Search Results for author:
Found 140 papers, 68 papers with code
Textomics: A Dataset for Genomics Data Summary Generation
We further illustrate how Textomics can be used to advance other applications, including evaluating scientific paper embeddings and generating masked templates for scientific paper understanding.
Pathway2Text: Dataset and Method for Biomedical Pathway Description Generation
Collectively, we envision our method will become an important benchmark for evaluating Graph2Text methods and advance biomedical research for complex diseases.
Dynamic allocation: extremes, tail dependence, and regime Shifts
By capturing outliers, volatility clustering, and tail dependence in the asset return distribution, we build a sophisticated model to predict the downside risk of the global financial market.
FedAPM: Federated Learning via ADMM with Partial Model Personalization
In federated learning (FL), the assumption that datasets from different devices are independent and identically distributed (i. i. d.)
HAMF: A Hybrid Attention-Mamba Framework for Joint Scene Context Understanding and Future Motion Representation Learning
Motion forecasting represents a critical challenge in autonomous driving systems, requiring accurate prediction of surrounding agents' future trajectories.
ReactDiff: Latent Diffusion for Facial Reaction Generation
Given the audio-visual clip of the speaker, facial reaction generation aims to predict the listener's facial reactions.
UniCAD: Efficient and Extendable Architecture for Multi-Task Computer-Aided Diagnosis System
The growing complexity and scale of visual model pre-training have made developing and deploying multi-task computer-aided diagnosis (CAD) systems increasingly challenging and resource-intensive.
Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation
In recent years, end-to-end speech-to-speech (S2S) dialogue systems have garnered increasing research attention due to their advantages over traditional cascaded systems, including achieving lower latency and more natural integration of nonverbal cues such as emotion and speaker identity.
RoboFlamingo-Plus: Fusion of Depth and RGB Perception with Vision-Language Models for Enhanced Robotic Manipulation
Our research achieves a nuanced fusion of RGB and depth information by integrating a pre-trained Vision Transformer (ViT) with a resampling technique, closely aligning this combined data with linguistic cues for superior multimodal understanding.
TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning
Model customization requires high-quality and diverse datasets, but acquiring such data remains challenging and costly.
DAST: Difficulty-Aware Self-Training on Large Language Models
Present Large Language Models (LLM) self-training methods always under-sample on challenging queries, leading to inadequate learning on difficult problems which limits LLMs' ability.
GrInAdapt: Scaling Retinal Vessel Structural Map Segmentation Through Grounding, Integrating and Adapting Multi-device, Multi-site, and Multi-modal Fundus Domains
Retinal vessel segmentation is critical for diagnosing ocular conditions, yet current deep learning methods are limited by modality-specific challenges and significant distribution shifts across imaging devices, resolutions, and anatomical regions.
Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models
After training on our dataset, the model also exhibits improved performance on other mainstream language tasks.
Med-LEGO: Editing and Adapting toward Generalist Medical Image Diagnosis
The adoption of visual foundation models has become a common practice in computer-aided diagnosis (CAD).
MITracker: Multi-View Integration for Visual Object Tracking
Multi-view object tracking (MVOT) offers promising solutions to challenges such as occlusion and target loss, which are common in traditional single-view tracking.
Group Ligands Docking to Protein Pockets
Molecular docking is a key task in computational biology that has attracted increasing interest from the machine learning community.
UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models
Despite demonstrating impressive capabilities, Large Language Models (LLMs) still often struggle to accurately express the factual knowledge they possess, especially in cases where the LLMs' knowledge boundaries are ambiguous.
MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization
Previous attempts to enhance modality alignment in Med-LVLMs through preference optimization have inadequately mitigated clinical relevance in preference data, making these samples easily distinguishable and reducing alignment effectiveness.
On Simplifying Large-Scale Spatial Vectors: Fast, Memory-Efficient, and Cost-Predictable k-means
Experiments show that when simplifying datasets with scale such as $10^6$, Dask-means uses less than $30$MB of memory, achieves over $168$ times speedup compared to the widely-used Lloyd's algorithm.
An Integral Equation in Portfolio Selection with Time-Inconsistent Preferences
This paper discusses a nonlinear integral equation arising from portfolio selection with a class of time-inconsistent preferences.
