Search Results for author:
Found 75 papers, 22 papers with code
A Transformer-based Threshold-Free Framework for Multi-Intent NLU
Furthermore, we propose a threshold-free intent multi-intent classifier that utilizes the output of IND task and detects the multiple intents without depending on the threshold.
Improving Non-Autoregressive Neural Machine Translation via Modeling Localness
Non-autoregressive translation (NAT) models, which eliminate the sequential dependencies within the target sentence, have achieved remarkable inference speed, but suffer from inferior translation quality.
MLP: Motion Label Prior for Temporal Sentence Localization in Untrimmed 3D Human Motions
In this paper, we address the unexplored question of temporal sentence localization in human motions (TSLM), aiming to locate a target moment from a 3D human motion that semantically corresponds to a text query.
On the Concept Trustworthiness in Concept Bottleneck Models
Concept Bottleneck Models (CBMs), which break down the reasoning process into the input-to-concept mapping and the concept-to-label prediction, have garnered significant attention due to their remarkable interpretability achieved by the interpretable concept bottleneck.
Training-Free Pretrained Model Merging
Furthermore, the visualization of the merged model within the multi-task loss landscape reveals that MuDSC enables the merged model to reside in the overlapping segment, featuring a unified lower loss for each task.
Automatic driving lane change safety prediction model based on LSTM
Autonomous driving technology can improve traffic safety and reduce traffic accidents.
Construction and application of artificial intelligence crowdsourcing map based on multi-track GPS data
In recent years, the rapid development of high-precision map technology combined with artificial intelligence has ushered in a new development opportunity in the field of intelligent vehicles.
EL-VIT: Probing Vision Transformer with Interactive Visualization
Therefore, a visualization system is needed to assist ViT users in understanding its functionality.
Speech Swin-Transformer: Exploring a Hierarchical Transformer with Shifted Windows for Speech Emotion Recognition
These segment-level patches are then encoded using a stack of Swin blocks, in which a local window Transformer is utilized to explore local inter-frame emotional information across frame patches of each segment patch.
Diffusion-based Pose Refinement and Muti-hypothesis Generation for 3D Human Pose Estimaiton
To address these two challenges, we propose a diffusion-based refinement framework called DRPose, which refines the output of deterministic models by reverse diffusion and achieves more suitable multi-hypothesis prediction for the current pose benchmark by multi-step refinement with multiple noises.
Agent-Aware Training for Agent-Agnostic Action Advising in Deep Reinforcement Learning
Instead, we employ a proxy model to extract state features that are both discriminative (adaptive to the agent) and generally applicable (robust to agent noise).
LLM4Vis: Explainable Visualization Recommendation using ChatGPT
To obtain demonstration examples with high-quality explanations, we propose a new explanation generation bootstrapping to iteratively refine generated explanations by considering the previous generation and template-based hint.
From Asset Flow to Status, Action and Intention Discovery: Early Malice Detection in Cryptocurrency
An ideal detection model is expected to achieve all three critical properties of (I) early detection, (II) good interpretability, and (III) versatility for various illicit activities.
CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUs
Data volumes have soared in recent years and the computational cost of an exhaustive exact nearest neighbor search is often prohibitive, necessitating the adoption of approximate techniques.
A practical PINN framework for multi-scale problems with multi-magnitude loss terms
The proposed methods not only significantly outperform the conventional PINN method in terms of computational efficiency and computational accuracy, but also compare favorably with the state-of-the-art methods in the recent literature.
Double-chain Constraints for 3D Human Pose Estimation in Images and Videos
Notably, our model achieves state-of-the-art performance on all action categories in the Human3. 6M dataset using detected 2D poses from CPN, and our code is available at: https://github. com/KHB1698/DC-GCT.
Ranked #44 on
3D Human Pose Estimation
on Human3.6M
REAL: A Representative Error-Driven Approach for Active Learning
Given a limited labeling budget, active learning (AL) aims to sample the most informative instances from an unlabeled pool to acquire labels for subsequent model training.
