Search Results for author:
Found 272 papers, 96 papers with code
Nebula-I: A General Framework for Collaboratively Training Deep Learning Models on Low-Bandwidth Cloud Clusters
We took natural language processing (NLP) as an example to show how Nebula-I works in different training phases that include: a) pre-training a multilingual language model using two remote clusters; and b) fine-tuning a machine translation model using knowledge distilled from pre-trained models, which run through the most popular paradigm of recent deep learning.
Cross-Lingual Natural Language Inference
Distributed Computing
+2
InternLM2 Technical Report
The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI).
Ranked #5 on
Long-Context Understanding
on Ada-LEval (BestAnswer)
InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition
We propose InternLM-XComposer, a vision-language large model that enables advanced image-text comprehension and composition.
Ranked #9 on
Visual Question Answering (VQA)
on InfiMM-Eval
InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model
We introduce InternLM-XComposer2, a cutting-edge vision-language model excelling in free-form text-image composition and comprehension.
Ranked #16 on
Visual Question Answering
on MM-Vet
InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD
The Large Vision-Language Model (LVLM) field has seen significant advancements, yet its progression has been hindered by challenges in comprehending fine-grained visual content due to limited resolution.
Ranked #11 on
Visual Question Answering
on MM-Vet
Accelerating linear solvers for Stokes problems with C++ metaprogramming
The efficiency is demonstrated with the example of accelerating an iterative solver of a discontinuous Galerkin finite element method for the Stokes problem.
Mathematical Software Distributed, Parallel, and Cluster Computing Data Structures and Algorithms Fluid Dynamics 35-04, 65-04, 65Y05, 65Y10, 65Y15, 97N80
WanJuan: A Comprehensive Multimodal Dataset for Advancing English and Chinese Large Models
The rise in popularity of ChatGPT and GPT-4 has significantly accelerated the development of large models, leading to the creation of numerous impressive large language models(LLMs) and multimodal large language models (MLLMs).
SBERT-WK: A Sentence Embedding Method by Dissecting BERT-based Word Models
Yet, it is an open problem to generate a high quality sentence representation from BERT-based word models.
Graph Structured Network for Image-Text Matching
The GSMN explicitly models object, relation and attribute as a structured phrase, which not only allows to learn correspondence of object, relation and attribute separately, but also benefits to learn fine-grained correspondence of structured phrase.
Ranked #16 on
Cross-Modal Retrieval
on Flickr30k
OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation
Based on the observation, OPERA introduces a penalty term on the model logits during the beam-search decoding to mitigate the over-trust issue, along with a rollback strategy that retrospects the presence of summary tokens in the previously generated tokens, and re-allocate the token selection if necessary.
Joint Extraction of Entities and Relations Based on a Novel Decomposition Strategy
Joint extraction of entities and relations aims to detect entity pairs along with their relations using a single model.
Ranked #1 on
Relation Extraction
on NYT-single
Performance-aware Approximation of Global Channel Pruning for Multitask CNNs
Global channel pruning (GCP) aims to remove a subset of channels (filters) across different layers from a deep model without hurting the performance.
Deep Uncertainty Quantification: A Machine Learning Approach for Weather Forecasting
We cast the weather forecasting problem as an end-to-end deep learning problem and solve it by proposing a novel negative log-likelihood error (NLE) loss function.
MeshODE: A Robust and Scalable Framework for Mesh Deformation
Given a pair of shapes, our framework provides a novel shape feature-preserving mapping function that continuously deforms one model to the other by minimizing fitting and rigidity losses based on the non-rigid iterative-closest-point (ICP) algorithm.
Graphics Computational Geometry
Bipartite Graph Embedding via Mutual Information Maximization
However, the global properties of bipartite graph, including community structures of homogeneous nodes and long-range dependencies of heterogeneous nodes, are not well preserved.
Few-Shot Physically-Aware Articulated Mesh Generation via Hierarchical Deformation
By observing an articulated object dataset containing only a few examples, we wish to learn a model that can generate diverse meshes with high visual fidelity and physical validity.
VIGC: Visual Instruction Generation and Correction
A practical solution to this problem would be to utilize the available multimodal large language models (MLLMs) to generate instruction data for vision-language tasks.
C3KG: A Chinese Commonsense Conversation Knowledge Graph
Existing commonsense knowledge bases often organize tuples in an isolated manner, which is deficient for commonsense conversational models to plan the next steps.
C^3KG: A Chinese Commonsense Conversation Knowledge Graph
Existing commonsense knowledge bases often organize tuples in an isolated manner, which is deficient for commonsense conversational models to plan the next steps.
Improving Knowledge Graph Embedding Using Simple Constraints
We examine non-negativity constraints on entity representations and approximate entailment constraints on relation representations.
SEG-MAT: 3D Shape Segmentation Using Medial Axis Transform
Segmenting arbitrary 3D objects into constituent parts that are structurally meaningful is a fundamental problem encountered in a wide range of computer graphics applications.
Parrot Captions Teach CLIP to Spot Text
Despite CLIP being the foundation model in numerous vision-language applications, the CLIP suffers from a severe text spotting bias.
