Search Results for author:
Found 470 papers, 185 papers with code
QuickGraph: A Rapid Annotation Tool for Knowledge Graph Extraction from Technical Text
Acquiring high-quality annotated corpora for complex multi-task information extraction (MT-IE) is an arduous and costly process for human-annotators.
PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow Estimation
We propose a novel end-to-end deep scene flow model, called PointPWC-Net, that directly processes 3D point cloud scenes with large motions in a coarse-to-fine fashion.
Lexicon-Based Graph Convolutional Network for Chinese Word Segmentation
Experimental results on five benchmarks and four cross-domain datasets show the lexicon-based graph convolutional network successfully captures the information of candidate words and helps to improve performance on the benchmarks (Bakeoff-2005 and CTB6) and the cross-domain datasets (SIGHAN-2010).
CIST@CL-SciSumm 2020, LongSumm 2020: Automatic Scientific Document Summarization
In the LongSumm shared task, we integrate both the extractive and abstractive summarization ways.
LexiClean: An annotation tool for rapid multi-task lexical normalisation
LexiClean’s main contribution is support for simultaneous in situ token-level modification and annotation that can be rapidly applied corpus wide.
End-to-end Speech Translation System Description of LIT for IWSLT 2019
We propose layer-tied self-attention for end-to-end speech translation.
What Causes the Failure of Explicit to Implicit Discourse Relation Recognition?
We consider an unanswered question in the discourse processing community: why do relation classifiers trained on explicit examples (with connectives removed) perform poorly in real implicit scenarios?
Variational Graph Auto-Encoder Based Inductive Learning Method for Semi-Supervised Classification
Graph representation learning is a fundamental research issue in various domains of applications, of which the inductive learning problem is particularly challenging as it requires models to generalize to unseen graph structures during inference.
CodeS: Natural Language to Code Repository via Multi-Layer Sketch
For feedback-based evaluation, we develop a VSCode plugin for CodeS and engage 30 participants in conducting empirical studies.
Event-Triggered State Estimation Through Confidence Level
This paper considers the state estimation problem for discrete-time linear systems under event-triggered scheme.
Reversible Jump Attack to Textual Classifiers with Modification Reduction
Recent studies on adversarial examples expose vulnerabilities of natural language processing (NLP) models.
LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models
Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts.
LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything Model
Benefiting from the popularity and scalably usability of Segment Anything Model (SAM), we first extract different regions according to semantic information and then track them through the video stream to maintain the temporal consistency.
OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models
We also observe that the initiation denoising timestep for noise blending is the key to identity preservation and layout.
Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples
In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models.
DialogGen: Multi-modal Interactive Dialogue System for Multi-turn Text-to-Image Generation
However, many of these works face challenges in identifying correct output modalities and generating coherent images accordingly as the number of output modalities increases and the conversations go deeper.
Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts
Despite recent advances in image-to-video generation, better controllability and local animation are less explored.
Category-Agnostic Pose Estimation for Point Clouds
The goal of object pose estimation is to visually determine the pose of a specific object in the RGB-D input.
RIS-Enabled Joint Near-Field 3D Localization and Synchronization in SISO Multipath Environments
Reconfigurable Intelligent Surfaces (RIS) show great promise in the realm of 6th generation (6G) wireless systems, particularly in the areas of localization and communication.
ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval
Specifically, our proposed ToolRerank includes Adaptive Truncation, which truncates the retrieval results related to seen and unseen tools at different positions, and Hierarchy-Aware Reranking, which makes retrieval results more concentrated for single-tool queries and more diverse for multi-tool queries.
Large Language Models are In-Context Molecule Learners
Specifically, ICMA incorporates the following three stages: Hybrid Context Retrieval, Post-retrieval Re-ranking, and In-context Molecule Tuning.
Modality-Agnostic Structural Image Representation Learning for Deformable Multi-Modality Medical Image Registration
Existing multi-modality image registration algorithms rely on statistical-based similarity measures or local structural image representations.
A Comprehensive Evaluation of Quantization Strategies for Large Language Models
Our experimental results indicate that LLMs with 4-bit quantization can retain performance comparable to their non-quantized counterparts, and perplexity can serve as a proxy metric for quantized LLMs on most benchmarks.
Multi-Constraint Safe RL with Objective Suppression for Safety-Critical Applications
Safe reinforcement learning tasks with multiple constraints are a challenging domain despite being very common in the real world.
Analysing The Impact of Sequence Composition on Language Model Pre-Training
In this work, we find that applying causal masking can lead to the inclusion of distracting information from previous documents during pre-training, which negatively impacts the performance of the models on language modelling and downstream tasks.
AICAttack: Adversarial Image Captioning Attack with Attention-Based Optimization
At the intersection of CV and NLP is the problem of image captioning, where the related models' robustness against adversarial attacks has not been well studied.
ChemLLM: A Chemical Large Language Model
ChemLLM beats GPT-3. 5 on all three principal tasks in chemistry, i. e., name conversion, molecular caption, and reaction prediction, and surpasses GPT-4 on two of them.