Vector Autoregressive Evolution for Dynamic Multi-Objective Optimisation
Dynamic multi-objective optimisation (DMO) handles optimisation problems with multiple (often conflicting) objectives in varying environments.
Target Detection for Construction Machinery Based on Deep Learning and Multisource Data Fusion
Target detection in use-case environments is a challenging task, which is influenced by complex and dynamic landscapes, illumination, and vibrations.
Intelligent multicast routing method based on multi-agent deep reinforcement learning in SDWN
To enable each agent to accurately understand the current network state and the status of multicast tree construction, the state space of each agent is designed based on the traffic and multicast tree status matrices, and the set of AP nodes in the network is used as the action space.
An Intelligent SDWN Routing Algorithm Based on Network Situational Awareness and Deep Reinforcement Learning
Second, a DRL-based data forwarding mechanism is designed in the knowledge plane.
Evolve Path Tracer: Early Detection of Malicious Addresses in Cryptocurrency
To detect fraud behaviors of malicious addresses in the early stage, we present Evolve Path Tracer, which consists of Evolve Path Encoder LSTM, Evolve Path Graph GCN, and Hierarchical Survival Predictor.
A Novel Self-Supervised Learning-Based Anomaly Node Detection Method Based on an Autoencoder in Wireless Sensor Networks
Due to the issue that existing wireless sensor network (WSN)-based anomaly detection methods only consider and analyze temporal features, in this paper, a self-supervised learning-based anomaly node detection method based on an autoencoder is designed.
MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation
In this work, we propose an ID-preserving talking head generation framework, which advances previous methods in two aspects.
Spatial-temporal traffic modeling with a fusion graph reconstructed by tensor decomposition
This paper proposes reconstructing the binary adjacency matrix via tensor decomposition, and a traffic flow forecasting method is proposed.
Hierarchical Terrain Attention and Multi-Scale Rainfall Guidance For Flood Image Prediction
With the deterioration of climate, the phenomenon of rain-induced flooding has become frequent.
HDNet: Hierarchical Dynamic Network for Gait Recognition using Millimeter-Wave Radar
Gait recognition is widely used in diversified practical applications.
Toward Intention Discovery for Early Malice Detection in Bitcoin
% With the type-dependent selection strategy and global status vectors, our model can be applied to detect various illicit activities with strong interpretability.
DRL-M4MR: An Intelligent Multicast Routing Approach Based on DQN Deep Reinforcement Learning in SDN
Traditional multicast routing methods have some problems in constructing a multicast tree, such as limited access to network state information, poor adaptability to dynamic and complex changes in the network, and inflexible data forwarding.
GestureLens: Visual Analysis of Gestures in Presentation Videos
There lacks an efficient method to help users conduct gesture exploration, which is challenging due to the intrinsically temporal evolution of gestures and their complex correlation to speech content.
Graph-based Approximate NN Search: A Revisit
For the graph construction, a two-stage graph diversification scheme is proposed, which makes a good trade-off between the efficiency and reachability for the search procedure that builds upon it.
A Novel Anomaly Detection Method for Multimodal WSN Data Flow via a Dynamic Graph Neural Network
Anomaly detection is widely used to distinguish system anomalies by analyzing the temporal and spatial features of wireless sensor network (WSN) data streams; it is one of critical technique that ensures the reliability of WSNs.
Interactive Data Analysis with Next-step Natural Language Query Recommendation
Natural language interfaces (NLIs) provide users with a convenient way to interactively analyze data through natural language queries.
StyleSwin: Transformer-based GAN for High-resolution Image Generation
To this end, we believe that local attention is crucial to strike the balance between computational efficiency and modeling capacity.
Ranked #1 on
Image Generation
on CelebA 256x256
(FID metric)
3rd Place Solution to Google Landmark Recognition Competition 2021
In this paper, we show our solution to the Google Landmark Recognition 2021 Competition.
