Swin Transformer to calculate multi-level features, and then feed them into a novel dynamic multi-sight embedding module to exploit both global structure and local texture of input images.
Aligning Recommendation and Conversation via Dual Imitation
Human conversations of recommendation naturally involve the shift of interests which can align the recommendation actions and conversation process to make accurate recommendations with rich explanations.
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions.
CodeExp: Explanatory Code Document Generation
Our experiments show that (1) our refined training dataset lets models achieve better performance in the explanation generation tasks compared to larger unrefined data (15x larger), and (2) fine-tuned models can generate well-structured long docstrings comparable to human-written ones.
Gradient Domain Weighted Guided Image Filtering
Guided image filter is a well-known local filter in image processing.
Overlapping oriented imbalanced ensemble learning method based on projective clustering and stagewise hybrid sampling
Secondly, according to the characteristics of subset classes, a stage-wise hybrid sampling algorithm is designed to realize the de-overlapping and balancing of subsets.
Open Domain Multi-document Summarization: A Comprehensive Study of Model Brittleness under Retrieval
Via extensive automatic and human evaluation, we determine: (1) state-of-the-art summarizers suffer large reductions in performance when applied to open-domain MDS, (2) additional training in the open-domain setting can reduce this sensitivity to imperfect retrieval, and (3) summarizers are insensitive to the retrieval of duplicate documents and the order of retrieved documents, but highly sensitive to other errors, like the retrieval of irrelevant documents.
Ranked #1 on
Multi-Document Summarization
on MS^2
MAESTER: Masked Autoencoder Guided Segmentation at Pixel Resolution for Accurate, Self-Supervised Subcellular Structure Recognition
Complete manual segmentation is unfeasible for large datasets, and while supervised methods have been proposed to automate segmentation, they often rely on manually generated ground truths which are especially challenging and time consuming to generate in biology due to the requirement of domain expertise.
Underwater Object Tracker: UOSTrack for Marine Organism Grasping of Underwater Vehicles
The UOHT training paradigm is designed to train the sample-imbalanced underwater tracker so that the tracker is exposed to a great number of underwater domain training samples and learns the feature expressions.
Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation
Towards human-like dialogue systems, current emotional dialogue approaches jointly model emotion and semantics with a unified neural network.
NodeCoder: a graph-based machine learning platform to predict active sites of modeled protein structures
While accurate protein structure predictions are now available for nearly every observed protein sequence, predicted structures lack much of the functional context offered by experimental structure determination.
DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets
In this paper we leverage the fact that it is possible to estimate the "velocity" of gene expression with RNA velocity techniques to develop an approach that addresses both challenges.
Prescribed Time Time-varying Output Formation Tracking for Uncertain Heterogeneous Multi-agent Systems
The time-varying output formation tracking for the heterogeneous multi-agent systems (MAS) is investigated in this paper.
Empathetic Response Generation via Emotion Cause Transition Graph
Empathetic dialogue is a human-like behavior that requires the perception of both affective factors (e. g., emotion status) and cognitive factors (e. g., cause of the emotion).
Variational operator learning: A unified paradigm marrying training neural operators and solving partial differential equations
We propose a novel paradigm that provides a unified framework of training neural operators and solving PDEs with the variational form, which we refer to as the variational operator learning (VOL).
Time Reversal Enabled Fiber-Optic Time Synchronization
It measures the clock difference between two locations without involving a data layer, which can reduce the complexity of the system.
Segment Anything in Medical Images
Medical image segmentation is a critical component in clinical practice, facilitating accurate diagnosis, treatment planning, and disease monitoring.
WangLab at MEDIQA-Chat 2023: Clinical Note Generation from Doctor-Patient Conversations using Large Language Models
This paper describes our submission to the MEDIQA-Chat 2023 shared task for automatic clinical note generation from doctor-patient conversations.
Supervised Domain Adaptation for Recognizing Retinal Diseases from Wide-Field Fundus Images
This paper addresses the emerging task of recognizing multiple retinal diseases from wide-field (WF) and ultra-wide-field (UWF) fundus images.
Boosting Event Extraction with Denoised Structure-to-Text Augmentation
Event extraction aims to recognize pre-defined event triggers and arguments from texts, which suffer from the lack of high-quality annotations.
Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding
We present Clinical Camel, an open large language model (LLM) explicitly tailored for clinical research.
Enhancing Personalized Dialogue Generation with Contrastive Latent Variables: Combining Sparse and Dense Persona
We design a Contrastive Latent Variable-based model (CLV) that clusters the dense persona descriptions into sparse categories, which are combined with the history query to generate personalized responses.
DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment
Thanks to the proposed fusion module, our method is robust not only to occlusion and large pitch and roll view angles, which is the benefit of our image space approach, but also to noise and large yaw angles, which is the benefit of our model space method.
Ranked #1 on
3D Face Reconstruction
on AFLW2000-3D
(Mean NME metric)
Decentralized Equalization for Massive MIMO Systems With Colored Noise Samples
However, current detection methods tailored to DBP only consider ideal white Gaussian noise scenarios, while in practice, the noise is often colored due to interference from neighboring cells.