Overcoming Language Priors with Self-supervised Learning for Visual Question Answering
Our method can compensate for the data biases by generating balanced data without introducing external annotations.
Curriculum-style Local-to-global Adaptation for Cross-domain Remote Sensing Image Segmentation
Although domain adaptation has been extensively studied in natural image-based segmentation task, the research on cross-domain segmentation for very high resolution (VHR) remote sensing images (RSIs) still remains underexplored.
Knowledge Graph Embedding with Iterative Guidance from Soft Rules
In this paper, we propose Rule-Guided Embedding (RUGE), a novel paradigm of KG embedding with iterative guidance from soft rules.
Ranked #2 on
Link Prediction
on YAGO37
Neural Collective Entity Linking Based on Recurrent Random Walk Network Learning
However, most neural collective EL methods depend entirely upon neural networks to automatically model the semantic dependencies between different EL decisions, which lack of the guidance from external knowledge.
Graph Geometry Interaction Learning
To utilize the strength of both Euclidean and hyperbolic geometries, we develop a novel Geometry Interaction Learning (GIL) method for graphs, a well-suited and efficient alternative for learning abundant geometric properties in graph.
Unsupervised Co-part Segmentation through Assembly
Co-part segmentation is an important problem in computer vision for its rich applications.
Attention-based sequence-to-sequence model for speech recognition: development of state-of-the-art system on LibriSpeech and its application to non-native English
Recent research has shown that attention-based sequence-to-sequence models such as Listen, Attend, and Spell (LAS) yield comparable results to state-of-the-art ASR systems on various tasks.
Just Rank: Rethinking Evaluation with Word and Sentence Similarities
Word and sentence similarity tasks have become the de facto evaluation method.
GazeSAM: What You See is What You Segment
This study investigates the potential of eye-tracking technology and the Segment Anything Model (SAM) to design a collaborative human-computer interaction system that automates medical image segmentation.
Self-supervised Video Representation Learning by Context and Motion Decoupling
A key challenge in self-supervised video representation learning is how to effectively capture motion information besides context bias.
MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversation
Applying existing methods to emotional support conversation -- which provides valuable assistance to people who are in need -- has two major limitations: (a) they generally employ a conversation-level emotion label, which is too coarse-grained to capture user's instant mental state; (b) most of them focus on expressing empathy in the response(s) rather than gradually reducing user's distress.
Heterogeneous Graph Attention Networks for Early Detection of Rumors on Twitter
A meta-path based heterogeneous graph attention network framework is proposed to capture the global semantic relations of text contents, together with the global structure information of source tweet propagations for rumor detection.
Task-adaptive Neural Process for User Cold-Start Recommendation
In this paper, we develop a novel meta-learning recommender called task-adaptive neural process (TaNP).
Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
Multimodal large language models have made significant advancements in recent years, yet they still suffer from a common issue known as the "hallucination problem", in which the models generate textual descriptions that inaccurately depict or entirely fabricate content from associated images.
Domain Generalization with Adversarial Intensity Attack for Medical Image Segmentation
In real-world scenarios, however, it is common for models to encounter data from new and different domains to which they were not exposed to during training.
Few-Shot Event Detection with Prototypical Amortized Conditional Random Field
Event detection tends to struggle when it needs to recognize novel event types with a few samples.
Cross-Domain Recommendation to Cold-Start Users via Variational Information Bottleneck
As a promising way, Cross-Domain Recommendation (CDR) has attracted a surge of interest, which aims to transfer the user preferences observed in the source domain to make recommendations in the target domain.
Coarse-to-Fine Pre-training for Named Entity Recognition
More recently, Named Entity Recognition hasachieved great advances aided by pre-trainingapproaches such as BERT.
Contrastive Cross-Domain Sequential Recommendation
Cross-Domain Sequential Recommendation (CDSR) aims to predict future interactions based on user's historical sequential interactions from multiple domains.
Reconstructed Convolution Module Based Look-Up Tables for Efficient Image Super-Resolution
To enlarge RF with contained LUT sizes, we propose a novel Reconstructed Convolution(RC) module, which decouples channel-wise and spatial calculation.
EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation
In this paper, we consider the problem of reference-based video super-resolution(RefVSR), i. e., how to utilize a high-resolution (HR) reference frame to super-resolve a low-resolution (LR) video sequence.
Reference-based Video Super-Resolution
Video Super-Resolution
Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework
Most sentence embedding techniques heavily rely on expensive human-annotated sentence pairs as the supervised signals.
MLLM-DataEngine: An Iterative Refinement Approach for MLLM
Despite the great advance of Multimodal Large Language Models (MLLMs) in both instruction dataset building and benchmarking, the independence of training and evaluation makes current MLLMs hard to further improve their capability under the guidance of evaluation results with a relatively low human cost.
Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning
This paper addresses such a challenge by Decomposed Mutual INformation Optimization (DOMINO) for context learning, which explicitly learns a disentangled context to maximize the mutual information between the context and historical trajectories, while minimizing the state transition prediction error.
Inductive Unsupervised Domain Adaptation for Few-Shot Classification via Clustering
We first build a representation extractor to derive features for unlabeled data from the target domain (no test data is necessary) and then group them with a cluster miner.