Poisson Process for Bayesian Optimization
BayesianOptimization(BO) is a sample-efficient black-box optimizer, and extensive methods have been proposed to build the absolute function response of the black-box function through a probabilistic surrogate model, including Tree-structured Parzen Estimator (TPE), random forest (SMAC), and Gaussian process (GP).
NFT1000: A Visual Text Dataset For Non-Fungible Token Retrieval
With the rise of 'Metaverse' and 'Web3. 0', NFT ( Non-Fungible Token ) has emerged as a kind of pivotal digital asset, garnering significant attention.
Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain
We expect that agents should learn to enhance the extent to which humans achieve these goals while maintaining agents' original abilities (e. g., winning games).
A Systematic Literature Review on Explainability for Machine/Deep Learning-based Software Engineering Research
The remarkable achievements of Artificial Intelligence (AI) algorithms, particularly in Machine Learning (ML) and Deep Learning (DL), have fueled their extensive deployment across multiple sectors, including Software Engineering (SE).
Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
Once attackers maliciously induce high energy consumption and latency time (energy-latency cost) during inference of VLMs, it will exhaust computational resources.
The Radiation Oncology NLP Database
ROND is specifically designed to address this gap in the domain of radiation oncology, a field that offers many opportunities for NLP exploration.
LUPET: Incorporating Hierarchical Information Path into Multilingual ASR
Many factors have separately shown their effectiveness on improving multilingual ASR.
TopCoW: Benchmarking Topology-Aware Anatomical Segmentation of the Circle of Willis (CoW) for CTA and MRA
The TopCoW dataset was the first public dataset with voxel-level annotations for thirteen possible CoW vessel components, enabled by virtual-reality (VR) technology.
DrugAssist: A Large Language Model for Molecule Optimization
Recently, the impressive performance of large language models (LLMs) on a wide range of tasks has attracted an increasing number of attempts to apply LLMs in drug discovery.
Experiential Co-Learning of Software-Developing Agents
Recent advancements in large language models (LLMs) have brought significant changes to various domains, especially through LLM-driven autonomous agents.
What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
We present deita (short for Data-Efficient Instruction Tuning for Alignment), a series of models fine-tuned from LLaMA and Mistral models using data samples automatically selected with our proposed approach.
DreamTuner: Single Image is Enough for Subject-Driven Generation
Diffusion-based models have demonstrated impressive capabilities for text-to-image generation and are expected for personalized applications of subject-driven generation, which require the generation of customized concepts with one or a few reference images.
Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling
Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to target domains where only rarely labeled data is available.
T-Code: Simple Temporal Latent Code for Efficient Dynamic View Synthesis
Novel view synthesis for dynamic scenes is one of the spotlights in computer vision.
Local Conditional Controlling for Text-to-Image Diffusion Models
In this paper, we introduce a new simple yet practical task setting: local control.
Enhancing the Rationale-Input Alignment for Self-explaining Rationalization
Rationalization empowers deep learning models with self-explaining capabilities through a cooperative game, where a generator selects a semantically consistent subset of the input as a rationale, and a subsequent predictor makes predictions based on the selected rationale.
MobileUtr: Revisiting the relationship between light-weight CNN and Transformer for efficient medical image segmentation
This work revisits the relationship between CNNs and Transformers in lightweight universal networks for medical image segmentation, aiming to integrate the advantages of both worlds at the infrastructure design level.
SRSNetwork: Siamese Reconstruction-Segmentation Networks based on Dynamic-Parameter Convolution
In this paper, we present a high-performance deep neural network for weak target image segmentation, including medical image segmentation and infrared image segmentation.
Noisy probing dose facilitated dose prediction for pencil beam scanning proton therapy: physics enhances generalizability
The noisy probing dose method showed better generalizability in the 6 outlier cases than the ROI-based and beam mask-based methods with 3D Gamma passing rates (for prostate cancer, targets: 89. 32%$\pm$1. 45% vs. 93. 48%$\pm$1. 51% vs. 96. 79%$\pm$0. 83%, OARs: 85. 87%$\pm$1. 73% vs. 91. 15%$\pm$1. 13% vs. 94. 29%$\pm$1. 01%).
SmoothVideo: Smooth Video Synthesis with Noise Constraints on Diffusion Models for One-shot Video Tuning
By applying the loss to existing one-shot video tuning methods, we significantly improve the overall consistency and smoothness of the generated videos.
BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP
Contrastive Vision-Language Pre-training, known as CLIP, has shown promising effectiveness in addressing downstream image recognition tasks.
FBChain: A Blockchain-based Federated Learning Model with Efficiency and Secure Communication
This article proposes Blockchain-based Federated Learning (FBChain) model for federated learning parameter communication to overcome the above two problems.
Damped Proximal Augmented Lagrangian Method for weakly-Convex Problems with Convex Constraints
For the former case, DPALM achieves the complexity of $\widetilde{\mathcal{O}}\left(\varepsilon^{-2. 5} \right)$ to produce an $\varepsilon$-KKT point by applying an accelerated proximal gradient (APG) method to each DPALM subproblem.
Holistic Evaluation of GPT-4V for Biomedical Imaging
GPT-4V represents a breakthrough in artificial general intelligence (AGI) for computer vision, with applications in the biomedical domain.
