research
∙
08/17/2023
EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding
We introduce EgoSchema, a very long-form video question-answering datase...
share
research
∙
06/15/2023
PaReprop: Fast Parallelized Reversible Backpropagation
The growing size of datasets and deep learning models has made faster an...
research
∙
04/06/2023
Diffusion Models as Masked Autoencoders
There has been a longstanding belief that generation can facilitate a tr...
research
∙
02/15/2023
Big Little Transformer Decoder
The recent emergence of Large Language Models based on the Transformer a...
research
∙
11/25/2022
Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization
Temporal action localization (TAL) requires long-form reasoning to predi...
research
∙
06/15/2022
Structured Video Tokens @ Ego4D PNR Temporal Localization Challenge 2022
This technical report describes the SViT approach for the Ego4D Point of...
research
∙
06/13/2022
Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens
Recent action recognition models have achieved impressive results by int...
research
∙
06/02/2022
Squeezeformer: An Efficient Transformer for Automatic Speech Recognition
The recently proposed Conformer model has become the de facto backbone m...
research
∙
01/20/2022
MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition
While today's video recognition systems parse snapshots or short clips a...
research
∙
12/29/2021
Overcoming Mode Collapse with Adaptive Multi Adversarial Training
Generative Adversarial Networks (GANs) are a class of generative models ...
research
∙
12/02/2021
Improved Multiscale Vision Transformers for Classification and Detection
In this paper, we study Multiscale Vision Transformers (MViT) as a unifi...
research
∙
10/13/2021
Object-Region Video Transformers
Evidence from cognitive psychology suggests that understanding spatio-te...
research
∙
04/22/2021
Multiscale Vision Transformers
We present Multiscale Vision Transformers (MViT) for video and image rec...
research
∙
12/02/2020
From Goals, Waypoints Paths To Long Term Human Trajectory Forecasting
Human trajectory forecasting is an inherently multi-modal problem. Uncer...
research
∙
07/07/2020
Long-term Human Motion Prediction with Scene Context
Human movement is goal-directed and influenced by the spatial layout of ...
research
∙
11/04/2019
Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision
We tackle the problem of Human Locomotion Forecasting, a task for jointl...
research
∙
12/01/2018
On Compressing U-net Using Knowledge Distillation
We study the use of knowledge distillation to compress the U-net archite...
research
∙
12/12/2017
Learning Spontaneity to Improve Emotion Recognition In Speech
We investigate the effect and usefulness of spontaneity in speech (i.e. ...
research
∙
11/30/2017
Future Person Localization in First-Person Videos
We present a new task that predicts future locations of people observed ...
research
∙
05/19/2017