Search Results for author:
Found 44 papers, 16 papers with code
Encoding and Fusing Semantic Connection and Linguistic Evidence for Implicit Discourse Relation Recognition
Prior studies use one attention mechanism to improve contextual semantic representation learning for implicit discourse relation recognition (IDRR).
ConnPrompt: Connective-cloze Prompt Learning for Implicit Discourse Relation Recognition
As the first trial of using this new paradigm for IDRR, this paper develops a Connective-cloze Prompt (ConnPrompt) to transform the relation prediction task as a connective-cloze task.
SocialCVAE: Predicting Pedestrian Trajectory via Interaction Conditioned Latents
Pedestrian trajectory prediction is the key technology in many applications for providing insights into human behavior and anticipating human future motions.
Zoom-shot: Fast and Efficient Unsupervised Zero-Shot Transfer of CLIP to Vision Encoders with Multimodal Loss
To address this issue, we propose Zoom-shot, a novel method for transferring the zero-shot capabilities of CLIP to any pre-trained vision encoder.
Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Values
However, real-world time series data is usually not well-structured, posting significant challenges to existing approaches: (1) The existence of missing values in multivariate time series data along variable and time dimensions hinders the effective modeling of interwoven spatial and temporal dependencies, resulting in important patterns being overlooked during model training; (2) Anomaly scoring with irregularly-sampled observations is less explored, making it difficult to use existing detectors for multivariate series without fully-observed values.
Explainable AI is Responsible AI: How Explainability Creates Trustworthy and Socially Responsible Artificial Intelligence
In this work, we explore state-of-the-art literature on RAI and XAI technologies.
Degradation-Aware Self-Attention Based Transformer for Blind Image Super-Resolution
In particular, we integrate both CNN and Transformer components into the SR network, where we first use the CNN modulated by the degradation information to extract local features, and then employ the degradation-aware Transformer to extract global semantic features.
Adaptive Prompt Learning with Distilled Connective Knowledge for Implicit Discourse Relation Recognition
Implicit discourse relation recognition (IDRR) aims at recognizing the discourse relation between two text segments without an explicit connective.
Hyper-pixel-wise Contrastive Learning Augmented Segmentation Network for Old Landslide Detection through Fusing High-Resolution Remote Sensing Images and Digital Elevation Model Data
To extract accurate semantic features, a hyper-pixel-wise contrastive learning augmented segmentation network (HPCL-Net) is proposed, which augments the local salient feature extraction from boundaries of landslides through HPCL-Net and fuses heterogeneous infromation in the semantic space from high-resolution remote sensing images and digital elevation model data.
End-to-end Hyperspectral Image Change Detection Network Based on Band Selection
For hyperspectral image change detection (HSI-CD), one key challenge is to reduce band redundancy, as only a few bands are crucial for change detection while other bands may be adverse to it.
Learner Referral for Cost-Effective Federated Learning Over Hierarchical IoT Networks
These methods are designed to minimize the cost incurred by the worst-case participant and ensure the long-term fairness of FL in hierarchical Internet of Things (HieIoT) networks.
DAPrompt: Deterministic Assumption Prompt Learning for Event Causality Identification
We use the probabilities of predicted events to evaluate the assumption rationality for the final event causality decision.
Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detection
To overcome these limitations, we propose a novel method, correlation-aware spatial-temporal graph learning (termed CST-GL), for time series anomaly detection.
Edit-DiffNeRF: Editing 3D Neural Radiance Fields using 2D Diffusion Model
To address this challenge, we propose the Edit-DiffNeRF framework, which is composed of a frozen diffusion model, a proposed delta module to edit the latent semantic space of the diffusion model, and a NeRF.
TEPrompt: Task Enlightenment Prompt Learning for Implicit Discourse Relation Recognition
Although an auxiliary task is not used to directly output final prediction, we argue that during the joint training some of its learned features can be useful to boost the main task.
MRGAN360: Multi-stage Recurrent Generative Adversarial Network for 360 Degree Image Saliency Prediction
We employ a recurrent neural network among adjacent prediction stages to model their correlations, and exploit a discriminator at the end of each stage to supervise the output saliency map.
X-Pruner: eXplainable Pruning for Vision Transformers
Recent studies have proposed to prune transformers in an unexplainable manner, which overlook the relationship between internal units of the model and the target class, thereby leading to inferior performance.
Multiscale Tensor Decomposition and Rendering Equation Encoding for View Synthesis
Instead of encoding view directions to model view-dependent effects, we further propose to encode the rendering equation in the feature space by employing the anisotropic spherical Gaussian mixture predicted from the proposed multiscale representation.
An Iterative Classification and Semantic Segmentation Network for Old Landslide Detection Using High-Resolution Remote Sensing Images
An object-level contrastive learning (OCL) strategy is employed in the object classification sub-network featuring a siamese network to realize the global features extraction, and a sub-object-level contrastive learning (SOCL) paradigm is designed in the semantic segmentation sub-network to efficiently extract salient features from boundaries of landslides.
Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusion
In this work, we investigate the problem of Model-Agnostic Zero-Shot Classification (MA-ZSC), which refers to training non-specific classification architectures (downstream models) to classify real images without using any real images during training.
Bi-Directional Iterative Prompt-Tuning for Event Argument Extraction
Recently, prompt-tuning has attracted growing interests in event argument extraction (EAE).