NumGPT: Improving Numeracy Ability of Generative Pre-trained Models
However, those models do not consider the numerical properties of numbers and cannot perform robustly on numerical reasoning tasks (e. g., math word problems and measurement estimation).
DeHumor: Visual Analytics for Decomposing Humor
Despite being a critical communication skill, grasping humor is challenging -- a successful use of humor requires a mixture of both engaging content build-up and an appropriate vocal delivery (e. g., pause).
M2Lens: Visualizing and Explaining Multimodal Models for Sentiment Analysis
Much research focuses on modeling the complex intra- and inter-modal interactions between different communication channels.
ZJUKLAB at SemEval-2021 Task 4: Negative Augmentation with Language Model for Reading Comprehension of Abstract Meaning
This paper presents our systems for the three Subtasks of SemEval Task4: Reading Comprehension of Abstract Meaning (ReCAM).
Ranked #1 on
Reading Comprehension
on ReCAM
(using extra training data)
Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
In this paper, we rely on representative prototypes, the feature centroids of classes, to address the two issues for unsupervised domain adaptation.
Ranked #10 on
Semantic Segmentation
on GTAV-to-Cityscapes Labels
Secure Process Algebra
Based on our previous work on truly concurrent process algebras APTC, we use it to verify the security protocols.
Logic in Computer Science Cryptography and Security
Affine Ricci solitons of three-dimensional Lorentzian Lie groups
In this paper, we classify affine Ricci solitons associated to canonical connections and Kobayashi-Nomizu connections and perturbed canonical connections and perturbed Kobayashi-Nomizu connections on three-dimensional Lorentzian Lie groups with some product structure.
Differential Geometry 53C40, 53C42
MA-Unet: An improved version of Unet based on multi-scale and attention mechanism for medical image segmentation
In this paper, we try to eliminate semantic ambiguity in skip connection operations by adding attention gates (AGs), and use attention mechanisms to combine local features with their corresponding global dependencies, explicitly model the dependencies between channels and use multi-scale predictive fusion to utilize global information at different scales.
Frequency Separation based Adaptive Feedforward Control for Rejecting Wideband Vibration with Application to Hard Disk Drives
Starting from the first region, the feedforward control parameters are learned simultaneously with the low order plant model in the same region and then moves to the next region until all the regions are performed.
GNNLens: A Visual Analytics Approach for Prediction Error Diagnosis of Graph Neural Networks
Two case studies and interviews with domain experts demonstrate the effectiveness of GNNLens in facilitating the understanding of GNN models and their errors.
On the Sparsity of Neural Machine Translation Models
Modern neural machine translation (NMT) models employ a large number of parameters, which leads to serious over-parameterization and typically causes the underutilization of computational resources.
Bidirectional Mapping Generative Adversarial Networks for Brain MR to PET Synthesis
Fusing multi-modality medical images, such as MR and PET, can provide various anatomical or functional information about human body.
Peer-inspired Student Performance Prediction in Interactive Online Question Pools with Graph Neural Network
Specifically, we model the relationship between students and questions using student interactions to construct the student-interaction-question network and further present a new GNN model, called R^2GCN, which intrinsically works for the heterogeneous networks, to achieve generalizable student performance prediction in interactive online question pools.
Visual Analysis of Discrimination in Machine Learning
The growing use of automated decision-making in critical applications, such as crime prediction and college admission, has raised questions about fairness in machine learning.
A Review on Computational Intelligence Techniques in Cloud and Edge Computing
These optimization problems usually have complex properties, such as non-convexity and NP-hardness, which may not be addressed by the traditional convex optimization-based solutions.
An end-to-end CNN framework for polarimetric vision tasks based on polarization-parameter-constructing network
Pixel-wise operations between polarimetric images are important for processing polarization information.