Evaluating Large Language Models in Ophthalmology
Methods: A 100-item ophthalmology single-choice test was administered to three different LLMs (GPT-3. 5, GPT-4, and PaLM2) and three different professional levels (medical undergraduates, medical masters, and attending physicians), respectively.
Evaluating multiple large language models in pediatric ophthalmology
IMPORTANCE The response effectiveness of different large language models (LLMs) and various individuals, including medical students, graduate students, and practicing physicians, in pediatric ophthalmology consultations, has not been clearly established yet.
Evaluating the Potential of Leading Large Language Models in Reasoning Biology Questions
Recent advances in Large Language Models (LLMs) have presented new opportunities for integrating Artificial General Intelligence (AGI) into biological research and education.
Discussing the Spectra of Physics-Enhanced Machine Learning via a Survey on Structural Mechanics Applications
The intersection of physics and machine learning has given rise to a paradigm that we refer to here as physics-enhanced machine learning (PEML), aiming to improve the capabilities and reduce the individual shortcomings of data- or physics-only methods.
From Indeterminacy to Determinacy: Augmenting Logical Reasoning Capabilities with Large Language Models
To address these challenges, we propose DetermLR, a novel reasoning framework that formulates the reasoning process as a transformational journey from indeterminate premises to determinate ones.
Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networks
Also, most of current ERE models do not take into account higher-order interactions between multiple entities and relations, while higher-order modeling could be beneficial. In this work, we propose HyperGraph neural network for ERE ($\hgnn{}$), which is built upon the PL-marker (a state-of-the-art marker-based pipleline model).
Simple Hardware-Efficient PCFGs with Independent Left and Right Productions
Scaling dense PCFGs to thousands of nonterminals via a low-rank parameterization of the rule probability tensor has been shown to be beneficial for unsupervised parsing.
Benchmarking a foundation LLM on its ability to re-label structure names in accordance with the AAPM TG-263 report
Conclusions: Given the accuracy of GPT-4 in re-labeling structure names of both target volumes and normal tissues as presented in this work, LLMs are poised to be the preferred method for standardizing structure names in radiation oncology, especially considering the rapid advancements in LLM capabilities that are likely to continue.
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
We thus propose VIDAL-10M with Video, Infrared, Depth, Audio and their corresponding Language, naming as VIDAL-10M.
Ranked #1 on
Zero-shot Audio Classification
on VGG-Sound
(using extra training data)
D-Separation for Causal Self-Explanation
Instead of attempting to rectify the issues of the MMI criterion, we propose a novel criterion to uncover the causal rationale, termed the Minimum Conditional Dependence (MCD) criterion, which is grounded on our finding that the non-causal features and the target label are \emph{d-separated} by the causal rationale.
Sparsely Shared LoRA on Whisper for Child Speech Recognition
Child speech, as a representative type of low-resource speech, is leveraged for adaptation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
CoMFLP: Correlation Measure based Fast Search on ASR Layer Pruning
The search process is carried out in two steps: (1) coarse search: to determine top $K$ candidates by pruning the most redundant layers based on the correlation matrix; (2) fine search: to select the best pruning proposal among $K$ candidates using a task-specific evaluation metric.
PolicyGPT: Automated Analysis of Privacy Policies with Large Language Models
In this study, we investigate a privacy policy text analysis framework PolicyGPT based on the LLM.
RadOnc-GPT: A Large Language Model for Radiation Oncology
This paper presents RadOnc-GPT, a large language model specialized for radiation oncology through advanced tuning methods.
Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimation
Additionally, we introduce the detail-enhanced DepthNet with an extra full-scale branch in the encoder and a grid decoder to enhance the restoration of fine details in depth maps.
DiffusionEngine: Diffusion Model is Scalable Data Engine for Object Detection
This paper reveals that the recently developed Diffusion Model is a scalable data engine for object detection.
MathAttack: Attacking Large Language Models Towards Math Solving Ability
Instead of attacking prompts in the use of LLMs, we propose a MathAttack model to attack MWP samples which are closer to the essence of security in solving math problems.
Radiology-Llama2: Best-in-Class Large Language Model for Radiology
This paper introduces Radiology-Llama2, a large language model specialized for radiology through a process known as instruction tuning.
Master-slave Deep Architecture for Top-K Multi-armed Bandits with Non-linear Bandit Feedback and Diversity Constraints
We propose a novel master-slave architecture to solve the top-$K$ combinatorial multi-armed bandits problem with non-linear bandit feedback and diversity constraints, which, to the best of our knowledge, is the first combinatorial bandits setting considering diversity constraints under bandit feedback.
SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding
However, LLMs are sometimes too footloose for natural language understanding (NLU) tasks which always have restricted output and input format.
LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image Enhancement
In this paper, we address this limitation by proposing a degradation-aware learning scheme for LLIE using diffusion models, which effectively integrates degradation and image priors into the diffusion process, resulting in improved image enhancement.
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).
Semi-supervised Cycle-GAN for face photo-sketch translation in the wild
Experiments show that SCG achieves competitive performance on public benchmarks and superior results on photos in the wild.
