research
∙
06/01/2023
Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
Modern hierarchical vision transformers have added several vision-specif...
share
research
∙
04/06/2023
Diffusion Models as Masked Autoencoders
There has been a longstanding belief that generation can facilitate a tr...
research
∙
04/03/2023
On the Benefits of 3D Pose and Tracking for Human Action Recognition
In this work we study the benefits of using tracking and 3D poses for ac...
research
∙
03/23/2023
The effectiveness of MAE pre-pretraining for billion-scale pretraining
This paper revisits the standard pretrain-then-finetune paradigm used in...
research
∙
01/19/2023
Multiview Compressive Coding for 3D Reconstruction
A central goal of visual recognition is to understand objects and scenes...
research
∙
01/05/2023
CiT: Curation in Training for Effective Vision-Language Data
Large vision-language models are generally applicable to many downstream...
research
∙
12/15/2022
MAViL: Masked Audio-Video Learners
We present Masked Audio-Video Learners (MAViL) to train audio-visual rep...
research
∙
12/01/2022
Scaling Language-Image Pre-training via Masking
We present Fast Language-Image Pre-training (FLIP), a simple and more ef...
research
∙
10/17/2022
Token Merging: Your ViT But Faster
We introduce Token Merging (ToMe), a simple method to increase the throu...
research
∙
07/13/2022
Masked Autoencoders that Listen
This paper studies a simple extension of image-based Masked Autoencoders...
research
∙
05/18/2022
Masked Autoencoders As Spatiotemporal Learners
This paper studies a conceptually simple extension of Masked Autoencoder...
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
∙
01/10/2022
A ConvNet for the 2020s
The "Roaring 20s" of visual recognition began with the introduction of V...
research
∙
12/16/2021
Masked Feature Prediction for Self-Supervised Visual Pre-Training
We present Masked Feature Prediction (MaskFeat) for self-supervised pre-...
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
∙
11/18/2021
PyTorchVideo: A Deep Learning Library for Video Understanding
We introduce PyTorchVideo, an open-source deep-learning library that pro...
research
∙
09/28/2021
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding
We present VideoCLIP, a contrastive approach to pre-train a unified mode...
research
∙
06/09/2021
Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers
In video transformers, the time dimension is often treated in the same w...
research
∙
05/20/2021
VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding
We present a simplified, task-agnostic multi-modal pre-training approach...
research
∙
04/29/2021
A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
We present a large-scale study on unsupervised spatiotemporal representa...
research
∙
04/22/2021
Multiscale Vision Transformers
We present Multiscale Vision Transformers (MViT) for video and image rec...
research
∙
04/01/2021
Multiview Pseudo-Labeling for Semi-supervised Learning from Video
We present a multiview pseudo-labeling approach to video learning, a nov...
research
∙
01/07/2021
TrackFormer: Multi-Object Tracking with Transformers
We present TrackFormer, an end-to-end multi-object tracking and segmenta...
research
∙
04/09/2020
X3D: Expanding Architectures for Efficient Video Recognition
This paper presents X3D, a family of efficient video networks that progr...
research
∙
04/07/2020
Feature Pyramid Grids
Feature pyramid networks have been widely adopted in the object detectio...
research
∙
01/23/2020
Audiovisual SlowFast Networks for Video Recognition
We present Audiovisual SlowFast Networks, an architecture for integrated...
research
∙
01/14/2020
EGO-TOPO: Environment Affordances from Egocentric Video
First-person video naturally brings the use of a physical environment to...
research
∙
12/02/2019
A Multigrid Method for Efficiently Training Video Models
Training competitive deep video models is an order of magnitude slower t...
research
∙
06/06/2019
Learning Temporal Pose Estimation from Sparsely-Labeled Videos
Modern approaches for multi-person pose estimation in video require larg...
research
∙
06/03/2019
Grounded Human-Object Interaction Hotspots from Video (Extended Abstract)
Learning how to interact with objects is an important step towards embod...
research
∙
01/21/2019
Modeling Human Motion with Quaternion-based Neural Networks
Previous work on predicting or generating 3D human pose sequences regres...
research
∙
12/12/2018
Long-Term Feature Banks for Detailed Video Understanding
To understand the world, we humans constantly need to relate the present...
research
∙
12/11/2018
Grounded Human-Object Interaction Hotspots from Video
Learning how to interact with objects is an important step towards embod...
research
∙
12/11/2018
Learning Discriminative Motion Features Through Detection
Despite huge success in the image domain, modern detection models such a...
research
∙
12/10/2018
SlowFast Networks for Video Recognition
We present SlowFast networks for video recognition. Our model involves (...
research
∙
11/28/2018
3D human pose estimation in video with temporal convolutions and semi-supervised training
In this work, we demonstrate that 3D poses in video can be effectively e...
research
∙
02/20/2018
Camera-based vehicle velocity estimation from monocular video
This paper documents the winning entry at the CVPR2017 vehicle velocity ...
research
∙
01/04/2018
What have we learned from deep representations for action recognition?
As the success of deep models has led to their deployment in all areas o...
research
∙
10/11/2017
Detect to Track and Track to Detect
Recent approaches for high accuracy detection and tracking of object cat...
research
∙
11/07/2016
Spatiotemporal Residual Networks for Video Action Recognition
Two-stream Convolutional Networks (ConvNets) have shown strong performan...
research
∙
04/22/2016