CongFu: Conditional Graph Fusion for Drug Synergy Prediction
Drug synergy, characterized by the amplified combined effect of multiple drugs, is critically important for optimizing therapeutic outcomes.
Spatially Resolved Gene Expression Prediction from H&E Histology Images via Bi-modal Contrastive Learning
Our results demonstrate the potential of BLEEP to provide insights into the molecular mechanisms underlying tissue architecture, with important implications in diagnosis and research of various diseases.
SplatFlow: Learning Multi-frame Optical Flow via Splatting
The occlusion problem remains a crucial challenge in optical flow estimation (OFE).
FFPDG: Fast, Fair and Private Data Generation
Generative modeling has been used frequently in synthetic data generation.
Training Physics-Informed Neural Networks via Multi-Task Optimization for Traffic Density Prediction
Physics-informed neural networks (PINNs) are a newly emerging research frontier in machine learning, which incorporate certain physical laws that govern a given data set, e. g., those described by partial differential equations (PDEs), into the training of the neural network (NN) based on such a data set.
Facilitating Multi-turn Emotional Support Conversation with Positive Emotion Elicitation: A Reinforcement Learning Approach
Experiments verify the superiority of Supporter in achieving positive emotion elicitation during responding while maintaining conversational goals including coherence.
Magnetic Field-Based Reward Shaping for Goal-Conditioned Reinforcement Learning
Existing reward shaping methods for goal-conditioned RL are typically built on distance metrics with a linear and isotropic distribution, which may fail to provide sufficient information about the ever-changing environment with high complexity.
Unleashing the Strengths of Unlabeled Data in Pan-cancer Abdominal Organ Quantification: the FLARE22 Challenge
The best-performing algorithms successfully generalized to holdout external validation sets, achieving a median DSC of 89. 5\%, 90. 9\%, and 88. 3\% on North American, European, and Asian cohorts, respectively.
The Multi-modality Cell Segmentation Challenge: Towards Universal Solutions
This benchmark and the improved algorithm offer promising avenues for more accurate and versatile cell analysis in microscopy imaging.
Mind vs. Mouth: On Measuring Re-judge Inconsistency of Social Bias in Large Language Models
We propose that this re-judge inconsistency can be similar to the inconsistency between human's unaware implicit social bias and their aware explicit social bias.
UnitModule: A Lightweight Joint Image Enhancement Module for Underwater Object Detection
In this paper, we propose a plug-and-play Underwater joint image enhancement Module (UnitModule) that provides the input image preferred by the detector.
A DenseNet-based method for decoding auditory spatial attention with EEG
ASAD methods are inspired by the brain lateralization of cortical neural responses during the processing of auditory spatial attention, and show promising performance for the task of auditory attention decoding (AAD) with neural recordings.
ORTexME: Occlusion-Robust Human Shape and Pose via Temporal Average Texture and Mesh Encoding
In 3D human shape and pose estimation from a monocular video, models trained with limited labeled data cannot generalize well to videos with occlusion, which is common in the wild videos.
Lightweight Full-Convolutional Siamese Tracker
Although single object trackers have achieved advanced performance, their large-scale models hinder their application on limited resources platforms.
Splicing Up Your Predictions with RNA Contrastive Learning
In the face of rapidly accumulating genomic data, our understanding of the RNA regulatory code remains incomplete.
Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents
Text embedding models have emerged as powerful tools for transforming sentences into fixed-sized feature vectors that encapsulate semantic information.
To Transformers and Beyond: Large Language Models for the Genome
In the rapidly evolving landscape of genomics, deep learning has emerged as a useful tool for tackling complex computational challenges.
Disordered hyperuniformity signals functioning and resilience of self-organized vegetation patterns
Here we show that disordered hyperuniformity as a striking class of hidden orders can exist in spatially self-organized vegetation landscapes.
GPT-4V(ision) Unsuitable for Clinical Care and Education: A Clinician-Evaluated Assessment
OpenAI's large multimodal model, GPT-4V(ision), was recently developed for general image interpretation.
ShareCMP: Polarization-Aware RGB-P Semantic Segmentation
Multimodal semantic segmentation is developing rapidly, but the modality of RGB-Polarization remains underexplored.
Ranked #1 on
Semantic Segmentation
on ZJU-RGB-P
Towards Verifiable Text Generation with Evolving Memory and Self-Reflection
Despite the remarkable ability of large language models (LLMs) in language comprehension and generation, they often suffer from producing factually incorrect information, also known as hallucination.
Random resistive memory-based deep extreme point learning machine for unified visual processing
Our random resistive memory-based deep extreme point learning machine may pave the way for energy-efficient and training-friendly edge AI across various data modalities and tasks.
Few-Shot Learning from Augmented Label-Uncertain Queries in Bongard-HOI
In our proposed method, we introduce novel label-uncertain query augmentation techniques to enhance the diversity of the query inputs, aiming to distinguish the positive HOI class from the negative ones.