LHPF: Look back the History and Plan for the Future in Autonomous Driving
However, these algorithms typically assess the current and historical plans independently, leading to discontinuities in driving intentions and an accumulation of errors with each step in a discontinuous plan.
Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension
To address these challenges, we introduce PepHAR, a hot-spot-driven autoregressive generative model for designing peptides targeting specific proteins.
CropCraft: Inverse Procedural Modeling for 3D Reconstruction of Crop Plants
The ability to automatically build 3D digital twins of plants from images has countless applications in agriculture, environmental science, robotics, and other fields.
FM-TS: Flow Matching for Time Series Generation
FM-TS is more efficient in terms of training and inference.
Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration
In this paper, we present a novel approach, ReverseGen, designed to automatically generate effective training samples that expose the weaknesses of LLMs.
ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom
Notably, the disassociation of capabilities allows seamless integration of existing large language models (LLMs) to compensate for the reasoning deficits of LVLMs.
MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models
Artificial Intelligence (AI) has demonstrated significant potential in healthcare, particularly in disease diagnosis and treatment planning.
MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
This paper addresses this gap by introducing a comprehensive investigation of Multilingual Confidence estimation (MlingConf) on LLMs, focusing on both language-agnostic (LA) and language-specific (LS) tasks to explore the performance and language dominance effects of multilingual confidence estimations on different tasks.
Unleashing the Power of LLMs as Multi-Modal Encoders for Text and Graph-Structured Data
Graph-structured information offers rich contextual information that can enhance language models by providing structured relationships and hierarchies, leading to more expressive embeddings for various applications such as retrieval, question answering, and classification.
QSpec: Speculative Decoding with Complementary Quantization Schemes
Compared to high-precision quantization methods, QSPEC empirically boosts token generation throughput by up to 1. 64x without any quality compromise, distinguishing it from other low-precision quantization approaches.
MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards
The rapid scaling of large language models necessitates more lightweight finetuning methods to reduce the explosive GPU memory overhead when numerous customized models are served simultaneously.
How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models
The rapid evolution of large language models (LLMs) has transformed the competitive landscape in natural language processing (NLP), particularly for English and other data-rich languages.
OCTCube-M: A 3D multimodal optical coherence tomography foundation model for retinal and systemic diseases with cross-cohort and cross-device validation
It then exploits a novel multi-modal contrastive learning framework COEP to integrate other retinal imaging modalities, such as fundus autofluorescence and infrared retinal imaging, into OCTCube, efficiently extending it into multi-modal foundation models.
Unleash the Power of Ellipsis: Accuracy-enhanced Sparse Vector Technique with Exponential Noise
To provide a rigorous DP guarantee for SVT, prior works in the literature adopt a conservative privacy analysis by assuming the direct disclosure of noisy query results as in typical private query releases.
On ADMM in Heterogeneous Federated Learning: Personalization, Robustness, and Fairness
Personalized FL (PFL) is an approach that aims to reduce the impact of statistical heterogeneity by developing personalized models for individual users, while also inherently providing benefits in terms of fairness and robustness.
Panacea: A foundation model for clinical trial search, summarization, design, and recruitment
To address this challenge, we propose a clinical trial foundation model named Panacea, designed to handle multiple tasks, including trial search, trial summarization, trial design, and patient-trial matching.
Data Augmentation of Multi-turn Psychological Dialogue via Knowledge-driven Progressive Thought Prompting
The thought generated by the progressive thought generator serves as a prompt to prevent the generated dialogue from having significant semantic deviations, while the psychology knowledge generator produces psychological knowledge to serve as the dialogue history for the LLM, guiding the dialogue generator to create multi-turn psychological dialogue.
Efficient k-means with Individual Fairness via Exponential Tilting
Our experiments demonstrate that TKM outperforms state-of-the-art methods in effectiveness, fairness, and efficiency.
A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery
In many scientific fields, large language models (LLMs) have revolutionized the way text and other modalities of data (e. g., molecules and proteins) are handled, achieving superior performance in various applications and augmenting the scientific discovery process.