Exploring Better Text Image Translation with Multimodal Codebook
Text image translation (TIT) aims to translate the source texts embedded in the image to target translations, which has a wide range of applications and thus has important research value.
GraphHop: An Enhanced Label Propagation Method for Node Classification
In Step 2, a new label vector is predicted for each node based on the label of the node itself and the aggregated label information obtained in Step 1.
Efficient Sentence Embedding via Semantic Subspace Analysis
Given the fact that word embeddings can capture semantic relationship while semantically similar words tend to form semantic groups in a high-dimensional embedding space, we develop a sentence representation scheme by analyzing semantic subspaces of its constituent words.
Ranking Cost: Building An Efficient and Scalable Circuit Routing Planner with Evolution-Based Optimization
In this work, we propose a new algorithm for circuit routing, named Ranking Cost, which innovatively combines search-based methods (i. e., A* algorithm) and learning-based methods (i. e., Evolution Strategies) to form an efficient and trainable router.
Inductive Learning on Commonsense Knowledge Graph Completion
Here, we propose to study the inductive learning setting for CKG completion where unseen entities may present at test time.
AnomalyHop: An SSL-based Image Anomaly Localization Method
An image anomaly localization method based on the successive subspace learning (SSL) framework, called AnomalyHop, is proposed in this work.
SynWMD: Syntax-aware Word Mover's Distance for Sentence Similarity Evaluation
It also outperforms other WMD-based methods on sentence classification tasks.
Analyzing and Evaluating Faithfulness in Dialogue Summarization
The factual correctness of summaries has the highest priority before practical applications.
GreenKGC: A Lightweight Knowledge Graph Completion Method
Knowledge graph completion (KGC) aims to discover missing relationships between entities in knowledge graphs (KGs).
Ranked #21 on
Link Prediction
on FB15k-237
Relation-Guided Few-Shot Relational Triple Extraction
To instantiate this strategy, we further propose a model, RelATE, which builds a dual-level attention to aggregate relationrelevant information to detect the relation occurrence and utilizes the annotated samples of the detected relations to extract the corresponding head/tail entities.
Relational Sentence Embedding for Flexible Semantic Matching
We present Relational Sentence Embedding (RSE), a new paradigm to further discover the potential of sentence embeddings.
GazeGNN: A Gaze-Guided Graph Neural Network for Chest X-ray Classification
To our best knowledge, GazeGNN is the first work that adopts GNN to integrate image and eye-gaze data.
SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning
We present SeaEval, a benchmark for multilingual foundation models.
CrossIn: An Efficient Instruction Tuning Approach for Cross-Lingual Knowledge Alignment
This performance discrepancy mainly stems from the imbalanced distribution of training data across languages during pre-training and instruction tuning stages.
Joint Distribution Alignment via Adversarial Learning for Domain Adaptive Object Detection
Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data.
Improving Aspect Term Extraction with Bidirectional Dependency Tree Representation
The key idea is to explicitly incorporate both representations gained separately from the bottom-up and top-down propagation on the given dependency syntactic tree.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
Evolving Deep Neural Networks by Multi-objective Particle Swarm Optimization for Image Classification
In recent years, convolutional neural networks (CNNs) have become deeper in order to achieve better classification accuracy in image classification.
Beyond Word Attention: Using Segment Attention in Neural Relation Extraction
Relation extraction studies the issue of predicting semantic relations between pairs of entities in sentences.
Ranked #29 on
Relation Extraction
on TACRED
Learning Hierarchical Dynamics with Spatial Adjacency for Image Enhancement
In various real-world image enhancement applications, the degradations are always non-uniform or non-homogeneous and diverse, which challenges most deep networks with fixed parameters during the inference phase.
Ranked #14 on
Image Dehazing
on SOTS Indoor
Post-Processing of Word Representations via Variance Normalization and Dynamic Embedding
Although embedded vector representations of words offer impressive performance on many natural language processing (NLP) applications, the information of ordered input sequences is lost to some extent if only context-based samples are used in the training.
PG$^2$Net: Personalized and Group Preferences Guided Network for Next Place Prediction
Targeting this, we propose an end-to-end framework named personalized and group preference guided network (PG$^2$Net), considering the users' preferences to various places at both individual and collective levels.
Improved training of neural trans-dimensional random field language models with dynamic noise-contrastive estimation
First, a dynamic noise distribution is introduced and trained simultaneously to converge to the data distribution.
Graph Representation Learning: A Survey
Research on graph representation learning has received a lot of attention in recent years since many data in real-world applications come in form of graphs.
Infusing Sequential Information into Conditional Masked Translation Model with Self-Review Mechanism
Concretely, we insert a left-to-right mask to the same decoder of CMTM, and then induce it to autoregressively review whether each generated word from CMTM is supposed to be replaced or kept.
Towards Robust Neural Machine Translation with Iterative Scheduled Data-Switch Training
Most existing methods on robust neural machine translation (NMT) construct adversarial examples by injecting noise into authentic examples and indiscriminately exploit two types of examples.
Rethinking the Reasonability of the Test Set for Simultaneous Machine Translation
Simultaneous machine translation (SimulMT) models start translation before the end of the source sentence, making the translation monotonically aligned with the source sentence.