A Novel Multi-Task Model Imitating Dermatologists for Accurate Differential Diagnosis of Skin Diseases in Clinical Images
Skin diseases are among the most prevalent health issues, and accurate computer-aided diagnosis methods are of importance for both dermatologists and patients.
Communicative Agents for Software Development
At the core of this paradigm lies ChatDev, a virtual chat-powered software development company that mirrors the established waterfall model, meticulously dividing the development process into four distinct chronological stages: designing, coding, testing, and documenting.
First-order Methods for Affinely Constrained Composite Non-convex Non-smooth Problems: Lower Complexity Bound and Near-optimal Methods
In this paper, we make the first attempt to establish lower complexity bounds of FOMs for solving a class of composite non-convex non-smooth optimization with linear constraints.
SAMAug: Point Prompt Augmentation for Segment Anything Model
Starting with an initial point prompt, SAM produces an initial mask, which is then fed into our proposed SAMAug to generate augmented point prompts.
DreamIdentity: Improved Editability for Efficient Face-identity Preserved Image Generation
While large-scale pre-trained text-to-image models can synthesize diverse and high-quality human-centric images, an intractable problem is how to preserve the face identity for conditioned face images.
CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?
We present the Chinese Elementary School Math Word Problems (CMATH) dataset, comprising 1. 7k elementary school-level math word problems with detailed annotations, source from actual Chinese workbooks and exams.
Segment Anything Model (SAM) for Radiation Oncology
Given that SAM, a model pre-trained purely on natural images, can handle the delineation of OARs from medical images with clinically acceptable accuracy, these results highlight SAM's robust generalization capabilities with consistent accuracy in automatic segmentation for radiotherapy.
UniMC: A Unified Framework for Long-Term Memory Conversation via Relevance Representation Learning
In this paper, we propose a Unified framework for Long-term Memory Conversations (UniMC), which increases the connection between different stages by learning relevance representation.
Radiology-GPT: A Large Language Model for Radiology
We introduce Radiology-GPT, a large language model for radiology.
Deep learning radiomics for assessment of gastroesophageal varices in people with compensated advanced chronic liver disease
Validation analysis revealed that the AUCs of DLRP were 0. 91 for GEV (95% CI 0. 90 to 0. 93, p < 0. 05) and 0. 88 for HRV (95% CI 0. 86 to 0. 89, p < 0. 01), which were significantly and robustly better than canonical risk indicators, including the value of LSM and SSM.
Global and Local Semantic Completion Learning for Vision-Language Pre-training
MGSC promotes learning more representative global features, which have a great impact on the performance of downstream tasks, while MLTC reconstructs modal-fusion local tokens, further enhancing accurate comprehension of multimodal data.
Modeling Structural Similarities between Documents for Coherence Assessment with Graph Convolutional Networks
Coherence is an important aspect of text quality, and various approaches have been applied to coherence modeling.
Annotation-Inspired Implicit Discourse Relation Classification with Auxiliary Discourse Connective Generation
Implicit discourse relation classification is a challenging task due to the absence of discourse connectives.
Artificial General Intelligence for Medical Imaging
In this review, we explore the potential applications of Artificial General Intelligence (AGI) models in healthcare, focusing on foundational Large Language Models (LLMs), Large Vision Models, and Large Multimodal Models.
GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions
Second, we introduce a residual dense transformer block (RDTB) as the final GridFormer layer.
Exploring the Compositional Generalization in Context Dependent Text-to-SQL Parsing
Based on these observations, we propose a method named \texttt{p-align} to improve the compositional generalization of Text-to-SQL models.
BiomedGPT: A Unified and Generalist Biomedical Generative Pre-trained Transformer for Vision, Language, and Multimodal Tasks
Conventional task- and modality-specific artificial intelligence (AI) models are inflexible in real-world deployment and maintenance for biomedicine.
Ranked #1 on
Text Summarization
on MeQSum
KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration
By spearheading the integration of Multilateration with facial analysis, KeyPosS marks a paradigm shift in facial landmark detection.
Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraint
However, such a cooperative game may incur the degeneration problem where the predictor overfits to the uninformative pieces generated by a not yet well-trained generator and in turn, leads the generator to converge to a sub-optimal model that tends to select senseless pieces.
Diffusion-Based Mel-Spectrogram Enhancement for Personalized Speech Synthesis with Found Data
One way to address this problem is to pre-enhance the speech with an enhancement model and then use the enhanced data for text-to-speech (TTS) model training.
MGR: Multi-generator Based Rationalization
Rationalization is to employ a generator and a predictor to construct a self-explaining NLP model in which the generator selects a subset of human-intelligible pieces of the input text to the following predictor.
Instruction-ViT: Multi-Modal Prompts for Instruction Learning in ViT
Prompts have been proven to play a crucial role in large language models, and in recent years, vision models have also been using prompts to improve scalability for multiple downstream tasks.
Img2Vec: A Teacher of High Token-Diversity Helps Masked AutoEncoders
To study which type of deep features is appropriate for MIM as a learning target, we propose a simple MIM framework with serials of well-trained self-supervised models to convert an Image to a feature Vector as the learning target of MIM, where the feature extractor is also known as a teacher model.
Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective
MOBA games, e. g., Dota2 and Honor of Kings, have been actively used as the testbed for the recent AI research on games, and various AI systems have been developed at the human level so far.
Deep-Learning-based Fast and Accurate 3D CT Deformable Image Registration in Lung Cancer
Conclusion: A patient-specific vision-transformer-based network was developed and shown to be accurate and efficient to reconstruct 3D CT images from kV images.
Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Task
To this end, in this study, we evaluate the performance of ChatGPT/GPT-4 on a radiology NLI task and compare it to other models fine-tuned specifically on task-related data samples.
Evaluating Large Language Models on a Highly-specialized Topic, Radiation Oncology Physics
We present the first study to investigate Large Language Models (LLMs) in answering radiation oncology physics questions.
SoftCLIP: Softer Cross-modal Alignment Makes CLIP Stronger
During the preceding biennium, vision-language pre-training has achieved noteworthy success on several downstream tasks.
Plug-and-Play Regulators for Image-Text Matching
Exploiting fine-grained correspondence and visual-semantic alignments has shown great potential in image-text matching.
Ranked #2 on
Image Retrieval
on Flickr30K 1K test
DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4
The digitization of healthcare has facilitated the sharing and re-using of medical data but has also raised concerns about confidentiality and privacy.
STGIC: a graph and image convolution-based method for spatial transcriptomic clustering
Spatial transcriptomic (ST) clustering employs spatial and transcription information to group spots spatially coherent and transcriptionally similar together into the same spatial domain.
CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attention
On the one hand, CEL blends each token with multiple patches of different scales, providing the self-attention module itself with cross-scale features.
Frauds Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process
In response, this study proposes a new method called the Fraud's Bargain Attack (FBA), which uses a randomization mechanism to expand the search space and produce high-quality adversarial examples with a higher probability of success.
OmniForce: On Human-Centered, Large Model Empowered and Cloud-Edge Collaborative AutoML System
Automated machine learning (AutoML) seeks to build ML models with minimal human effort.
Q-Cogni: An Integrated Causal Reinforcement Learning Framework
We present Q-Cogni, an algorithmically integrated causal reinforcement learning framework that redesigns Q-Learning with an autonomous causal structure discovery method to improve the learning process with causal inference.
AugGPT: Leveraging ChatGPT for Text Data Augmentation
Text data augmentation is an effective strategy for overcoming the challenge of limited sample sizes in many natural language processing (NLP) tasks.
Leveraging phone-level linguistic-acoustic similarity for utterance-level pronunciation scoring
Recent studies on pronunciation scoring have explored the effect of introducing phone embeddings as reference pronunciation, but mostly in an implicit manner, i. e., addition or concatenation of reference phone embedding and actual pronunciation of the target phone as the phone-level pronunciation quality representation.
Mask-guided BERT for Few Shot Text Classification
The main challenge of FSL is the difficulty of training robust models on small amounts of samples, which frequently leads to overfitting.
An ASR-free Fluency Scoring Approach with Self-Supervised Learning
A typical fluency scoring system generally relies on an automatic speech recognition (ASR) system to obtain time stamps in input speech for either the subsequent calculation of fluency-related features or directly modeling speech fluency with an end-to-end approach.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Design Booster: A Text-Guided Diffusion Model for Image Translation with Spatial Layout Preservation
Specifically, our method co-encodes images and text into a new domain during the training phase.
Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization
Recent success in Deep Reinforcement Learning (DRL) methods has shown that policy optimization with respect to an off-policy distribution via importance sampling is effective for sample reuse.
CFFT-GAN: Cross-domain Feature Fusion Transformer for Exemplar-based Image Translation
In this paper, we propose a more general learning approach by considering two domain features as a whole and learning both inter-domain correspondence and intra-domain potential information interactions.
HDFormer: High-order Directed Transformer for 3D Human Pose Estimation
Human pose estimation is a challenging task due to its structured data sequence nature.
Ranked #74 on
3D Human Pose Estimation
on Human3.6M
ReGANIE: Rectifying GAN Inversion Errors for Accurate Real Image Editing
Specifically, in Phase I, a W-space-oriented StyleGAN inversion network is trained and used to perform image inversion and editing, which assures the editability but sacrifices reconstruction quality.
Planning and Tracking Control of Full Drive-by-Wire Electric Vehicles in Unstructured Scenario
Full drive-by-wire electric vehicles (FDWEV) with X-by-wire technology can achieve independent driving, braking, and steering of each wheel, providing a good application platform for autonomous driving technology.
Heterogeneous Diversity Driven Active Learning for Multi-Object Tracking
HD-AMOT defines the diversified informative representation by encoding the geometric and semantic information, and formulates the frame inference strategy as a Markov decision process to learn an optimal sampling policy based on the designed informative representation.
MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions
In this paper, we propose a framework, MoralDial to train and evaluate moral dialogue systems.
Tencent AVS: A Holistic Ads Video Dataset for Multi-modal Scene Segmentation
Therefore, TAVS is distinguished from previous temporal segmentation datasets due to its multi-modal information, holistic view of categories, and hierarchical granularities.
Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning
Cross-modal alignment is essential for vision-language pre-training (VLP) models to learn the correct corresponding information across different modalities.
Ranked #8 on
Zero-Shot Video Retrieval
on LSMDC
PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples
In addition, existing attack approaches towards point cloud classifiers cannot be applied to the completion models due to different output forms and attack purposes.
Curriculum-based Asymmetric Multi-task Reinforcement Learning
To mitigate the negative influence of customizing the one-off training order in curriculum-based AMTL, CAMRL switches its training mode between parallel single-task RL and asymmetric multi-task RL (MTRL), according to an indicator regarding the training time, the overall performance, and the performance gap among tasks.
A Survey of Deep Face Restoration: Denoise, Super-Resolution, Deblur, Artifact Removal
Second, we discuss the challenges of face restoration.
Model Compression for DNN-based Speaker Verification Using Weight Quantization
Experimental results on VoxCeleb show that weight quantization is effective for compressing SV models.
A Bibliometric Analysis and Review on Reinforcement Learning for Transportation Applications
Transportation is the backbone of the economy and urban development.
Online LiDAR-Camera Extrinsic Parameters Self-checking
This calibration task is multi-modal, where the rich color and texture information captured by the camera and the accurate three-dimensional spatial information from the LiDAR is incredibly significant for downstream tasks.
Neural Extended Kalman Filters for Learning and Predicting Dynamics of Structural Systems
Typically, conventional variational inference models are parameterized by neural networks independent of the latent dynamics models.
FR: Folded Rationalization with a Unified Encoder
Conventional works generally employ a two-phase model in which a generator selects the most important pieces, followed by a predictor that makes predictions based on the selected pieces.
Towards In-distribution Compatibility in Out-of-distribution Detection
Various training criteria for these auxiliary outliers are proposed based on heuristic intuitions.
Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task
However, CL on VQA involves not only the expansion of label sets (new Answer sets).
SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization
Matching-based methods, especially those based on space-time memory, are significantly ahead of other solutions in semi-supervised video object segmentation (VOS).
Semantic Segmentation
Semi-Supervised Video Object Segmentation
+1
DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection
We further propose a parallel design that integrates the convolutional network with a powerful self-attention mechanism to provide complementary clues between the attention path and convolutional path.
CircuitNet: An Open-Source Dataset for Machine Learning Applications in Electronic Design Automation (EDA)
The electronic design automation (EDA) community has been actively exploring machine learning (ML) for very large-scale integrated computer-aided design (VLSI CAD).
Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips
The security of deep neural networks (DNNs) has attracted increasing attention due to their widespread use in various applications.
NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation
To this end, we propose a novel NoIsy label CorrEction and Sample Training strategy for SGG: NICEST.
Towards Efficient Adversarial Training on Vision Transformers
Vision Transformer (ViT), as a powerful alternative to Convolutional Neural Network (CNN), has received much attention.
Neural modal ordinary differential equations: Integrating physics-based modeling with neural ordinary differential equations for modeling high-dimensional monitored structures
In the scope of physics-informed machine learning, this paper proposes a framework -- termed Neural Modal ODEs -- to integrate physics-based modeling with deep learning for modeling the dynamics of monitored and high-dimensional engineered systems.
Boosting Multi-Modal E-commerce Attribute Value Extraction via Unified Learning Scheme and Dynamic Range Minimization
2) Secondly, a text-guided information range minimization method is proposed to adaptively encode descriptive parts of each modality into an identical space with a powerful pretrained linguistic model.
Egocentric Video-Language Pretraining @ EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022
In this report, we propose a video-language pretraining (VLP) based solution \cite{kevin2022egovlp} for the EPIC-KITCHENS-100 Multi-Instance Retrieval (MIR) challenge.
Egocentric Video-Language Pretraining @ Ego4D Challenge 2022
In this report, we propose a video-language pretraining (VLP) based solution \cite{kevin2022egovlp} for four Ego4D challenge tasks, including Natural Language Query (NLQ), Moment Query (MQ), Object State Change Classification (OSCC), and PNR Localization (PNR).
Hybridization of evolutionary algorithm and deep reinforcement learning for multi-objective orienteering optimization
Multi-objective orienteering problems (MO-OPs) are classical multi-objective routing problems and have received a lot of attention in the past decades.
Towards Generalizable Person Re-identification with a Bi-stream Generative Model
Guided by original pedestrian images, one stream is employed to learn a camera-invariant global feature for the CC problem via filtering cross-camera interference factors.
Domain Generalization
Generalizable Person Re-identification
EDITnet: A Lightweight Network for Unsupervised Domain Adaptation in Speaker Verification
This paper proposes a domain transfer network, named EDITnet, to alleviate the language-mismatch problem on speaker embeddings without requiring speaker labels.
Unsupervised Knowledge Adaptation for Passenger Demand Forecasting
These multimodal forecasting models can improve accuracy but be less practical when different parts of multimodal datasets are owned by different institutions who cannot directly share data among them.
