3.1k citations · 3.1k across the 6 of their papers we have counts for
7 papers
Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions
Mathew Monfort, SouYoung Jin, Alexander Liu +4
When people observe events, they are able to abstract key information and build concise summaries of what is happening. These summaries include contextual and semantic information…
We Have So Much In Common: Modeling Semantic Relational Set Abstractions in Videos
Alex Andonian, Camilo Fosco, Mathew Monfort +4
Identifying common patterns among events is a key ability in human and machine perception, as it underlies intelligent decision making. We propose an approach for learning semantic…
Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding
Mathew Monfort, Bowen Pan, Kandan Ramakrishnan +7
Videos capture events that typically contain multiple sequential, and simultaneous, actions even in the span of only a few seconds. However, most large-scale datasets built to trai…
Reasoning About Human-Object Interactions Through Dual Attention Networks
Tete Xiao, Quanfu Fan, Dan Gutfreund +3
Objects are entities we act upon, where the functionality of an object is determined by how we interact with it. In this work we propose a Dual Attention Network model which reason…
Multi-Agent Tensor Fusion for Contextual Trajectory Prediction
Tianyang Zhao, Yifei Xu, Mathew Monfort +5
Accurate prediction of others' trajectories is essential for autonomous driving. Trajectory prediction is challenging because it requires reasoning about agents' past movements, so…
Moments in Time Dataset: one million videos for event understanding
Mathew Monfort, Alex Andonian, Bolei Zhou +8
We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds. Modelin…
End to End Learning for Self-Driving Cars
Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski +10
We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powe…