Instructive Dialogue Summarization with Query Aggregations
With the advancement of instruction-finetuned language models, we introduce instruction-tuning to dialogues to expand the capability set of dialogue summarization models.
Ranked #1 on
Text Summarization
on DialogSum
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.
Distribution-Aware Data Expansion with Diffusion Models
In this paper, we propose DistDiff, an effective data expansion framework based on the distribution-aware diffusion model.
Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension
Hence, in this paper, we propose to improve the response generation performance by examining the model's ability to answer a reading comprehension question, where the question is focused on the omitted information in the dialog.
Learning Modified Indicator Functions for Surface Reconstruction
We design a novel deep neural network to perform surface integral and learn the modified indicator functions from un-oriented and noisy point clouds.
Structure-Unified M-Tree Coding Solver for MathWord Problem
As one of the challenging NLP tasks, designing math word problem (MWP) solvers has attracted increasing research attention for the past few years.
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.
CN-RMA: Combined Network with Ray Marching Aggregation for 3D Indoors Object Detection from Multi-view Images
This paper introduces CN-RMA, a novel approach for 3D indoor object detection from multi-view images.
TEAM: We Need More Powerful Adversarial Examples for DNNs
In this paper, we propose a novel method (TEAM, Taylor Expansion-Based Adversarial Methods) to generate more powerful adversarial examples than previous methods.
Focus-Constrained Attention Mechanism for CVAE-based Response Generation
To model diverse responses for a given post, one promising way is to introduce a latent variable into Seq2Seq models.
Exploring the Interactive Guidance for Unified and Effective Image Matting
Although avoiding the extensive labors of trimap annotation, existing methods still suffer from two limitations: (1) For the single image with multiple objects, it is essential to provide extra interaction information to help determining the matting target; (2) For transparent objects, the accurate regression of alpha matte from RGB image is much more difficult compared with the opaque ones.
A Focused Study on Sequence Length for Dialogue Summarization
Output length is critical to dialogue summarization systems.
Point normal orientation and surface reconstruction by incorporating isovalue constraints to Poisson equation
In this work, we bridge orientation and reconstruction in the implicit space and propose a novel approach to orient point cloud normals by incorporating isovalue constraints to the Poisson equation.
Transformer based Generative Adversarial Network for Liver Segmentation
The premise behind this choice is that the self-attention mechanism of the Transformers allows the network to aggregate the high dimensional feature and provide global information modeling.
Dilation-Erosion for Single-Frame Supervised Temporal Action Localization
To balance the annotation labor and the granularity of supervision, single-frame annotation has been introduced in temporal action localization.
Knowledge Graph Embedding with 3D Compound Geometric Transformations
The cascade of 2D geometric transformations were exploited to model relations between entities in a knowledge graph (KG), leading to an effective KG embedding (KGE) model, CompoundE.
Ranked #7 on
Link Property Prediction
on ogbl-wikikg2
Deep Structural Point Process for Learning Temporal Interaction Networks
A temporal interaction network consists of a series of chronological interactions between users and items.
Geometry Contrastive Learning on Heterogeneous Graphs
Self-supervised learning (especially contrastive learning) methods on heterogeneous graphs can effectively get rid of the dependence on supervisory data.
Robust Network Architecture Search via Feature Distortion Restraining
This process is modeled as a multi-objective bilevel optimization problem and a novel algorithm is proposed to solve this optimization.
Domain Generalization with Correlated Style Uncertainty
In this regard, style augmentation is a strong DG method taking advantage of instance-specific feature statistics containing informative style characteristics to synthetic novel domains.
WiTUnet: A U-Shaped Architecture Integrating CNN and Transformer for Improved Feature Alignment and Local Information Fusion
Low-dose computed tomography (LDCT) has become the technology of choice for diagnostic medical imaging, given its lower radiation dose compared to standard CT, despite increasing image noise and potentially affecting diagnostic accuracy.
UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition
This paper presents the UniMER dataset to provide the first study on Mathematical Expression Recognition (MER) towards complex real-world scenarios.
Evolving Deep Convolutional Neural Networks by Variable-length Particle Swarm Optimization for Image Classification
Convolutional neural networks (CNNs) are one of the most effective deep learning methods to solve image classification problems, but the best architecture of a CNN to solve a specific problem can be extremely complicated and hard to design.
Electric Vehicle Driver Clustering using Statistical Model and Machine Learning
Electric Vehicle (EV) is playing a significant role in the distribution energy management systems since the power consumption level of the EVs is much higher than the other regular home appliances.
Learning neural trans-dimensional random field language models with noise-contrastive estimation
However, the training efficiency of neural TRF LMs is not satisfactory, which limits the scalability of TRF LMs on large training corpus.
Language modeling with Neural trans-dimensional random fields
The idea is to use nonlinear potentials with continuous features, implemented by neural networks (NNs), in the TRF framework.
Multi-stage Multi-recursive-input Fully Convolutional Networks for Neuronal Boundary Detection
This design is biologically-plausible, as it likes a human visual system to compare different possible segmentation solutions to address the ambiguous boundary issue.
