activity
20162021
most citedVideoLSTM Convolves, Attends and Flows for Action Recognition

64 citations · 66 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CV2021

Motion-Augmented Self-Training for Video Recognition at Smaller Scale

Kirill Gavrilyuk, Mihir Jain, Ilia Karmanov +1

The goal of this paper is to self-train a 3D convolutional neural network on an unlabeled video collection for deployment on small-scale video collections. As smaller video dataset…

cs.CV2020

Actor-Transformers for Group Activity Recognition

Kirill Gavrilyuk, Ryan Sanford, Mehrsan Javan +1

This paper strives to recognize individual actions and group activities from videos. While existing solutions for this challenging problem explicitly model spatial and temporal rel…

cs.CV2020

Cloth in the Wind: A Case Study of Physical Measurement through Simulation

Tom F. H. Runia, Kirill Gavrilyuk, Cees G. M. Snoek +1

For many of the physical phenomena around us, we have developed sophisticated models explaining their behavior. Nevertheless, measuring physical properties from visual observations…

cs.CV20192 cited

Go with the Flow: Perception-refined Physics Simulation

Tom F. H. Runia, Kirill Gavrilyuk, Cees G. M. Snoek +1

For many of the physical phenomena around us, we have developed sophisticated models explaining their behavior. Nevertheless, inferring specifics from visual observations is challe…

cs.CV2018

Actor and Action Video Segmentation from a Sentence

Kirill Gavrilyuk, Amir Ghodrati, Zhenyang Li +1

This paper strives for pixel-level segmentation of actors and their actions in video content. Different from existing works, which all learn to segment from a fixed vocabulary of a…

cs.CV201664 cited

VideoLSTM Convolves, Attends and Flows for Action Recognition

Zhenyang Li, Efstratios Gavves, Mihir Jain +1

We present a new architecture for end-to-end sequence learning of actions in video, we call VideoLSTM. Rather than adapting the video to the peculiarities of established recurrent…