Meta-Interpolation: Time-Arbitrary Frame Interpolation via Dual Meta-Learning
Extensive qualitative and quantitative evaluations, as well as ablation studies, demonstrate that, via introducing meta-learning in our framework in such a well-designed way, our method not only achieves superior performance to state-of-the-art frame interpolation approaches but also owns an extended capacity to support the interpolation at an arbitrary time-step.
eX-ViT: A Novel eXplainable Vision Transformer for Weakly Supervised Semantic Segmentation
To close these crucial gaps, we propose a novel vision transformer dubbed the eXplainable Vision Transformer (eX-ViT), an intrinsically interpretable transformer model that is able to jointly discover robust interpretable features and perform the prediction.
DFGC 2022: The Second DeepFake Game Competition
There is a two-party game between DeepFake creators and defenders.
Multi-faceted Graph Attention Network for Radar Target Recognition in Heterogeneous Radar Network
In this paper, a two-stream semantic feature fusion model, termed Multi-faceted Graph Attention Network (MF-GAT), is proposed to greatly improve the accuracy in the low SNR region of the heterogeneous radar network.
Unsupervised Representation Learning for 3D MRI Super Resolution with Degradation Adaptation
However, the difference in degradation representations between synthetic and authentic LR images suppresses the quality of SR images reconstructed from authentic LR images.
Spatio-Temporal-Frequency Graph Attention Convolutional Network for Aircraft Recognition Based on Heterogeneous Radar Network
This paper proposes a knowledge-and-data-driven graph neural network-based collaboration learning model for reliable aircraft recognition in a heterogeneous radar network.
Contrastive Learning for Automotive mmWave Radar Detection Points Based Instance Segmentation
Deep learning-based instance segmentation enables real-time object identification from the radar detection points.
Human Biometric Signals Monitoring based on WiFi Channel State Information using Deep Learning
This system overall accuracy for the heart and respiration rate estimation can reach 99. 109% and 98. 581%, respectively.
A Survey of Implicit Discourse Relation Recognition
As sentences are normally consist of multiple text segments, correct understanding of the theme of a discourse should take into consideration of the relations in between text segments.
DDU-Net: Dual-Decoder-U-Net for Road Extraction Using High-Resolution Remote Sensing Images
Extracting roads from high-resolution remote sensing images (HRSIs) is vital in a wide variety of applications, such as autonomous driving, path planning, and road navigation.
TE-YOLOF: Tiny and efficient YOLOF for blood cell detection
In this work, an object detector based on YOLOF has been proposed to detect blood cell objects such as red blood cells, white blood cells and platelets.
DPN-SENet:A self-attention mechanism neural network for detection and diagnosis of COVID-19 from chest x-ray images
We propose a deep learning model that can help radiologists and clinicians use chest X-rays to diagnose COVID-19 cases and show the diagnostic features of pneumonia.
AGSFCOS: Based on attention mechanism and Scale-Equalizing pyramid network of object detection
In order to solve the above problems, Experiments show that our model has a certain improvement in accuracy compared with the current popular detection models on the COCO dataset, the designed attention mechanism module can capture contextual information well, improve detection accuracy, and use sepc network to help balance abstract and detailed information, and reduce the problem of semantic gap in the feature pyramid network.
Denoising Higher-order Moments for Blind Digital Modulation Identification in Multiple-antenna Systems
The paper proposes a new technique that substantially improves blind digital modulation identification (DMI) algorithms that are based on higher-order statistics (HOS).
Probabilistic Placement Optimization for Non-coherent and Coherent Joint Transmission in Cache-Enabled Cellular Networks
Using stochastic geometry, we derive an integral expression for the successful transmission probability (STP) in NC-JT scheme, and present an upper bound and a tight approximation for the STP of the C-JT scheme.
Information Theory Information Theory
MemTorch: An Open-source Simulation Framework for Memristive Deep Learning Systems
Memristive devices have shown great promise to facilitate the acceleration and improve the power efficiency of Deep Learning (DL) systems.
Emerging Technologies
Anypath Routing Protocol Design via Q-Learning for Underwater Sensor Networks
As a promising technology in the Internet of Underwater Things, underwater sensor networks have drawn a widespread attention from both academia and industry.
Dynamic Energy Dispatch Based on Deep Reinforcement Learning in IoT-Driven Smart Isolated Microgrids
Microgrids (MGs) are small, local power grids that can operate independently from the larger utility grid.
Training Progressively Binarizing Deep Networks Using FPGAs
While hardware implementations of inference routines for Binarized Neural Networks (BNNs) are plentiful, current realizations of efficient BNN hardware training accelerators, suitable for Internet of Things (IoT) edge devices, leave much to be desired.
Multi-user Resource Control with Deep Reinforcement Learning in IoT Edge Computing
By leveraging the concept of mobile edge computing (MEC), massive amount of data generated by a large number of Internet of Things (IoT) devices could be offloaded to MEC server at the edge of wireless network for further computational intensive processing.
Accelerating Deterministic and Stochastic Binarized Neural Networks on FPGAs Using OpenCL
Consequently, the performance and complexity of Artificial Neural Networks (ANNs) is burgeoning.
Basis Signal Optimization for N-Continuous OFDM
A novel basis signal optimization method is proposed for reducing the interference in the N-continuous orthogonal frequency division multiplexing (NC-OFDM) system.
Context-Aware Single-Shot Detector
SSD is one of the state-of-the-art object detection algorithms, and it combines high detection accuracy with real-time speed.