Traffic-Aware Transmission Mode Selection in D2D-enabled Cellular Networks with Token System
We consider a D2D-enabled cellular network where user equipments (UEs) owned by rational users are incentivized to form D2D pairs using tokens.
Model Interpolation with Trans-dimensional Random Field Language Models for Speech Recognition
The dominant language models (LMs) such as n-gram and neural network (NN) models represent sentence probabilities in terms of conditionals.
Large Scale Purchase Prediction with Historical User Actions on B2C Online Retail Platform
This paper describes the solution of Bazinga Team for Tmall Recommendation Prize 2014.
Sequential Click Prediction for Sponsored Search with Recurrent Neural Networks
Click prediction is one of the fundamental problems in sponsored search.
Combination of Diverse Ranking Models for Personalized Expedia Hotel Searches
The ICDM Challenge 2013 is to apply machine learning to the problem of hotel ranking, aiming to maximize purchases according to given hotel characteristics, location attractiveness of hotels, user's aggregated purchase history and competitive online travel agency information for each potential hotel choice.
A Hybrid Differential Evolution Approach to Designing Deep Convolutional Neural Networks for Image Classification
In this paper, a new hybrid differential evolution (DE) algorithm with a newly added crossover operator is proposed to evolve the architectures of CNNs of any lengths, which is named DECNN.
Graph-based Deep-Tree Recursive Neural Network (DTRNN) for Text Classification
A novel graph-to-tree conversion mechanism called the deep-tree generation (DTG) algorithm is first proposed to predict text data represented by graphs.
Neural Material: Learning Elastic Constitutive Material and Damping Models from Sparse Data
The challenge is that such data is sparse as it is consistently given only on part of the surface.
Graphics
Multi-view Laplacian Eigenmaps Based on Bag-of-Neighbors For RGBD Human Emotion Recognition
As RGB view and depth view lie in different spaces, a new distance metric bag of neighbors (BON) used in MvLE can get the similar distributions of the two views.
Synthetic Dynamic PMU Data Generation: A Generative Adversarial Network Approach
This paper concerns with the production of synthetic phasor measurement unit (PMU) data for research and education purposes.
Relation Extraction with Multi-instance Multi-label Convolutional Neural Networks
In this paper, we propose a multi-instance multi-label convolutional neural network for distantly supervised RE.
Evaluating Word Embedding Models: Methods and Experimental Results
Extensive evaluation on a large number of word embedding models for language processing applications is conducted in this work.
Can Walking and Measuring Along Chord Bunches Better Describe Leaf Shapes?
A novel chord bunch walks (CBW) descriptor is developed through the chord walking that effectively integrates the shape image function over the walked chord to reflect the contour features and the inner properties of the shape.
Automatic Thumbnail Generation Based on Visual Representativeness and Foreground Recognizability
We present an automatic thumbnail generation technique based on two essential considerations: how well they visually represent the original photograph, and how well the foreground can be recognized after the cropping and downsizing steps of thumbnailing.
A Hybrid GA-PSO Method for Evolving Architecture and Short Connections of Deep Convolutional Neural Networks
Three major contributions of this work are: Firstly, a new encoding strategy is proposed to encode a CNN, where the architecture and the shortcut connections are encoded separately; Secondly, a hybrid two-level EC method, which combines particle swarm optimisation and genetic algorithms, is developed to search for the optimal CNNs; Lastly, an adjustable learning rate is introduced for the fitness evaluations, which provides a better learning rate for the training process given a fixed number of epochs.
Graph Attention Memory for Visual Navigation
To address the long-term memory issue, this paper proposes a graph attention memory (GAM) architecture consisting of memory construction module, graph attention module and control module.
Adaptive Convolution for Multi-Relational Learning
We consider the problem of learning distributed representations for entities and relations of multi-relational data so as to predict missing links therein.
Ranked #10 on
Link Prediction
on WN18
YNU NLP at SemEval-2019 Task 5: Attention and Capsule Ensemble for Identifying Hate Speech
We participate in both subtask A and subtask B for English.
YNUWB at SemEval-2019 Task 6: K-max pooling CNN with average meta-embedding for identifying offensive language
This paper describes the system submitted to SemEval 2019 Task 6: OffensEval 2019.
Efficiently Indexing Large Sparse Graphs for Similarity Search
Abstract—The graph structure is a very important means to model schemaless data with complicated structures, such as protein- protein interaction networks, chemical compounds, knowledge query inferring systems, and road networks.
Particle Swarm Optimisation for Evolving Deep Neural Networks for Image Classification by Evolving and Stacking Transferable Blocks
Deep Convolutional Neural Networks (CNNs) have been widely used in image classification tasks, but the process of designing CNN architectures is very complex, so Neural Architecture Search (NAS), automatically searching for optimal CNN architectures, has attracted more and more research interests.
On the Strong Equivalences of LPMLN Programs
Firstly, we present the notions of p-strong and w-strong equivalences between LPMLN programs.
On the Strong Equivalences for LPMLN Programs
In this paper, we study the strong equivalence for LPMLN programs, which is an important tool for program rewriting and theoretical investigations in the field of logic programming.
