recent news


  1. Two papers to be presented at NeurIPS 2023:

  2. Ego4D Goal-Step: Toward Hierarchical Understanding of Procedural Activities,
    with Yale Song, Gene Byrne, Tushar Nagarajan, Huiyu Wang, and Miguel Martin. Accepted as spotlight.

  3. HT-Step: Aligning Instructional Articles with How-To Videos,
    with Triantafyllos Afouras, Effrosyni Mavroudi, Tushar Nagarajan, and Huiyu Wang. 


  1. Two papers presented at ICCV 2023:

  2. Ego-Only: Egocentric Action Detection without Exocentric Transferring,
    with Huiyu Wang, and Mitesh Kumar Singh. 

  3. Learning to Ground Instructional Articles in Videos through Narrations,
    with Effrosyni Mavroudi, and Triantafyllos Afouras. 


  1. Three papers presented at CVPR 2023 as highlights (10% of accepted papers, 2.6% of submitted papers):

  2. Egocentric Video Task Translation,
    with Zihui Xue, Yale Song, and Kristen Grauman. 

  3. HierVL: Learning Hierarchical Video-Language Embeddings,
    with Kumar Ashutosh, Rohit Girdhar, and Kristen Grauman.

  4. Relational Space-Time Query in Long-Form Videos,
    with Xitong Yang, Fu-Jen Chu, Raghav Goyal, Matt Feiszli, and Du Tran.



research overview


My research interests are in computer vision and machine learning. My current work is primarily focused on multimodal learning and video understanding.



previous affiliations


  1. Dartmouth, Computer Science

  2. Fulbright U.S. Scholar at Ashesi University in Ghana.

  3. Microsoft Research Cambridge, Machine Learning and Perception

  4. Riya/Like.com

  5. New York University, Computer Science

  6. Stanford University, Computer Science

  7. DigitalPersona

  8. IRST

  9. University of Milan, Computer Science

Lorenzo Torresani


Research Director

Facebook AI Research (FAIR), Meta


Email / Google Scholar