Picture for Hung-Ting Su

Hung-Ting Su

Investigating Video Reasoning Capability of Large Language Models with Tropes in Movies

Add code
Jun 16, 2024
Viaarxiv icon

Enhancing Sustainable Urban Mobility Prediction with Telecom Data: A Spatio-Temporal Framework Approach

Add code
May 26, 2024
Viaarxiv icon

Tracking-Assisted Object Detection with Event Cameras

Add code
Mar 27, 2024
Figure 1 for Tracking-Assisted Object Detection with Event Cameras
Figure 2 for Tracking-Assisted Object Detection with Event Cameras
Figure 3 for Tracking-Assisted Object Detection with Event Cameras
Figure 4 for Tracking-Assisted Object Detection with Event Cameras
Viaarxiv icon

AED: Adaptable Error Detection for Few-shot Imitation Policy

Add code
Feb 06, 2024
Viaarxiv icon

TelTrans: Applying Multi-Type Telecom Data to Transportation Evaluation and Prediction via Multifaceted Graph Modeling

Add code
Jan 06, 2024
Figure 1 for TelTrans: Applying Multi-Type Telecom Data to Transportation Evaluation and Prediction via Multifaceted Graph Modeling
Figure 2 for TelTrans: Applying Multi-Type Telecom Data to Transportation Evaluation and Prediction via Multifaceted Graph Modeling
Figure 3 for TelTrans: Applying Multi-Type Telecom Data to Transportation Evaluation and Prediction via Multifaceted Graph Modeling
Figure 4 for TelTrans: Applying Multi-Type Telecom Data to Transportation Evaluation and Prediction via Multifaceted Graph Modeling
Viaarxiv icon

Unsupervised Adversarial Detection without Extra Model: Training Loss Should Change

Add code
Aug 07, 2023
Figure 1 for Unsupervised Adversarial Detection without Extra Model: Training Loss Should Change
Figure 2 for Unsupervised Adversarial Detection without Extra Model: Training Loss Should Change
Figure 3 for Unsupervised Adversarial Detection without Extra Model: Training Loss Should Change
Figure 4 for Unsupervised Adversarial Detection without Extra Model: Training Loss Should Change
Viaarxiv icon

Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering

Add code
Apr 07, 2023
Figure 1 for Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering
Figure 2 for Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering
Figure 3 for Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering
Figure 4 for Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering
Viaarxiv icon

BIRD-PCC: Bi-directional Range Image-based Deep LiDAR Point Cloud Compression

Add code
Mar 09, 2023
Figure 1 for BIRD-PCC: Bi-directional Range Image-based Deep LiDAR Point Cloud Compression
Figure 2 for BIRD-PCC: Bi-directional Range Image-based Deep LiDAR Point Cloud Compression
Figure 3 for BIRD-PCC: Bi-directional Range Image-based Deep LiDAR Point Cloud Compression
Figure 4 for BIRD-PCC: Bi-directional Range Image-based Deep LiDAR Point Cloud Compression
Viaarxiv icon

Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling

Add code
Oct 08, 2022
Figure 1 for Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling
Figure 2 for Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling
Figure 3 for Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling
Figure 4 for Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling
Viaarxiv icon

MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer

Add code
Mar 28, 2022
Figure 1 for MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer
Figure 2 for MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer
Figure 3 for MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer
Figure 4 for MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer
Viaarxiv icon