Inter-slice Super-resolution of Magnetic Resonance Images by Pre-training and Self-supervised Fine-tuning
To reduce slice spacing, deep-learning-based super-resolution techniques are widely investigated.
HETHUB: A Distributed Training System with Heterogeneous Cluster for Large-Scale Models
We train the Llama-140B model on a heterogeneous cluster with 768 GPU-accelerators(128 AMD and 640 GPU-accelerator A).
BiomedParse: a biomedical foundation model for image parsing of everything everywhere all at once
On object recognition, which aims to identify all objects in a given image along with their semantic types, we showed that BiomedParse can simultaneously segment and label all biomedical objects in an image (all at once).
Gaze-DETR: Using Expert Gaze to Reduce False Positives in Vulvovaginal Candidiasis Screening
Accurate detection of vulvovaginal candidiasis is critical for women's health, yet its sparse distribution and visually ambiguous characteristics pose significant challenges for accurate identification by pathologists and neural networks alike.
DragTraffic: Interactive and Controllable Traffic Scene Generation for Autonomous Driving
Inspired by DragGAN in image generation, we propose DragTraffic, a generalized, interactive, and controllable traffic scene generation framework based on conditional diffusion.
CopilotCAD: Empowering Radiologists with Report Completion Models and Quantitative Evidence from Medical Image Foundation Models
Computer-aided diagnosis systems hold great promise to aid radiologists and clinicians in radiological clinical practice and enhance diagnostic accuracy and efficiency.
Monocular 3D lane detection for Autonomous Driving: Recent Achievements, Challenges, and Outlooks
This review looks back and analyzes the current state of achievements in the field of 3D lane detection research.
Physical Property Understanding from Language-Embedded Feature Fields
Can computers perceive the physical properties of objects solely through vision?
Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluation
Frontier general-domain models such as GPT-4V still have significant performance gaps in multimodal biomedical applications.
MUC: Mixture of Uncalibrated Cameras for Robust 3D Human Body Reconstruction
Rather than merely averaging the models across views, we develop a neural network trained to assign weights to individual views for all human body joints, based on the estimated distribution of joint distances from each camera.
LoRA Meets Dropout under a Unified Framework
Hence, a possible contradiction arises from negligible trainable parameters of LoRA and the effectiveness of previous dropout methods, which has been largely overlooked.
PRoLoRA: Partial Rotation Empowers More Parameter-Efficient LoRA
Hopefully, the conspicuously higher parameter efficiency can establish PRoLoRA as a resource-friendly alternative to LoRA.
Two-stage Cytopathological Image Synthesis for Augmenting Cervical Abnormality Screening
In the first Global Image Generation stage, a Normal Image Generator is designed to generate cytopathological images full of normal cervical cells.
A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
This paper addresses this gap by introducing a comprehensive investigation of Multilingual Confidence estimation (MlingConf) on LLMs, focusing on both language-agnostic (LA) and language-specific (LS) tasks to explore the performance and language dominance effects of multilingual confidence estimations on different tasks.
T-Rex: Text-assisted Retrosynthesis Prediction
As a fundamental task in computational chemistry, retrosynthesis prediction aims to identify a set of reactants to synthesize a target molecule.
Dynamic portfolio selection under generalized disappointment aversion
This paper addresses the continuous-time portfolio selection problem under generalized disappointment aversion (GDA).
CLIP in Medical Imaging: A Survey
With the aim of facilitating a deeper understanding of this promising direction, this survey offers an in-depth exploration of the CLIP within the domain of medical imaging, regarding both refined CLIP pre-training and CLIP-driven applications.
Mining Gaze for Contrastive Learning toward Computer-Assisted Diagnosis
Accordingly, we introduce the Medical contrastive Gaze Image Pre-training (McGIP) as a plug-and-play module for contrastive learning frameworks.
GDTS: Goal-Guided Diffusion Model with Tree Sampling for Multi-Modal Pedestrian Trajectory Prediction
To address these challenges and facilitate the use of diffusion models in multi-modal trajectory prediction, we propose GDTS, a novel Goal-Guided Diffusion Model with Tree Sampling for multi-modal trajectory prediction.
