Search Results for author:
Found 17 papers, 7 papers with code
Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Clues
SPSC and SDSC augment live samples into simulated attack samples by simulating spoofing clues of physical and digital attacks, respectively, which significantly improve the capability of the model to detect "unseen" attack types.
GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation
Instead, we propose a user-agnostic global trajectory flow map and a novel Graph Enhanced Transformer model (GETNext) to better exploit the extensive collaborative signals for a more accurate next POI prediction, and alleviate the cold start problem in the meantime.
Space Meets Time: Local Spacetime Neural Network For Traffic Flow Forecasting
We argue that such correlations are universal and play a pivotal role in traffic flow.
Towards Automatically Extracting UML Class Diagrams from Natural Language Specifications
To develop our approach, we create a dataset of UML class diagrams and their English specifications with the help of volunteers.
Ranked #1 on
Model extraction
on UML Classes With Specs
Tribrid: Stance Classification with Neural Inconsistency Detection
In the second case, we show that using the confidence scores to remove doubtful predictions allows our method to achieve human-like performance over the retained information, which is still a sizable part of the original input.
USER: Unsupervised Structural Entropy-based Robust Graph Neural Network
To this end, we propose USER, an unsupervised robust version of graph neural networks that is based on structural entropy.
Classification of full exceptional collections of line bundles on three blow-ups of $\mathbb{P}^{3}$
A fullness conjecture of Kuznetsov says that if a smooth projective variety $X$ admits a full exceptional collection of line bundles of length $l$, then any exceptional collection of line bundles of length $l$ is full.
Algebraic Geometry 14F05, 14J45, 18E30
Multimodal Learning For Classroom Activity Detection
The experimental results demonstrate the benefits of our approach on learning attention based neural network from classroom data with different modalities, and show our approach is able to outperform state-of-the-art baselines in terms of various evaluation metrics.
S-index: Towards Better Metrics for Quantifying Research Impact
The ongoing growth in the volume of scientific literature available today precludes researchers from efficiently discerning the relevant from irrelevant content.
Space Meets Time: Local Spacetime Neural Network For Traffic Flow Forecasting
We argue that such correlations are universal and play a pivotal role in traffic flow.
GACAN: Graph Attention-Convolution-Attention Networks for Traffic Forecasting Based on Multi-granularity Time Series
The main novelty of the model is the integration of time series of four different time granularities: the original time series, together with hourly, daily, and weekly time series.
Replacing the Framingham-based equation for prediction of cardiovascular disease risk and adverse outcome by using artificial intelligence and retinal imaging
Purpose: To create and evaluate the accuracy of an artificial intelligence Deep learning platform (ORAiCLE) capable of using only retinal fundus images to predict both an individuals overall 5 year cardiovascular risk (CVD) and the relative contribution of the component risk factors that comprise this risk.
Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding
All existing works first utilize a sparse sampling strategy to extract a fixed number of video frames and then conduct multi-modal interactions with query sentence for reasoning.
Structure-reinforced Transformer for Dynamic Graph Representation Learning with Edge Temporal States
The burgeoning field of dynamic graph representation learning, fuelled by the increasing demand for graph data analysis in real-world applications, poses both enticing opportunities and formidable challenges.
S-T CRF: Spatial-Temporal Conditional Random Field for Human Trajectory Prediction
Trajectory prediction is of significant importance in computer vision.
Large Language Model Meets Graph Neural Network in Knowledge Distillation
Despite recent community revelations about the advancements and potential applications of Large Language Models (LLMs) in understanding Text-Attributed Graph (TAG), the deployment of LLMs for production is hindered by its high computational and storage requirements, as well as long latencies during model inference.
MLS-Track: Multilevel Semantic Interaction in RMOT
The new trend in multi-object tracking task is to track objects of interest using natural language.