Logic in Computer Science D.1.6
From Species to Cultivar: Soybean Cultivar Recognition using Multiscale Sliding Chord Matching of Leaf Images
Encouraging experimental results of the proposed method in comparison to the state-of-the-art leaf species recognition methods demonstrate the availability of cultivar information in soybean leaves and effectiveness of the proposed MSCM for soybean cultivar identification, which may advance the research in leaf recognition from species to cultivar.
A game method for improving the interpretability of convolution neural network
The reason is, we believe that: the network is essentially a perceptual model.
YNU-junyi in BioNLP-OST 2019: Using CNN-LSTM Model with Embeddings for SeeDev Binary Event Extraction
We participated in the BioNLP 2019 Open Shared Tasks: binary relation extraction of SeeDev task.
Global Adaptive Generative Adjustment
Many traditional signal recovery approaches can behave well basing on the penalized likelihood.
Spot Evasion Attacks: Adversarial Examples for License Plate Recognition Systems with Convolutional Neural Networks
In this paper, we propose an evasion attack on CNN classifiers in the context of License Plate Recognition (LPR), which adds predetermined perturbations to specific regions of license plate images, simulating some sort of naturally formed spots (such as sludge, etc.).
Towards cross-platform automated rotation electron diffraction
A DigitalMicrograph script InsteaDMatic has been developed to facilitate rapid automated continuous rotation electron diffraction (cRED) data acquisition.
Materials Science
An Improved Coarse-to-Fine Method for Solving Generation Tasks
The methods first generate a rough sketch in the coarse stage and then use the sketch to get the final result in the fine stage.
TEAM: An Taylor Expansion-Based Method for Generating Adversarial Examples
Although Deep Neural Networks(DNNs) have achieved successful applications in many fields, they are vulnerable to adversarial examples. Adversarial training is one of the most effective methods to improve the robustness of DNNs, and it is generally considered as solving a saddle point problem that minimizes risk and maximizes perturbation. Therefore, powerful adversarial examples can effectively replicate the situation of perturbation maximization to solve the saddle point problem. The method proposed in this paper approximates the output of DNNs in the input neighborhood by using the Taylor expansion, and then optimizes it by using the Lagrange multiplier method to generate adversarial examples.
Feature-Driven Super-Resolution for Object Detection
Comparing with some state-of-the-art SR algorithms with 4$\times$ scale factor, FDSR outperforms the detection performance mAP on MS COCO validation, VOC2007 databases with good generalization to other detection networks.
Unified Multi-Criteria Chinese Word Segmentation with BERT
Besides, the pre-trained BERT language model has been also introduced into the MCCWS task in a multi-task learning framework.
Attention-based Transducer for Online Speech Recognition
We propose attention-based transducer with modification over RNN-T in two aspects.
Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Nets
Generative adversarial imitation learning (GAIL) has shown promising results by taking advantage of generative adversarial nets, especially in the field of robot learning.
Modeling Discourse Structure for Document-level Neural Machine Translation
Finally, we combine the discourse structure information with the word embedding before it is fed into the encoder.
Xiaomi's Submissions for IWSLT 2020 Open Domain Translation Task
This paper describes the Xiaomi{'}s submissions to the IWSLT20 shared open domain translation task for Chinese{\textless}-{\textgreater}Japanese language pair.
Surrogate-assisted Particle Swarm Optimisation for Evolving Variable-length Transferable Blocks for Image Classification
A new effective and efficient surrogate-assisted particle swarm optimisation algorithm is proposed to automatically evolve convolutional neural networks.
A Novel Line Integral Transform for 2D Affine-Invariant Shape Retrieval
While conducting the trace transform once only generates a single feature and multiple trace transforms of different functionals are needed to derive more to make the descriptors informative.
EI-MTD:Moving Target Defense for Edge Intelligence against Adversarial Attacks
This dynamic defense can prohibit the adversary from selecting an optimal substitute model for black-box attacks.
Constructing Multiple High-Quality Deep Neural Networks: A TRUST-TECH Based Approach
To realize effective TRUST-TECH searches to train deep neural networks on large datasets, a dynamic search paths (DSP) method is proposed to provide an improved search guidance in TRUST-TECH method.
Approximating Pareto Frontier through Bayesian-optimization-directed Robust Multi-objective Reinforcement Learning
Thirdly, the agent’s learning process is regarded as a black-box, and the comprehensive metric we proposed is computed after each episode of training, then a Bayesian optimization (BO) algorithm is adopted to guide the agent to evolve towards improving the quality of the approximated Pareto frontier.
Bayesian Optimization
Multi-Objective Reinforcement Learning
+1
An Adversarial Attack via Feature Contributive Regions
Recently, to deal with the vulnerability to generate examples of CNNs, there are many advanced algorithms that have been proposed.
Robust Memory Augmentation by Constrained Latent Imagination
The latent dynamics model summarizes an agent’s high dimensional experiences in a compact way.
Ranking Cost: One-Stage Circuit Routing by Directly Optimizing Global Objective Function
In our method, we introduce a new set of variables called cost maps, which can help the A* router to find out proper paths to achieve the global object.
A novel combination of theoretical analysis and data-driven method for reconstruction of structural defects
To address this issue, a novel approach to quantitative reconstruction of defects using the integration of data-driven method with the guided wave scattering analysis has been proposed in this paper.