Egocentric Video-Language Pretraining
Video-Language Pretraining (VLP), which aims to learn transferable representation to advance a wide range of video-text downstream tasks, has recently received increasing attention.
Efficient-Adam: Communication-Efficient Distributed Adam
Distributed adaptive stochastic gradient methods have been widely used for large-scale nonconvex optimization, such as training deep learning models.
An Investigation on Applying Acoustic Feature Conversion to ASR of Adult and Child Speech
The performance of child speech recognition is generally less satisfactory compared to adult speech due to limited amount of training data.
Demand Response Method Considering Multiple Types of Flexible Loads in Industrial Parks
With the rapid development of the energy internet, the proportion of flexible loads in smart grid is getting much higher than before.
An Inexact Augmented Lagrangian Algorithm for Training Leaky ReLU Neural Network with Group Sparsity
Moreover, we show the relationship between the new model and the original problem.
Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs
Recent research found it beneficial to use large state spaces for HMMs and PCFGs.
Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning
They base the visual grounding on the features from pre-generated proposals or anchors, and fuse these features with the text embeddings to locate the target mentioned by the text.
Deep Reinforcement Learning for Orienteering Problems Based on Decomposition
A dynamic pointer network (DYPN) is introduced as the TSP solver, which takes city locations as inputs and immediately outputs a permutation of nodes.
ChildPredictor: A Child Face Prediction Framework with Disentangled Learning
On this basis, we formulate predictions as a mapping from parents' genetic factors to children's genetic factors, and disentangle them from external and variety factors.
Age-Invariant Face Recognition
Image-to-Image Translation
+2
XMP-Font: Self-Supervised Cross-Modality Pre-training for Few-Shot Font Generation
The cross-modality encoder is pre-trained in a self-supervised manner to allow effective capture of cross- and intra-modality correlations, which facilitates the content-style disentanglement and modeling style representations of all scales (stroke-level, component-level and character-level).
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations
With multi-level representations for video and text, hierarchical contrastive learning is designed to explore fine-grained cross-modal relationships, i. e., frame-word, clip-phrase, and video-sentence, which enables HCMI to achieve a comprehensive semantic comparison between video and text modalities.
Ranked #1 on
Video Retrieval
on MSR-VTT-1kA
(using extra training data)
Improving Vision Transformers by Revisiting High-frequency Components
Inspired by this finding, we first investigate the effects of existing techniques for improving ViT models from a new frequency perspective, and find that the success of some techniques (e. g., RandAugment) can be attributed to the better usage of the high-frequency components.
Ranked #2 on
Domain Generalization
on Stylized-ImageNet
Masked Autoencoders for Point Cloud Self-supervised Learning
Then, a standard Transformer based autoencoder, with an asymmetric design and a shifting mask tokens operation, learns high-level latent features from unmasked point patches, aiming to reconstruct the masked point patches.
Ranked #2 on
Point Cloud Segmentation
on PointCloud-C
3D Part Segmentation
Few-Shot 3D Point Cloud Classification
+2
CROON: Automatic Multi-LiDAR Calibration and Refinement Method in Road Scene
Sensor-based environmental perception is a crucial part of the autonomous driving system.
CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP
Once trained, the transformer can generate coherent image tokens based on the text embedding extracted from the text encoder of CLIP upon an input text.
Unpaired Quad-Path Cycle Consistent Adversarial Networks for Single Image Defogging
To address these issues, we develop a novel generative adversarial network, called quad-path cycle consistent adversarial network (QPC-Net), for single image defogging.
Deep Single Image Deraining using An Asymetric Cycle Generative and Adversarial Framework
The former consists of parallel rain removal path and rain-fog feature extraction path by the rain and derain-fog network and the attention rain-fog feature extraction network (ARFE) , while the latter only contains a synthetic rain transformation path.
Exploring Structural Sparsity in Neural Image Compression
Neural image compression have reached or out-performed traditional methods (such as JPEG, BPG, WebP).
Constrained Variational Policy Optimization for Safe Reinforcement Learning
Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications.
DynaMixer: A Vision MLP Architecture with Dynamic Mixing
In contrast with vision transformers and CNNs, the success of MLP-like models shows that simple information fusion operations among tokens and channels can yield a good representation power for deep recognition models.
DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations
AI-aided drug discovery (AIDD) is gaining increasing popularity due to its promise of making the search for new pharmaceuticals quicker, cheaper and more efficient.
Spatio-Temporal Graph Representation Learning for Fraudster Group Detection
Then we use an RNN on the spatial relations to predict the spatio-temporal relations of reviewers in the group.
Coherent Point Drift Revisited for Non-Rigid Shape Matching and Registration
In this paper, we explore a new type of extrinsic method to directly align two geometric shapes with point-to-point correspondences in ambient space by recovering a deformation, which allows more continuous and smooth maps to be obtained.
RFNet: Unsupervised Network for Mutually Reinforcing Multi-Modal Image Registration and Fusion
Specifically, for image registration, we solve the bottlenecks of defining registration metrics applicable for multi-modal images and facilitating the network convergence.