Dependency Relationships-Enhanced Attentive Group Recommendation in HINs
Finally, we develop an attention aggregator that aggregates users' preferences as the group's preferences for the group recommendation task.
MeLo: Low-rank Adaptation is Better than Fine-tuning for Medical Image Diagnosis
By fixing the weight of ViT models and only adding small low-rank plug-ins, we achieve competitive results on various diagnosis tasks across different imaging modalities using only a few trainable parameters.
Uni-COAL: A Unified Framework for Cross-Modality Synthesis and Super-Resolution of MR Images
Cross-modality synthesis (CMS), super-resolution (SR), and their combination (CMSR) have been extensively studied for magnetic resonance imaging (MRI).
Personalized Federated Learning via ADMM with Moreau Envelope
Our experiments validate that FLAME, when trained on heterogeneous data, outperforms state-of-the-art methods in terms of model performance.
ForeSeer: Product Aspect Forecasting Using Temporal Graph Embedding
ForeSeer transfers reviews from similar products on a large product graph and exploits these reviews to predict aspects that might emerge in future reviews.
MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning
In this paper, we address the limitation above by 1) introducing vision-language Model with Multi-Modal In-Context Learning(MMICL), a new approach to allow the VLM to deal with multi-modal inputs efficiently; 2) proposing a novel context scheme to augment the in-context learning ability of the VLM; 3) constructing the Multi-modal In-Context Learning (MIC) dataset, designed to enhance the VLM's ability to understand complex multi-modal prompts.
Ranked #17 on
Visual Reasoning
on Winoground
AdLER: Adversarial Training with Label Error Rectification for One-Shot Medical Image Segmentation
To address these issues, we propose a novel one-shot medical image segmentation method with adversarial training and label error rectification (AdLER), with the aim of improving the diversity of generated data and correcting label errors to enhance segmentation performance.
Evaluating Large Language Models for Radiology Natural Language Processing
The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP).
CellGAN: Conditional Cervical Cell Synthesis for Augmenting Cytopathological Image Classification
In this paper, we propose CellGAN to synthesize cytopathological images of various cervical cell types for augmenting patch-level cell classification.
Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications
Model pre-training on large text corpora has been demonstrated effective for various downstream applications in the NLP domain.
ChatCAD+: Towards a Universal and Reliable Interactive CAD using LLMs
The integration of Computer-Aided Diagnosis (CAD) with Large Language Models (LLMs) presents a promising frontier in clinical applications, notably in automating diagnostic processes akin to those performed by radiologists and providing consultations similar to a virtual family doctor.
Learning Better Contrastive View from Radiologist's Gaze
Then, we propose a novel augmentation method, i. e., FocusContrast, to learn from radiologists' gaze in diagnosis and generate contrastive views for medical images with guidance from radiologists' visual attention.
A Cognitive Stimulation Dialogue System with Multi-source Knowledge Fusion for Elders with Cognitive Impairment
In this paper, we propose a multi-source knowledge fusion method for CS dialogue (CSD), to generate open-ended responses guided by the CS principle and emotional support strategy.
Domain Generalization for Mammographic Image Analysis with Contrastive Learning
The training of an efficacious deep learning model requires large data with diverse styles and qualities.
Arbitrary Reduction of MRI Inter-slice Spacing Using Hierarchical Feature Conditional Diffusion
Magnetic resonance (MR) images collected in 2D scanning protocols typically have large inter-slice spacing, resulting in high in-plane resolution but reduced through-plane resolution.
DoctorGLM: Fine-tuning your Chinese Doctor is not a Herculean Task
The recent progress of large language models (LLMs), including ChatGPT and GPT-4, in comprehending and responding to human instructions has been remarkable.
BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs
Therefore, training an effective generalist biomedical model requires high-quality multimodal data, such as parallel image-text pairs.
Ranked #2 on
Medical Visual Question Answering
on SLAKE-English
BLIAM: Literature-based Data Synthesis for Synergistic Drug Combination Prediction
Instead of obtaining features from language models, we propose BLIAM, a literature-based data synthesis approach to directly generate training data points that are interpretable and model-agnostic to downstream applications.
ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Models
Large language models (LLMs) have recently demonstrated their potential in clinical applications, providing valuable medical knowledge and advice.
RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation
However, learning a robust representation from numerous unlabeled images remains challenging due to potential noise in pseudo labels and insufficient class separability in feature space, which undermines the performance of current semi-supervised segmentation approaches.
Robust One-shot Segmentation of Brain Tissues via Image-aligned Style Transformation
In this paper, we propose a novel image-aligned style transformation to reinforce the dual-model iterative learning for robust one-shot segmentation of brain tissues.
Retrieval augmentation of large language models for lay language generation
Recent lay language generation systems have used Transformer models trained on a parallel corpus to increase health information accessibility.
MetaFill: Text Infilling for Meta-Path Generation on Heterogeneous Information Networks
Meta-path, a sequence of node types and edge types, is the core technique to embed HINs.
Modern Tontine with Transaction Costs
The wealth of the retiree is divided into a bequest account and a tontine account.
POPDx: An Automated Framework for Patient Phenotyping across 392,246 Individuals in the UK Biobank Study
We describe a method for phenotype recognition that imputes phenotype codes for all UK Biobank participants.
TBI-GAN: An Adversarial Learning Approach for Data Synthesis on Traumatic Brain Segmentation
To address these issues, we propose a novel medical image inpainting model named TBI-GAN to synthesize TBI MR scans with paired brain label maps.
Brain-Aware Replacements for Supervised Contrastive Learning in Detection of Alzheimer's Disease
On top of BAR, we propose using a soft-label-capable supervised contrastive loss, aiming to learn the relative similarity of representations that reflect how mixed are the synthetic MRIs using our soft labels.
Accurate RNA 3D structure prediction using a language model-based deep learning approach
Accurate prediction of RNA three-dimensional (3D) structure remains an unsolved challenge.
A fully differentiable ligand pose optimization framework guided by deep learning and traditional scoring functions
In this work, we propose a fully differentiable framework for ligand pose optimization based on a hybrid scoring function (SF) combined with a multi-layer perceptron (DeepRMSD) and the traditional AutoDock Vina SF.
Graph-in-Graph Network for Automatic Gene Ontology Description Generation
This task aims to automatically generate a sentence that describes the function of a GO term belonging to one of the three categories, i. e., molecular function, biological process, and cellular component.
Hedging option books using neural-SDE market models
We study the capability of arbitrage-free neural-SDE market models to yield effective strategies for hedging options.
Eye-gaze-guided Vision Transformer for Rectifying Shortcut Learning
To address this problem, we propose to infuse human experts' intelligence and domain knowledge into the training of deep neural networks.
Spatial Attention-based Implicit Neural Representation for Arbitrary Reduction of MRI Slice Spacing
Magnetic resonance (MR) images collected in 2D clinical protocols typically have large inter-slice spacing, resulting in high in-plane resolution and reduced through-plane resolution.
Seed-Guided Topic Discovery with Out-of-Vocabulary Seeds
Discovering latent topics from text corpora has been studied for decades.
ProTranslator: zero-shot protein function prediction using textual description
Here, we tackle this problem by annotating proteins to a function only based on its textual description so that we do not need to know any associated proteins for this function.
Follow My Eye: Using Gaze to Supervise Computer-Aided Diagnosis
In this paper, we demonstrate that the eye movement of radiologists reading medical images can be a new form of supervision to train the DNN-based computer-aided diagnosis (CAD) system.
Estimating risks of option books using neural-SDE market models
In this paper, we examine the capacity of an arbitrage-free neural-SDE market model to produce realistic scenarios for the joint dynamics of multiple European options on a single underlying.
Adaptive Transfer Learning for Plant Phenotyping
Plant phenotyping (Guo et al. 2021; Pieruschka et al. 2019) focuses on studying the diverse traits of plants related to the plants' growth.
Knee Cartilage Defect Assessment by Graph Representation and Surface Convolution
Knee osteoarthritis (OA) is the most common osteoarthritis and a leading cause of disability.
SurvODE: Extrapolating Gene Expression Distribution for Early Cancer Identification
With the increasingly available large-scale cancer genomics datasets, machine learning approaches have played an important role in revealing novel insights into cancer development.
Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive Learning
Specifically, the backbone network is firstly trained with a multi-style and multi-view unsupervised self-learning scheme for the embedding of invariant features to various vendor-styles.
GraphPrompt: Graph-Based Prompt Templates for Biomedical Synonym Prediction
In the expansion of biomedical dataset, the same category may be labeled with different terms, thus being tedious and onerous to curate these terms.
Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation
KGAE consists of a pre-constructed knowledge graph, a knowledge-driven encoder and a knowledge-driven decoder.
Joint Progressive and Coarse-to-fine Registration of Brain MRI via Deformation Field Integration and Non-Rigid Feature Fusion
Registration of brain MRI images requires to solve a deformation field, which is extremely difficult in aligning intricate brain tissues, e. g., subcortical nuclei, etc.
Leveraging the Cell Ontology to classify unseen cell types
Single cell technologies are rapidly generating large amounts of data that enables us to understand biological systems at single-cell resolution.
Graphine: A Dataset for Graph-aware Terminology Definition Generation
Unfortunately, the lack of large-scale terminology definition dataset hinders the process toward definition generation.
Combined Trojan Y Chromosome Strategy and Sterile Insect Technique to Eliminate Mosquitoes: Modelling and Analysis
Sterile insect technique has been successfully applied in the control of agricultural pests, however, it has a limited ability to control mosquitoes.
UniFaceGAN: A Unified Framework for Temporally Consistent Facial Video Editing
Compared with the state-of-the-art facial image editing methods, our framework generates video portraits that are more photo-realistic and temporally smooth.
Adaptive Residue-wise Profile Fusion for Low Homologous Protein SecondaryStructure Prediction Using External Knowledge
Protein secondary structure prediction (PSSP) is essential for protein function analysis.
Shallow Feature Matters for Weakly Supervised Object Localization
In practice, our SPOL model first generates the CAMs through a novel element-wise multiplication of shallow and deep feature maps, which filters the background noise and generates sharper boundaries robustly.
DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation
In this paper, we propose a novel disentangled heterogeneous graph attention network DisenHAN for top-$N$ recommendation, which learns disentangled user/item representations from different aspects in a heterogeneous information network.
Arbitrage-free neural-SDE market models
Modelling joint dynamics of liquid vanilla options is crucial for arbitrage-free pricing of illiquid derivatives and managing risks of option trade books.
EBM-Fold: Fully-Differentiable Protein Folding Powered by Energy-based Models
In this paper, we propose a fully-differentiable approach for protein structure optimization, guided by a data-driven generative network.
tFold-TR: Combining Deep Learning Enhanced Hybrid Potential Energy for Template-Based Modeling Structure Refinement
Protein structure prediction has been a grand challenge for over 50 years, owing to its broad scientific and application interests.
A Reinforcement Learning Based R-Tree for Spatial Data Indexing in Dynamic Environments
Learned indices have been proposed to replace classic index structures like B-Tree with machine learning (ML) models.
InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring
Compared with the visual grounding on 2D images, the natural-language-guided 3D object localization on point clouds is more challenging.
Towards Accurate Active Camera Localization
These approaches localize the camera in the discrete pose space and are agnostic to the localization-driven scene property, which restricts the camera pose accuracy in the coarse scale.
On the Efficiency of K-Means Clustering: Evaluation, Optimization, and Algorithm Selection
This paper presents a thorough evaluation of the existing methods that accelerate Lloyd's algorithm for fast k-means clustering.
High-Fidelity 3D Digital Human Head Creation from RGB-D Selfies
We present a fully automatic system that can produce high-fidelity, photo-realistic 3D digital human heads with a consumer RGB-D selfie camera.
Detecting and repairing arbitrage in traded option prices
In addition, we show that removing arbitrage from prices data by our repair method can improve model calibration with enhanced robustness and reduced calibration error.
Boosting Ant Colony Optimization via Solution Prediction and Machine Learning
In the first phase of our ML-ACO algorithm, an ML model is trained using a set of small problem instances where the optimal solution is known.
STADB: A Self-Thresholding Attention Guided ADB Network for Person Re-identification
Specifically, STADB first obtains an attention map by channel-wise pooling and returns a drop mask by thresholding the attention map.
