1.5k citations · 3.1k across the 62 of their papers we have counts for
7 papers · 1 filter
HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization
Hang Zhao, Antonio Torralba, Lorenzo Torresani +1
This paper presents a new large-scale dataset for recognition and temporal localization of human actions collected from Web videos. We refer to it as HACS (Human Action Clips and S…
Detect-and-Track: Efficient Pose Estimation in Videos
Rohit Girdhar, Georgia Gkioxari, Lorenzo Torresani +2
This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video. We propose an extremely lightweight yet highly effective approach t…
A Closer Look at Spatiotemporal Convolutions for Action Recognition
Du Tran, Heng Wang, Lorenzo Torresani +3
In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition. Our motivation stems from the observation th…
Connectivity Learning in Multi-Branch Networks
Karim Ahmed, Lorenzo Torresani
While much of the work in the design of convolutional networks over the last five years has revolved around the empirical investigation of the importance of depth, filter sizes, an…
Learning to Inpaint for Image Compression
Mohammad Haris Baig, Vladlen Koltun, Lorenzo Torresani
We study the design of deep architectures for lossy image compression. We present two architectural recipes in the context of multi-stage progressive encoders and empirically demon…
Deep-Learning for Classification of Colorectal Polyps on Whole-Slide Images
Bruno Korbar, Andrea M. Olofson, Allen P. Miraflor +5
Histopathological characterization of colorectal polyps is an important principle for determining the risk of colorectal cancer and future rates of surveillance for patients. This…
BranchConnect: Large-Scale Visual Recognition with Learned Branch Connections
Karim Ahmed, Lorenzo Torresani
We introduce an architecture for large-scale image categorization that enables the end-to-end learning of separate visual features for the different classes to distinguish. The pro…