Lorenzo Torresani

8

Papers

134

Total Citations

Papers (8)

Video ReCap: Recursive Captioning of Hour-Long Videos

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

NeurIPS 2025arXiv

Step Differences in Instructional Video

VITED: Video Temporal Evidence Distillation

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

Enrich and Detect: Video Temporal Grounding with Multimodal LLMs

Learning to Segment Referred Objects from Narrated Egocentric Videos

BIMBA: Selective-Scan Compression for Long-Range Video Question Answering