b'Du Tran'

Long-Short Temporal Contrastive Learning of Video Transformers

Video transformers have recently emerged as a competitive alternative to...
06/17/2021 ∙ by Jue Wang, et al. ∙ 0 ∙ share

read it
Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation

Current state-of-the-art object detection and segmentation methods work ...
04/10/2021 ∙ by Weiyao Wang, et al. ∙ 0 ∙ share

read it
FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation

A majority of approaches solve the problem of video frame interpolation ...
12/15/2020 ∙ by Tarun Kalluri, et al. ∙ 7 ∙ share

read it
Self-Supervised Learning by Cross-Modal Audio-Video Clustering

The visual and audio modalities are highly correlated yet they contain d...
11/28/2019 ∙ by Humam Alwassel, et al. ∙ 25 ∙ share

read it
FASTER Recurrent Networks for Video Classification

Video classification methods often divide the video into short clips, do...
06/10/2019 ∙ by Linchao Zhu, et al. ∙ 0 ∙ share

read it
UniDual: A Unified Model for Image and Video Understanding

Although a video is effectively a sequence of images, visual perception ...
06/10/2019 ∙ by Yufei Wang, et al. ∙ 4 ∙ share

read it
Video Modeling with Correlation Networks

Motion is a salient cue to recognize actions in video. Modern action rec...
06/07/2019 ∙ by Heng Wang, et al. ∙ 0 ∙ share

read it
Learning Temporal Pose Estimation from Sparsely-Labeled Videos

Modern approaches for multi-person pose estimation in video require larg...
06/06/2019 ∙ by Gedas Bertasius, et al. ∙ 0 ∙ share

read it
What Makes Training Multi-Modal Networks Hard?

Consider end-to-end training of a multi-modal vs. a single-modal network...
05/29/2019 ∙ by Weiyao Wang, et al. ∙ 0 ∙ share

read it
Large-scale weakly-supervised pre-training for video action recognition

Current fully-supervised video datasets consist of only a few hundred th...
05/02/2019 ∙ by Deepti Ghadiyaram, et al. ∙ 0 ∙ share

read it
SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition

While many action recognition datasets consist of collections of brief, ...
04/08/2019 ∙ by Bruno Korbar, et al. ∙ 0 ∙ share

read it
Video Classification with Channel-Separated Convolutional Networks

Group convolution has been shown to offer great computational savings in...
04/04/2019 ∙ by Du Tran, et al. ∙ 0 ∙ share

read it
DistInit: Learning Video Representations without a Single Labeled Video

Video recognition models have progressed significantly over the past few...
01/26/2019 ∙ by Rohit Girdhar, et al. ∙ 0 ∙ share

read it
Learning Discriminative Motion Features Through Detection

Despite huge success in the image domain, modern detection models such a...
12/11/2018 ∙ by Gedas Bertasius, et al. ∙ 0 ∙ share

read it
Co-Training of Audio and Video Representations from Self-Supervised Temporal Synchronization

There is a natural correlation between the visual and auditive elements ...
06/30/2018 ∙ by Bruno Korbar, et al. ∙ 0 ∙ share

read it
Detect-and-Track: Efficient Pose Estimation in Videos

This paper addresses the problem of estimating and tracking human body k...
12/26/2017 ∙ by Rohit Girdhar, et al. ∙ 0 ∙ share

read it
A Closer Look at Spatiotemporal Convolutions for Action Recognition

In this paper we discuss several forms of spatiotemporal convolutions fo...
11/30/2017 ∙ by Du Tran, et al. ∙ 0 ∙ share

read it
Transformation-Based Models of Video Sequences

In this work we propose a simple unsupervised approach for next frame pr...
01/29/2017 ∙ by Joost van Amersfoort, et al. ∙ 0 ∙ share

read it
VideoMCC: a New Benchmark for Video Comprehension

While there is overall agreement that future technology for organizing, ...
06/23/2016 ∙ by Du Tran, et al. ∙ 0 ∙ share

read it
Learning Spatiotemporal Features with 3D Convolutional Networks

We propose a simple, yet effective approach for spatiotemporal feature l...
12/02/2014 ∙ by Du Tran, et al. ∙ 0 ∙ share

read it
EXMOVES: Classifier-based Features for Scalable Action Recognition

This paper introduces EXMOVES, learned exemplar-based features for effic...
12/20/2013 ∙ by Du Tran, et al. ∙ 0 ∙ share

read it

Du Tran

Featured Co-authors

Yi Yang

Yann LeCun

Bernard Ghanem

Deva Ramanan

Arthur Szlam

Jue Wang

Manmohan Chandraker

Lorenzo Torresani

Marc'Aurelio Ranzato

Rob Fergus

Jianbo Shi

Long-Short Temporal Contrastive Learning of Video Transformers

Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation

FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation

Self-Supervised Learning by Cross-Modal Audio-Video Clustering

FASTER Recurrent Networks for Video Classification

UniDual: A Unified Model for Image and Video Understanding

Video Modeling with Correlation Networks

Learning Temporal Pose Estimation from Sparsely-Labeled Videos

What Makes Training Multi-Modal Networks Hard?

Large-scale weakly-supervised pre-training for video action recognition

SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition

Video Classification with Channel-Separated Convolutional Networks

DistInit: Learning Video Representations without a Single Labeled Video

Learning Discriminative Motion Features Through Detection

Co-Training of Audio and Video Representations from Self-Supervised Temporal Synchronization

Detect-and-Track: Efficient Pose Estimation in Videos

A Closer Look at Spatiotemporal Convolutions for Action Recognition

Transformation-Based Models of Video Sequences

VideoMCC: a New Benchmark for Video Comprehension

Learning Spatiotemporal Features with 3D Convolutional Networks

EXMOVES: Classifier-based Features for Scalable Action Recognition