Picture for Arian Bakhtiarnia

Arian Bakhtiarnia

Audio-Visual Dataset and Method for Anomaly Detection in Traffic Videos

Add code
May 24, 2023
Viaarxiv icon

Accurate Gigapixel Crowd Counting by Iterative Zooming and Refinement

Add code
May 16, 2023
Viaarxiv icon

PromptMix: Text-to-image diffusion models enhance the performance of lightweight networks

Add code
Jan 31, 2023
Viaarxiv icon

Crowd Counting on Heavily Compressed Images with Curriculum Pre-Training

Add code
Aug 15, 2022
Figure 1 for Crowd Counting on Heavily Compressed Images with Curriculum Pre-Training
Figure 2 for Crowd Counting on Heavily Compressed Images with Curriculum Pre-Training
Figure 3 for Crowd Counting on Heavily Compressed Images with Curriculum Pre-Training
Figure 4 for Crowd Counting on Heavily Compressed Images with Curriculum Pre-Training
Viaarxiv icon

Efficient High-Resolution Deep Learning: A Survey

Add code
Jul 26, 2022
Figure 1 for Efficient High-Resolution Deep Learning: A Survey
Figure 2 for Efficient High-Resolution Deep Learning: A Survey
Figure 3 for Efficient High-Resolution Deep Learning: A Survey
Figure 4 for Efficient High-Resolution Deep Learning: A Survey
Viaarxiv icon

Analysis of the Effect of Low-Overhead Lossy Image Compression on the Performance of Visual Crowd Counting for Smart City Applications

Add code
Jul 20, 2022
Figure 1 for Analysis of the Effect of Low-Overhead Lossy Image Compression on the Performance of Visual Crowd Counting for Smart City Applications
Figure 2 for Analysis of the Effect of Low-Overhead Lossy Image Compression on the Performance of Visual Crowd Counting for Smart City Applications
Figure 3 for Analysis of the Effect of Low-Overhead Lossy Image Compression on the Performance of Visual Crowd Counting for Smart City Applications
Figure 4 for Analysis of the Effect of Low-Overhead Lossy Image Compression on the Performance of Visual Crowd Counting for Smart City Applications
Viaarxiv icon

Dynamic Split Computing for Efficient Deep Edge Intelligence

Add code
May 23, 2022
Figure 1 for Dynamic Split Computing for Efficient Deep Edge Intelligence
Figure 2 for Dynamic Split Computing for Efficient Deep Edge Intelligence
Figure 3 for Dynamic Split Computing for Efficient Deep Edge Intelligence
Viaarxiv icon

Continual Transformers: Redundancy-Free Attention for Online Inference

Add code
Jan 17, 2022
Viaarxiv icon

Multi-Exit Vision Transformer for Dynamic Inference

Add code
Jun 30, 2021
Figure 1 for Multi-Exit Vision Transformer for Dynamic Inference
Figure 2 for Multi-Exit Vision Transformer for Dynamic Inference
Figure 3 for Multi-Exit Vision Transformer for Dynamic Inference
Figure 4 for Multi-Exit Vision Transformer for Dynamic Inference
Viaarxiv icon

Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead

Add code
May 19, 2021
Figure 1 for Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead
Figure 2 for Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead
Figure 3 for Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead
Figure 4 for Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead
Viaarxiv icon