activity
20142024
most citedDeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection

13 citations · 16 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV2024

Semantic Compositions Enhance Vision-Language Contrastive Learning

Maxwell Aladago, Lorenzo Torresani, Soroush Vosoughi

In the field of vision-language contrastive learning, models such as CLIP capitalize on matched image-caption pairs as positive examples and leverage within-batch non-matching pair…

cs.CV2023

Multiscale Video Pretraining for Long-Term Activity Forecasting

Reuben Tan, Matthias De Lange, Michael Iuzzolino +4

Long-term activity forecasting is an especially challenging research problem because it requires understanding the temporal relationships between observed actions, as well as the v…

cs.CV20231 cited

Learning to Ground Instructional Articles in Videos through Narrations

Effrosyni Mavroudi, Triantafyllos Afouras, Lorenzo Torresani

In this paper we present an approach for localizing steps of procedural activities in narrated how-to videos. To deal with the scarcity of labeled data at scale, we source the step…

cs.CV20231 cited

MINOTAUR: Multi-task Video Grounding From Multimodal Queries

Raghav Goyal, Effrosyni Mavroudi, Xitong Yang +5

Video understanding tasks take many forms, from action detection to visual query localization and spatio-temporal grounding of sentences. These tasks differ in the type of inputs (…

cs.CV20231 cited

Egocentric Video Task Translation @ Ego4D Challenge 2022

Zihui Xue, Yale Song, Kristen Grauman +1

This technical report describes the EgoTask Translation approach that explores relations among a set of egocentric video tasks in the Ego4D challenge. To improve the primary task o…

cs.CV201413 cited

DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection

Gedas Bertasius, Jianbo Shi, Lorenzo Torresani

Contour detection has been a fundamental component in many image segmentation and object detection systems. Most previous work utilizes low-level features such as texture or salien…