Generative Pretraining at Scale: Transformer-Based Encoding of Transactional Behavior for Fraud Detection
In this work, we introduce an innovative autoregressive model leveraging Generative Pretrained Transformer (GPT) architectures, tailored for fraud detection in payment systems.
GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse
The exponential growth of social media has profoundly transformed how information is created, disseminated, and absorbed, exceeding any precedent in the digital age.
U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation
Convolutional Neural Networks (CNNs) and Transformers have been the most popular architectures for biomedical image segmentation, but both of them have limited ability to handle long-range dependencies because of inherent locality or computational complexity.
ConvConcatNet: a deep convolutional neural network to reconstruct mel spectrogram from the EEG
To investigate the processing of speech in the brain, simple linear models are commonly used to establish a relationship between brain signals and speech features.
Self-supervised speech representation and contextual text embedding for match-mismatch classification with EEG recording
Contrastive learning was used to relate EEG features to speech features.
Integrate Any Omics: Towards genome-wide data integration for patient stratification
High-throughput omics profiling advancements have greatly enhanced cancer patient stratification.
Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models
Then we propose to fine-tune a small language model as the debate judge for harmfulness inference, to facilitate multimodal fusion between the harmfulness rationales and the intrinsic multimodal information within memes.
Decentralised, Collaborative, and Privacy-preserving Machine Learning for Multi-Hospital Data
In addition, the ML models trained with DeCaPH framework in general outperform those trained solely with the private datasets from individual parties, showing that DeCaPH enhances the model generalizability.
Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces
Attention mechanisms have been widely used to capture long-range dependencies among nodes in Graph Transformers.
Have Seen Me Before? Automating Dataset Updates Towards Reliable and Timely Evaluation
The basic idea is to generate unseen and high-quality testing samples based on existing ones to mitigate leakage issues.
Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings
We introduce a novel suite of state-of-the-art bilingual text embedding models that are designed to support English and another target language.
Learning Exposure Correction in Dynamic Scenes
While image exposure correction is a popular topic, the video counterpart is less explored in the literature.
In-Memory Learning: A Declarative Learning Framework for Large Language Models
The exploration of whether agents can align with their environment without relying on human-labeled data presents an intriguing research topic.
Sculpting Molecules in 3D: A Flexible Substructure Aware Framework for Text-Oriented Molecular Optimization
This work not only holds general significance for the advancement of deep learning methodologies but also paves the way for a transformative shift in molecular design strategies.
Knowledge Condensation and Reasoning for Knowledge-based VQA
We condense the retrieved knowledge passages from two perspectives.
Rethinking Multi-view Representation Learning via Distilled Disentangling
To this end, we propose an innovative framework for multi-view representation learning, which incorporates a technique we term 'distilled disentangling'.
SceneTracker: Long-term Scene Flow Estimation Network
Considering the complementarity of scene flow estimation in the spatial domain's focusing capability and 3D object tracking in the temporal domain's coherence, this study aims to address a comprehensive new task that can simultaneously capture fine-grained and long-term 3D motion in an online manner: long-term scene flow estimation (LSFE).
FraGNNet: A Deep Probabilistic Model for Mass Spectrum Prediction
The process of identifying a compound from its mass spectrum is a critical step in the analysis of complex mixtures.
Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion Model
Demonstrating equivalent generative quality to the software baseline, our system achieved remarkable enhancements in generative speed for both unconditional and conditional generation tasks, by factors of 64. 8 and 156. 5, respectively.
NTIRE 2024 Challenge on Image Super-Resolution ($\times$4): Methods and Results
This paper reviews the NTIRE 2024 challenge on image super-resolution ($\times$4), highlighting the solutions proposed and the outcomes obtained.
Efficient and accurate neural field reconstruction using resistive memory
The GE harnesses the intrinsic stochasticity of resistive memory for efficient input encoding, while the PE achieves precise weight mapping through a Hardware-Aware Quantization (HAQ) circuit.
The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking.
WPS-Dataset: A benchmark for wood plate segmentation in bark removal processing
However, the lack of publicly available datasets for wood plate segmentation in bark removal processing poses challenges for researchers in this field.
CRFR: Improving Conversational Recommender Systems via Flexible Fragments Reasoning on Knowledge Graphs
Although paths of user interests shift in knowledge graphs (KGs) can benefit conversational recommender systems (CRS), explicit reasoning on KGs has not been well considered in CRS, due to the complex of high-order and incomplete paths.
Ranked #2 on
Text Generation
on ReDial
Multi-Attribute Controlled Text Generation with Contrastive-Generator and External-Discriminator
To achieve this, we design a contrastive-generator that can effectively generate texts with more attributes.
TopKG: Target-oriented Dialog via Global Planning on Knowledge Graph
We design a global reinforcement learning with the planned paths to flexibly adjust the local response generation model towards the global target.
CR-GIS: Improving Conversational Recommendation via Goal-aware Interest Sequence Modeling
In CRS, implicit patterns of user interest sequence guide the smooth transition of dialog utterances to the goal item.
Dataset Debt in Biomedical Language Modeling
Large-scale language modeling and natural language prompting have demonstrated exciting capabilities for few and zero shot learning in NLP.
