Davide Modolo

papers

639

total citations

papers (13)

What To Look at and Where: Semantic and Spatial Refined Transformer for Detecting Human-Object Interactions

CVPR 2022arXiv

citations

Hierarchical Self-Supervised Representation Learning for Movie Understanding

CVPR 2022arXiv

citations

ScaleDet: A Scalable Multi-Dataset Object Detector

CVPR 2023arXiv

citations

Self-Supervised Multi-Object Tracking with Path Consistency

CVPR 2024arXiv

citations

MaCLR: Motion-Aware Contrastive Learning of Representations for Videos

ECCV 2022arXiv

citations

Hyperbolic Learning with Synthetic Captions for Open-World Detection

CVPR 2024arXiv

citations

Selective Feature Compression for Efficient Activity Recognition Inference

ICCV 2021arXiv

citations

Enhancing Numerical Prediction of MLLMs with Soft Labeling

ICCV 2025

citations

SkeleTR: Towards Skeleton-based Action Recognition in the Wild

ICCV 2023

citations

Davide Modolo

papers (13)

SiamMOT: Siamese Multi-Object Tracking

Combining Detection and Tracking for Human Pose Estimation in Videos

TubeR: Tubelet Transformer for Video Action Detection

Semi-supervised Vision Transformers at Scale

What To Look at and Where: Semantic and Spatial Refined Transformer for Detecting Human-Object Interactions

Hierarchical Self-Supervised Representation Learning for Movie Understanding

ScaleDet: A Scalable Multi-Dataset Object Detector

Self-Supervised Multi-Object Tracking with Path Consistency

MaCLR: Motion-Aware Contrastive Learning of Representations for Videos

Hyperbolic Learning with Synthetic Captions for Open-World Detection

Selective Feature Compression for Efficient Activity Recognition Inference

Enhancing Numerical Prediction of MLLMs with Soft Labeling

SkeleTR: Towards Skeleton-based Action Recognition in the Wild

papers (13)

SiamMOT: Siamese Multi-Object Tracking

Combining Detection and Tracking for Human Pose Estimation in Videos

TubeR: Tubelet Transformer for Video Action Detection

Semi-supervised Vision Transformers at Scale

What To Look at and Where: Semantic and Spatial Refined Transformer for Detecting Human-Object Interactions

Hierarchical Self-Supervised Representation Learning for Movie Understanding

ScaleDet: A Scalable Multi-Dataset Object Detector

Self-Supervised Multi-Object Tracking with Path Consistency

MaCLR: Motion-Aware Contrastive Learning of Representations for Videos

Hyperbolic Learning with Synthetic Captions for Open-World Detection

Selective Feature Compression for Efficient Activity Recognition Inference

Enhancing Numerical Prediction of MLLMs with Soft Labeling

SkeleTR: Towards Skeleton-based Action Recognition in the Wild