Picture for Song Yang

Song Yang

MLS-Track: Multilevel Semantic Interaction in RMOT

Apr 18, 2024
Figure 1 for MLS-Track: Multilevel Semantic Interaction in RMOT
Figure 2 for MLS-Track: Multilevel Semantic Interaction in RMOT
Figure 3 for MLS-Track: Multilevel Semantic Interaction in RMOT
Figure 4 for MLS-Track: Multilevel Semantic Interaction in RMOT
Viaarxiv icon

Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Clues

Add code
Apr 12, 2024
Viaarxiv icon

Large Language Model Meets Graph Neural Network in Knowledge Distillation

Feb 09, 2024
Viaarxiv icon

S-T CRF: Spatial-Temporal Conditional Random Field for Human Trajectory Prediction

Nov 30, 2023
Viaarxiv icon

GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation

Add code
Mar 03, 2023
Figure 1 for GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation
Figure 2 for GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation
Figure 3 for GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation
Figure 4 for GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation
Viaarxiv icon

USER: Unsupervised Structural Entropy-based Robust Graph Neural Network

Add code
Feb 12, 2023
Figure 1 for USER: Unsupervised Structural Entropy-based Robust Graph Neural Network
Figure 2 for USER: Unsupervised Structural Entropy-based Robust Graph Neural Network
Figure 3 for USER: Unsupervised Structural Entropy-based Robust Graph Neural Network
Figure 4 for USER: Unsupervised Structural Entropy-based Robust Graph Neural Network
Viaarxiv icon

Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding

Jan 02, 2023
Figure 1 for Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding
Figure 2 for Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding
Figure 3 for Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding
Figure 4 for Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding
Viaarxiv icon

Towards Automatically Extracting UML Class Diagrams from Natural Language Specifications

Add code
Oct 27, 2022
Figure 1 for Towards Automatically Extracting UML Class Diagrams from Natural Language Specifications
Figure 2 for Towards Automatically Extracting UML Class Diagrams from Natural Language Specifications
Figure 3 for Towards Automatically Extracting UML Class Diagrams from Natural Language Specifications
Figure 4 for Towards Automatically Extracting UML Class Diagrams from Natural Language Specifications
Viaarxiv icon

GACAN: Graph Attention-Convolution-Attention Networks for Traffic Forecasting Based on Multi-granularity Time Series

Oct 27, 2021
Figure 1 for GACAN: Graph Attention-Convolution-Attention Networks for Traffic Forecasting Based on Multi-granularity Time Series
Figure 2 for GACAN: Graph Attention-Convolution-Attention Networks for Traffic Forecasting Based on Multi-granularity Time Series
Figure 3 for GACAN: Graph Attention-Convolution-Attention Networks for Traffic Forecasting Based on Multi-granularity Time Series
Figure 4 for GACAN: Graph Attention-Convolution-Attention Networks for Traffic Forecasting Based on Multi-granularity Time Series
Viaarxiv icon

Tribrid: Stance Classification with Neural Inconsistency Detection

Add code
Sep 14, 2021
Figure 1 for Tribrid: Stance Classification with Neural Inconsistency Detection
Figure 2 for Tribrid: Stance Classification with Neural Inconsistency Detection
Figure 3 for Tribrid: Stance Classification with Neural Inconsistency Detection
Figure 4 for Tribrid: Stance Classification with Neural Inconsistency Detection
Viaarxiv icon