DGL-GAN: Discriminator Guided Learning for GAN Compression
Moreover, DGL-GAN is also effective in boosting the performance of original uncompressed GANs.
Triangle Attack: A Query-efficient Decision-based Adversarial Attack
Decision-based attack poses a severe threat to real-world applications since it regards the target model as a black box and only accesses the hard prediction label.
CO2Sum:Contrastive Learning for Factual-Consistent Abstractive Summarization
We propose CO2Sum (Contrastive for Consistency), a contrastive learning scheme that can be easily applied on sequence-to-sequence models for factual-consistent abstractive summarization, proving that the model can be fact-aware without modifying the architecture.
Generalized and Discriminative Few-Shot Object Detection via SVD-Dictionary Enhancement
To alleviate the impact of few samples, enhancing the generalization and discrimination abilities of detectors on new objects plays an important role.
MC-Blur: A Comprehensive Benchmark for Image Deblurring
Blur artifacts can seriously degrade the visual quality of images, and numerous deblurring methods have been proposed for specific scenarios.
Neural Routing by Memory
However, they use the same procedure sequence for all inputs, regardless of the intermediate features. This paper proffers a simple yet effective idea of constructing parallel procedures and assigning similar intermediate features to the same specialized procedures in a divide-and-conquer fashion.
PlantStereo: A Stereo Matching Benchmark for Plant Surface Dense Reconstruction
In this paper, we aim to address the issue between datasets and models and propose a large scale stereo dataset with high accuracy disparity ground truth named PlantStereo.
Social Fraud Detection Review: Methods, Challenges and Analysis
Many studies proposed approaches based on user behaviors and review text to address the challenges of fraud detection.
SpineOne: A One-Stage Detection Framework for Degenerative Discs and Vertebrae
Spinal degeneration plagues many elders, office workers, and even the younger generations.
Meter-Range Wireless Motor Drive for Pipeline Transportation
This paper proposes and implements a meter-range wireless motor drive (WMD) system for promising applications of underground pipeline transportations or in-pipe robots.
Physics-guided Deep Markov Models for Learning Nonlinear Dynamical Systems with Uncertainty
To address this, we bridge physics-based state space models with Deep Markov Models, thus delivering a hybrid modeling framework for unsupervised learning and identification of nonlinear dynamical systems.
Rethinking the Spatial Route Prior in Vision-and-Language Navigation
In a most information-rich case of knowing environment maps and admitting shortest-path prior, we observe that given an origin-destination node pair, the internal route can be uniquely determined.
A Simplified System Model for Optical Camera Communication
Data rate and communication distance are two important criteria for measuring the performance of optical camera communication (OCC) systems.
EDFace-Celeb-1M: Benchmarking Face Hallucination with a Million-scale Dataset
It is thus unclear how these algorithms perform on public face hallucination datasets.
Ranked #1 on
Image Super-Resolution
on WLFW
Exploiting Pre-Trained ASR Models for Alzheimer's Disease Recognition Through Spontaneous Speech
Input to these classifiers are speech transcripts produced by automatic speech recognition (ASR) models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing
To address these limitations, we design a Dynamic Style Manipulation Network (DyStyle) whose structure and parameters vary by input samples, to perform nonlinear and adaptive manipulation of latent codes for flexible and precise attribute control.
Utterance-level neural confidence measure for end-to-end children speech recognition
The investigation is focused on evaluating and comparing the efficacies of predictor features that are derived from different internal and external modules of the E2E system.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Semantic-Preserving Adversarial Text Attacks
In this paper, we propose a Bigram and Unigram based adaptive Semantic Preservation Optimization (BU-SPO) method to examine the vulnerability of deep models.
End2End Occluded Face Recognition by Masking Corrupted Features
However, the state-of-the-art general face recognition models do not generalize well to occluded face images, which are exactly the common cases in real-world scenarios.
SynFace: Face Recognition with Synthetic Data
We then analyze the underlying causes behind the performance gap, e. g., the poor intra-class variations and the domain gap between synthetic and real face images.
Structure-Aware Feature Generation for Zero-Shot Learning
In this paper, we introduce a novel structure-aware feature generation scheme, termed as SA-GAN, to explicitly account for the topological structure in learning both the latent space and the generative networks.
CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention
On the one hand, CEL blends each embedding with multiple patches of different scales, providing the self-attention module itself with cross-scale features.
Ranked #42 on
Semantic Segmentation
on ADE20K val
Decentralized Federated Learning: Balancing Communication and Computing Costs
The performance of decentralized SGD is jointly influenced by inter-node communications and local updates.
A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing
The effectiveness and superior performance of our approach are validated through comprehensive experiments in a range of applications.
Controlled Caption Generation for Images Through Adversarial Attacks
In contrast, we propose a GAN-based algorithm for crafting adversarial examples for neural image captioning that mimics the internal representation of the CNN such that the resulting deep features of the input image enable a controlled incorrect caption generation through the recurrent network.
ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
We trained the model with 10 billion parameters on a 4TB corpus consisting of plain texts and a large-scale knowledge graph.
Stock Market Analysis with Text Data: A Review
Then, we cover the analysis techniques and create a taxonomy of the main stock market forecast models.
