Picture for Marcella Cornia

Marcella Cornia

Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis

Add code
Dec 04, 2024
Viaarxiv icon

Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation

Add code
Nov 28, 2024
Viaarxiv icon

Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering

Add code
Nov 25, 2024
Viaarxiv icon

TPP-Gaze: Modelling Gaze Dynamics in Space and Time with Neural Temporal Point Processes

Add code
Oct 30, 2024
Viaarxiv icon

Personalized Instance-based Navigation Toward User-Specific Objects in Realistic Environments

Add code
Oct 23, 2024
Viaarxiv icon

Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training

Add code
Oct 09, 2024
Figure 1 for Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training
Figure 2 for Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training
Figure 3 for Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training
Figure 4 for Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training
Viaarxiv icon

Fluent and Accurate Image Captioning with a Self-Trained Reward Model

Add code
Aug 29, 2024
Figure 1 for Fluent and Accurate Image Captioning with a Self-Trained Reward Model
Figure 2 for Fluent and Accurate Image Captioning with a Self-Trained Reward Model
Figure 3 for Fluent and Accurate Image Captioning with a Self-Trained Reward Model
Figure 4 for Fluent and Accurate Image Captioning with a Self-Trained Reward Model
Viaarxiv icon

Revisiting Image Captioning Training Paradigm via Direct CLIP-based Optimization

Add code
Aug 26, 2024
Viaarxiv icon

Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities

Add code
Jul 29, 2024
Viaarxiv icon

BRIDGE: Bridging Gaps in Image Captioning Evaluation with Stronger Visual Cues

Add code
Jul 29, 2024
Viaarxiv icon