Picture for Nicola Messina

Nicola Messina

Mind the Prompt: A Novel Benchmark for Prompt-based Class-Agnostic Counting

Add code
Sep 24, 2024
Viaarxiv icon

Joint-Dataset Learning and Cross-Consistent Regularization for Text-to-Motion Retrieval

Add code
Jul 02, 2024
Figure 1 for Joint-Dataset Learning and Cross-Consistent Regularization for Text-to-Motion Retrieval
Figure 2 for Joint-Dataset Learning and Cross-Consistent Regularization for Text-to-Motion Retrieval
Figure 3 for Joint-Dataset Learning and Cross-Consistent Regularization for Text-to-Motion Retrieval
Figure 4 for Joint-Dataset Learning and Cross-Consistent Regularization for Text-to-Motion Retrieval
Viaarxiv icon

Is CLIP the main roadblock for fine-grained open-world perception?

Add code
Apr 04, 2024
Viaarxiv icon

The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding

Add code
Nov 29, 2023
Figure 1 for The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding
Figure 2 for The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding
Figure 3 for The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding
Figure 4 for The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding
Viaarxiv icon

Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language

Add code
May 25, 2023
Viaarxiv icon

Development of a Realistic Crowd Simulation Environment for Fine-grained Validation of People Tracking Methods

Add code
Apr 26, 2023
Figure 1 for Development of a Realistic Crowd Simulation Environment for Fine-grained Validation of People Tracking Methods
Figure 2 for Development of a Realistic Crowd Simulation Environment for Fine-grained Validation of People Tracking Methods
Figure 3 for Development of a Realistic Crowd Simulation Environment for Fine-grained Validation of People Tracking Methods
Figure 4 for Development of a Realistic Crowd Simulation Environment for Fine-grained Validation of People Tracking Methods
Viaarxiv icon

CrowdSim2: an Open Synthetic Benchmark for Object Detectors

Add code
Apr 11, 2023
Viaarxiv icon

Deep learning for structural health monitoring: An application to heritage structures

Add code
Nov 04, 2022
Viaarxiv icon

A Spatio-Temporal Attentive Network for Video-Based Crowd Counting

Add code
Aug 24, 2022
Figure 1 for A Spatio-Temporal Attentive Network for Video-Based Crowd Counting
Figure 2 for A Spatio-Temporal Attentive Network for Video-Based Crowd Counting
Figure 3 for A Spatio-Temporal Attentive Network for Video-Based Crowd Counting
Figure 4 for A Spatio-Temporal Attentive Network for Video-Based Crowd Counting
Viaarxiv icon

ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval

Add code
Jul 29, 2022
Figure 1 for ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval
Figure 2 for ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval
Figure 3 for ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval
Figure 4 for ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval
Viaarxiv icon