Computational Engineering, Finance, and Science J.2
Pre-training with Meta Learning for Chinese Word Segmentation
Recent researches show that pre-trained models (PTMs) are beneficial to Chinese Word Segmentation (CWS).
Electric Vehicle Charging Infrastructure Planning: A Scalable Computational Framework
The optimal charging infrastructure planning problem over a large geospatial area is challenging due to the increasing network sizes of the transportation system and the electric grid.
Visually Imperceptible Adversarial Patch Attacks on Digital Images
With this soft mask, we develop a new loss function with inverse temperature to search for optimal perturbations in CFR.
Modeling Homophone Noise for Robust Neural Machine Translation
In this paper, we propose a robust neural machine translation (NMT) framework.
Horizon curvature and spacetime structure influences on black hole scalarization
Comparing with negative and zero cases, the scalar field near AdS black hole with positive curvature could be much easier to emerge.
General Relativity and Quantum Cosmology
Phase transitions in four-dimensional AdS black holes with a nonlinear electrodynamics source
In this work we consider black hole solutions to Einstein theory coupled to a nonlinear power-law electromagnetic field with a fixed exponent value.
General Relativity and Quantum Cosmology High Energy Physics - Theory
Black holes of $(2+1)$-dimensional $f(R)$ gravity coupled to a scalar field
We consider $f(R)$ gravity theories in the presence of a scalar field minimally coupled to gravity with a self-interacting potential in $(2+1)$-dimensions.
General Relativity and Quantum Cosmology
Towards Speeding up Adversarial Training in Latent Spaces
Adversarial training is wildly considered as one of the most effective way to defend against adversarial examples.
Polyphone Disambiguition in Mandarin Chinese with Semi-Supervised Learning
In this paper, we propose a novel semi-supervised learning (SSL) framework for Mandarin Chinese polyphone disambiguation that can potentially leverage unlimited unlabeled text data.
Train a One-Million-Way Instance Classifier for Unsupervised Visual Representation Learning
However, scaling up the classification task from thousands of semantic labels to millions of instance labels brings specific challenges including 1) the large-scale softmax computation; 2) the slow convergence due to the infrequent visiting of instance samples; and 3) the massive number of negative classes that can be noisy.
The collider tests of a leptophilic scalar for the anomalous magnetic moments
Our results show that the leptophilic scalar in the mass range of $\mathcal{O}(10)- \mathcal{O}(1000 )\,\rm GeV$ can be fully probed by the future experimental searches at the HL-LHC and the lepton colliders at their early stages.
High Energy Physics - Phenomenology
Progressive Depth Learning for Single Image Dehazing
However, we note that the guidance of the depth information for transmission estimation could remedy the decreased visibility as distances increase.
Studies of form factors and branching ratios for $D\rightarrow S,Al\bar{ν_{l}}$ with light-cone sum rules
We systematically study the semileptonic decay process of $ D\rightarrow S, A l\bar{\nu_{l}}(l=e,\mu)$ by light-cone sum rules (LCSR) with chiral currents, calculate the form factors containing only the contribution of the leading twist light-cone distribution amplitudes (LCDAs).
High Energy Physics - Phenomenology
Forecasts on Interacting Dark Energy from 21-cm Angular Power Spectrum with BINGO and SKA observations
Then we estimate the noise level of three upcoming HI intensity mapping surveys, BINGO, SKA1-MID Band$\,$1 and Band$\,$2, respectively, and employ a Fisher matrix approach to forecast their constraints on the IDE model.
Cosmology and Nongalactic Astrophysics General Relativity and Quantum Cosmology High Energy Physics - Phenomenology
BLOCKEYE: Hunting For DeFi Attacks on Blockchain
We applied BLOCKEYE in several popular DeFi projects and managed to discover potential security attacks that are unreported before.
Cryptography and Security Computers and Society
Progressive residual learning for single image dehazing
The recent physical model-free dehazing methods have achieved state-of-the-art performances.
Improve GAN-based Neural Vocoder using Pointwise Relativistic LeastSquare GAN
GAN-based neural vocoders, such as Parallel WaveGAN and MelGAN have attracted great interest due to their lightweight and parallel structures, enabling them to generate high fidelity waveform in a real-time manner.
Dynamic Texture Synthesis by Incorporating Long-range Spatial and Temporal Correlations
The main challenge of dynamic texture synthesis lies in how to maintain spatial and temporal consistency in synthesized videos.
Recent Advances on Sub-Nyquist Sampling-Based Wideband Spectrum Sensing
Cognitive radio (CR) is a promising technology enabling efficient utilization of the spectrum resource for future wireless systems.
Integrated Communication and Navigation for Ultra-Dense LEO Satellite Networks: Vision, Challenges and Solutions
Next generation beyond 5G networks are expected to provide both Terabits per second data rate communication services and centimeter-level accuracy localization services in an efficient, seamless and cost-effective manner.
An Efficient Network Solver for Dynamic Simulation of Power Systems Based on Hierarchical Inverse Computation and Modification
In power system dynamic simulation, up to 90% of the computational time is devoted to solve the network equations, i. e., a set of linear equations.
