activity
20162025
most citedWorking Memory Connections for LSTM

282 citations · 650 across the 73 of their papers we have counts for

collaborators
Showing 2024Show all

20 papers · 1 filter

cs.CV2024

Is Multiple Object Tracking a Matter of Specialization?

Gianluca Mancusi, Mattia Bernardi, Aniello Panariello +3

End-to-end transformer-based trackers have achieved remarkable performance on most human-related datasets. However, training these trackers in heterogeneous scenarios poses signifi…

cs.CV2024

KRONC: Keypoint-based Robust Camera Optimization for 3D Car Reconstruction

Davide Di Nucci, Alessandro Simoni, Matteo Tomei +3

The three-dimensional representation of objects or scenes starting from a set of images has been a widely discussed topic for years and has gained additional attention after the di…

cs.RO2024

UNMuTe: Unifying Navigation and Multimodal Dialogue-like Text Generation

Niyati Rawal, Roberto Bigazzi, Lorenzo Baraldi +1

Smart autonomous agents are becoming increasingly important in various real-life applications, including robotics and autonomous vehicles. One crucial skill that these agents must…

cs.CV2024

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

Sara Sarto, Marcella Cornia, Lorenzo Baraldi +1

Effectively aligning with human judgment when evaluating machine-generated image captions represents a complex yet intriguing challenge. Existing evaluation metrics like CIDEr or C…

cs.CV2024

Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities

Lorenzo Baraldi, Federico Cocchi, Marcella Cornia +2

Discerning between authentic content and that generated by advanced AI methods has become increasingly challenging. While previous research primarily addresses the detection of fak…

cs.CV2024

Mask and Compress: Efficient Skeleton-based Action Recognition in Continual Learning

Matteo Mosconi, Andriy Sorokin, Aniello Panariello +6

The use of skeletal data allows deep learning models to perform action recognition efficiently and effectively. Herein, we believe that exploring this problem within the context of…