Unsupervised Learning of Depth, Optical Flow and Pose with Occlusion from 3D Geometry
In the occluded region, as depth and camera motion can provide more reliable motion estimation, they can be used to instruct unsupervised learning of optical flow.
VoiceCoach: Interactive Evidence-based Training for Voice Modulation Skills in Public Speaking
The modulation of voice properties, such as pitch, volume, and speed, is crucial for delivering a successful public speech.
Go From the General to the Particular: Multi-Domain Translation with Domain Transformation Networks
The key challenge of multi-domain translation lies in simultaneously encoding both the general knowledge shared across domains and the particular knowledge distinctive to each domain in a unified model.
Visual Analytics of Student Learning Behaviors on K-12 Mathematics E-learning Platforms
With increasing popularity in online learning, a surge of E-learning platforms have emerged to facilitate education opportunities for k-12 (from kindergarten to 12th grade) students and with this, a wealth of information on their learning logs are getting recorded.
EmoCo: Visual Analysis of Emotion Coherence in Presentation Videos
Our visualization system features a channel coherence view and a sentence clustering view that together enable users to obtain a quick overview of emotion coherence and its temporal evolution.
DeepDrawing: A Deep Learning Approach to Graph Drawing
Node-link diagrams are widely used to facilitate network explorations.
Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations
Zero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings.
Convolutional neural networks with fractional order gradient method
This paper proposes a fractional order gradient method for the backward propagation of convolutional neural networks.
Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)
To leverage the data and resources, a new machine learning paradigm, called edge learning, has emerged where learning algorithms are deployed at the edge for providing fast and intelligent services to mobile users.
SPI-Optimizer: an integral-Separated PI Controller for Stochastic Optimization
Inspired by the conditional integration idea in classical control society, we propose SPI-Optimizer, an integral-Separated PI controller based optimizer WITHOUT introducing extra hyperparameter.
Structured Parallel Programming
Based on our previous work on algebraic laws for true concurrency, we design a structured parallel programming language for true concurrency called PPL.
Logic in Computer Science
Meta-Learning for Low-Resource Neural Machine Translation
We frame low-resource translation as a meta-learning problem, and we learn to adapt to low-resource languages based on multilingual high-resource language tasks.
Evaluating the Readability of Force Directed Graph Layouts: A Deep Learning Approach
In this paper, we present a novel deep learning-based approach to evaluate the readability of graph layouts by directly using graph images.
Multi-scale prediction for robust hand detection and classification
In this paper, we present a multi-scale Fully Convolutional Networks (MSP-RFCN) to robustly detect and classify human hands under various challenging conditions.
A Many-Objective Evolutionary Algorithm with Angle-Based Selection and Shift-Based Density Estimation
Specifically, the former is devised to find a pair of individuals with the minimum vector angle, which means that these two individuals share the most similar search direction.
Search Engine Guided Non-Parametric Neural Machine Translation
In this paper, we extend an attention-based neural machine translation (NMT) model by allowing it to access an entire training set of parallel sentence pairs even after training.
An Adaptive Framework to Tune the Coordinate Systems in Evolutionary Algorithms
In the evolutionary computation research community, the performance of most evolutionary algorithms (EAs) depends strongly on their implemented coordinate system.
Survey of modern Fault Diagnosis methods in networks
With the advent of modern computer networks, fault diagnosis has been a focus of research activity.
Challenge of Multi-Camera Tracking
Multi-camera tracking is quite different from single camera tracking, and it faces new technology and system architecture challenges.
Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction
This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy.
Analysis of Solution Quality of a Multiobjective Optimization-based Evolutionary Algorithm for Knapsack Problem
Multi-objective optimisation is regarded as one of the most promising ways for dealing with constrained optimisation problems in evolutionary optimisation.
Derivations of Normalized Mutual Information in Binary Classifications
In this work, we propose to assess classifiers in terms of normalized mutual information (NI), which is novel and well defined in a compact range for classifier evaluation.