Task-agnostic Temporally Consistent Facial Video Editing
Compared with the state-of-the-art facial image editing methods, our framework generates video portraits that are more photo-realistic and temporally smooth.
mr2NST: Multi-Resolution and Multi-Reference Neural Style Transfer for Mammography
However, the image styles of different vendors are very distinctive, and there may exist domain gap among different vendors that could potentially compromise the universal applicability of one deep learning model.
Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation
Unsupervised domain adaptation enables to alleviate the need for pixel-wise annotation in the semantic segmentation.
Ranked #28 on
Domain Adaptation
on SYNTHIA-to-Cityscapes
Analysis of Indexing Structures for Immutable Data
We establish the worst-case guarantees of each index in terms of these five metrics, and we experimentally evaluate all indexes in a large variety of settings.
Databases
PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling
Extensive experiments verify the robustness and superiority of our approach in point clouds processing tasks regardless of synthesis data, indoor data, and outdoor data with or without noise.
Ranked #27 on
Semantic Segmentation
on S3DIS
Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation
We investigate the posterior collapse problem of current RNN-based VAEs for molecule sequence generation.
PANDA: Facilitating Usable AI Development
In many complex applications such as healthcare, subject matter experts (e. g. Clinicians) are the ones who appreciate the importance of features that affect health, and their knowledge together with existing knowledge bases are critical to the end results.
Rafiki: Machine Learning as an Analytics Service System
Second, expertise knowledge is required to optimize the training and inference procedures in terms of efficiency and effectiveness, which imposes heavy burden on the system users.
ForkBase: An Efficient Storage Engine for Blockchain and Forkable Applications
By integrating the core application properties into the storage, ForkBase not only delivers high performance but also reduces development effort.
Databases Cryptography and Security Distributed, Parallel, and Cluster Computing
Adaptive Graph Convolutional Neural Networks
Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks.
Folding membrane proteins by deep transfer learning
Computational elucidation of membrane protein (MP) structures is challenging partially due to lack of sufficient solved structures for homology modeling.
Robust Contextual Bandit via the Capped-$\ell_{2}$ norm
In the critic updating, the capped-$\ell_{2}$ norm is used to measure the approximation error, which prevents outliers from dominating our objective.
Predicting membrane protein contacts from non-membrane proteins by deep transfer learning
Tested on 510 non-redundant MPs, our deep model (learned from only non-MPs) has top L/10 long-range contact prediction accuracy 0. 69, better than our deep model trained by only MPs (0. 63) and much better than a representative DCA method CCMpred (0. 47) and the CASP11 winner MetaPSICOV (0. 55).
Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model
Using our predicted contacts as restraints, we can (ab initio) fold 208 of the 398 membrane proteins with TMscore>0. 5.
Deep Learning At Scale and At Ease
The other is scalability, that is the deep learning system must be able to provision for a huge demand of computing resources for training large models with massive datasets.
Protein secondary structure prediction using deep convolutional neural fields
Protein secondary structure (SS) prediction is important for studying protein structure and function.
Ranked #1 on
Protein Secondary Structure Prediction
on CullPDB
AUC-maximized Deep Convolutional Neural Fields for Sequence Labeling
Our experimental results confirm that maximum-AUC greatly outperforms the other two training methods on 8-state secondary structure prediction and disorder prediction since their label distributions are highly imbalanced and also have similar performance as the other two training methods on the solvent accessibility prediction problem which has three equally-distributed labels.
Feature Learning based Deep Supervised Hashing with Pairwise Labels
For another common application scenario with pairwise labels, there have not existed methods for simultaneous feature learning and hash-code learning.
MRFalign: Protein Homology Detection through Alignment of Markov Random Fields
A sequence profile is usually represented as a position-specific scoring matrix (PSSM) or an HMM (Hidden Markov Model) and accordingly PSSM-PSSM or HMM-HMM comparison is used for homolog detection.
Protein Contact Prediction by Integrating Joint Evolutionary Coupling Analysis and Supervised Learning
To further improve the accuracy of the estimated precision matrices, we employ a supervised learning method to predict contact probability from a variety of evolutionary and non-evolutionary information and then incorporate the predicted probability as prior into our GGL framework.
