Search Results for author:
Found 25 papers, 5 papers with code
AMOA: Global Acoustic Feature Enhanced Modal-Order-Aware Network for Multimodal Sentiment Analysis
Our model also achieves state-of-the-art performance on a widely used sarcasm dataset.
Weakly Supervised Anomaly Detection via Knowledge-Data Alignment
In this paper, we introduce a novel framework Knowledge-Data Alignment (KDAlign) to integrate rule knowledge, typically summarized by human experts, to supplement the limited labeled data.
Temporal-Aware Refinement for Video-based Human Pose and Shape Recovery
Though significant progress in human pose and shape recovery from monocular RGB images has been made in recent years, obtaining 3D human motion with high accuracy and temporal consistency from videos remains challenging.
DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation
However, due to the presence of linguistic and acoustic diversity, the target speech follows a complex multimodal distribution, posing challenges to achieving both high-quality translations and fast decoding speeds for S2ST models.
Using AI Uncertainty Quantification to Improve Human Decision-Making
These results indicate that implementing high quality, instance-level UQ for AI may improve decision-making with real systems compared to AI predictions alone.
LKPNR: LLM and KG for Personalized News Recommendation Framework
Traditional methods are usually difficult to grasp the complex semantic information in news texts, resulting in unsatisfactory recommendation results.
BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models
To minimize human workload, we propose to transfer the capabilities of language generation and instruction following from English to other languages through an interactive translation task.
Carbon emissions and sustainability of launching 5G mobile networks in China
We show that the decline in carbon efficiency leads to a carbon efficiency trap, estimated to cause additional carbon emissions of 23. 82 +- 1. 07 megatons in China.
CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation
End-to-end speech translation (ST) is the task of translating speech signals in the source language into text in the target language.
Attention-guided Multi-step Fusion: A Hierarchical Fusion Network for Multimodal Recommendation
The main idea of multimodal recommendation is the rational utilization of the item's multimodal information to improve the recommendation performance.
Deep learning reveals the common spectrum underlying multiple brain disorders in youth and elders from brain functional networks
Brain disorders in the early and late life of humans potentially share pathological alterations in brain functions.
HGAN: Hierarchical Graph Alignment Network for Image-Text Retrieval
Then, a multi-granularity shared space is established with a designed Multi-granularity Feature Aggregation and Rearrangement (MFAR) module, which enhances the semantic corresponding relations between the local and global information, and obtains more accurate feature representations for the image and text modalities.
Deep Multi-Scale Representation Learning with Attention for Automatic Modulation Classification
In this report, we find some experienced improvements by using large kernel size for convolutional deep convolution neural network based AMC, which is more efficient in extracting multi-scale features of the raw signal I/Q sequence data.
Modeling dynamic volatility under uncertain environment with fuzziness and randomness
The problem related to predicting dynamic volatility in financial market plays a crucial role in many contexts.
Stochastic volatility modeling of high-frequency CSI 300 index and dynamic jump prediction driven by machine learning
This paper models stochastic process of price time series of CSI 300 index in Chinese financial market, analyzes volatility characteristics of intraday high-frequency price data.
Deep Q-learning of global optimizer of multiply model parameters for viscoelastic imaging
Significance: DQMP method is promising for imaging of multiple parameters, and can be generalized to global optimization for many other complex nonconvex functions and imaging of physical parameters.
An Arbitrary Scale Super-Resolution Approach for 3D MR Images via Implicit Neural Representation
In the ArSSR model, the reconstruction of HR images with different up-scaling rates is defined as learning a continuous implicit voxel function from the observed LR images.
Multi-concept adversarial attacks
In this paper, we address the above research question by developing novel attack techniques that can simultaneously attack one set of ML models while preserving the accuracy of the other.
Improving Fairness of AI Systems with Lossless De-biasing
We demonstrate the effectiveness of our technique on real datasets using a variety of fairness metrics.
A Reversed and Shift Sparse Array Scheme based on the Difference and Sum Co-array
The reversed and shift (RAS) sparse array scheme, which is based on the difference and sum co-array (DSCA) and remarkably enhances the capability of identifying sources, is proposed.
Does Explainable Artificial Intelligence Improve Human Decision-Making?
Explainable AI provides insight into the "why" for model predictions, offering potential for users to better understand and trust a model, and to recognize and correct AI predictions that are incorrect.
Dynamics of ferromagnetic bimerons driven by spin currents and magnetic fields
Numerical simulations demonstrate that two bimerons with opposite signs of topological numbers can be created simultaneously in a ferromagnetic thin film via current-induced spin torques.
Mesoscale and Nanoscale Physics
Sample Dropout for Audio Scene Classification Using Multi-Scale Dense Connected Convolutional Neural Network
In this paper, we explore the use of multi-scale Dense connected convolutional neural network (DenseNet) for the classification task, with the goal to improve the classification performance as multi-scale features can be extracted from the time-frequency representation of the audio signal.
Breaking Transferability of Adversarial Samples with Randomness
We demonstrate that introducing randomness to the DNN models is sufficient to defeat adversarial attacks, given that the adversary does not have an unlimited attack budget.
Magnetic skyrmion-based synaptic devices
Magnetic skyrmions are promising candidates for next-generation information carriers, owing to their small size, topological stability, and ultralow depinning current density.