Towards an Online Empathetic Chatbot with Emotion Causes
Existing emotion-aware conversational models usually focus on controlling the response contents to align with a specific emotion class, whereas empathy is the ability to understand and concern the feelings and experience of others.
Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning
However, such a decoder only exploits the preorder traversal based preceding actions, which are insufficient to ensure correct action predictions.
Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment
In addition, we use a novel agent network named Population Invariant agent with Transformer (PIT) to realize the coordination transfer in more varieties of scenarios.
Lijunyi at SemEval-2020 Task 4: An ALBERT Model Based Maximum Ensemble with Different Training Sizes and Depths for Commonsense Validation and Explanation
This article describes the system submitted to SemEval 2020 Task 4: Commonsense Validation and Explanation.
Lee at SemEval-2020 Task 5: ALBERT Model Based on the Maximum Ensemble Strategy and Different Data Sampling Methods for Detecting Counterfactual Statements
Our methods achieved a F1 score of 0. 85 in subtask A.
Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Training
In current studies, we observe that class imbalance in SSOD severely impedes the effectiveness of self-training.
Multi-Scale Local-Temporal Similarity Fusion for Continuous Sign Language Recognition
Continuous sign language recognition (cSLR) is a public significant task that transcribes a sign language video into an ordered gloss sequence.
Risk Concentration and the Mean-Expected Shortfall Criterion
Recently, Wang and Zitikis (2021) put forward four economic axioms for portfolio risk assessment and provide the first economic axiomatic foundation for the family of ES.
Optimal Scheduling of Integrated Demand Response-Enabled Community Integrated Energy Systems in Uncertain Environments
The community integrated energy system (CIES) is an essential energy internet carrier that has recently been the focus of much attention.
Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification
The goal of few-shot fine-grained image classification is to recognize rarely seen fine-grained objects in the query set, given only a few samples of this class in the support set.
Densely Semantic Enhancement for Domain Adaptive Region-free Detectors
Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data.
Porous Lattice Transformer Encoder for Chinese NER
Incorporating lexicons into character-level Chinese NER by lattices is proven effective to exploitrich word boundary information.
Learning to Prune Dependency Trees with Rethinking for Neural Relation Extraction
Dependency trees have been shown to be effective in capturing long-range relations between target entities.
A Multi-stage Transfer Learning Framework for Diabetic Retinopathy Grading on Small Data
Diabetic retinopathy (DR) is one of the major blindness-causing diseases currently known.
Learning Explicit Credit Assignment for Multi-agent Joint Q-learning
In contrast, we formulate an \emph{explicit} credit assignment problem where each agent gives its suggestion about how to weight individual Q-values to explicitly maximize the joint Q-value, besides guaranteeing the Bellman optimality of the joint Q-value.
Task-Specific Dependency-based Word Embedding Methods
Two task-specific dependency-based word embedding methods are proposed for text classification in this work.
PEDENet: Image Anomaly Localization via Patch Embedding and Density Estimation
PEDENet contains a patch embedding (PE) network, a density estimation (DE) network, and an auxiliary network called the location prediction (LP) network.
Ranked #71 on
Anomaly Detection
on MVTec AD
Maximal Clique Based Non-Autoregressive Open Information Extraction
However, the popular OpenIE systems usually output facts sequentially in the way of predicting the next fact conditioned on the previous decoded ones, which enforce an unnecessary order on the facts and involve the error accumulation between autoregressive steps.
Model-Based Reinforcement Learning via Imagination with Derived Memory
Model-based reinforcement learning aims to improve the sample efficiency of policy learning by modeling the dynamics of the environment.
Model-based Reinforcement Learning
reinforcement-learning
+1
VECTORIZATION METHODS IN RECOMMENDER SYSTEM
The most used recommendation method is collaborative filtering, and the key part of collaborative filtering is to compute the similarity.
ScaleVLAD: Improving Multimodal Sentiment Analysis via Multi-Scale Fusion of Locally Descriptors
This paper proposes a fusion model named ScaleVLAD to gather multi-Scale representation from text, video, and audio with shared Vectors of Locally Aggregated Descriptors to improve unaligned multimodal sentiment analysis.
Hierarchical Stochastic Scheduling of Multi-Community Integrated Energy Systems in Uncertain Environments via Stackelberg Game
An operating entity utilizing community-integrated energy systems with a large number of small-scale distributed energy sources can easily trade with existing distribution markets.
SanMove: Next Location Recommendation via Self-Attention Network
To address the above challenges, we propose a novel method named SanMove, a self-attention network based model, to predict the next location via capturing the long- and short-term mobility patterns of users.
ViR:the Vision Reservoir
To address these problems, a novel method, namely, Vision Reservoir computing (ViR), is proposed here for image classification, as a parallel to ViT.
CORE: A Knowledge Graph Entity Type Prediction Method via Complex Space Regression and Embedding
A new KG entity type prediction method, named CORE (COmplex space Regression and Embedding), is proposed in this work.
KGBoost: A Classification-based Knowledge Base Completion Method with Negative Sampling
Knowledge base completion is formulated as a binary classification problem in this work, where an XGBoost binary classifier is trained for each relation using relevant links in knowledge graphs (KGs).
