Lorenzo Torresani

research

∙ 07/24/2023

Multiscale Video Pretraining for Long-Term Activity Forecasting

Long-term activity forecasting is an especially challenging research pro...

0 Reuben Tan, et al. ∙

research

∙ 06/06/2023

Learning to Ground Instructional Articles in Videos through Narrations

In this paper we present an approach for localizing steps of procedural ...

0 Effrosyni Mavroudi, et al. ∙

research

∙ 03/09/2023

Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervision

Many top-down architectures for instance segmentation achieve significan...

3 Tarun Kalluri, et al. ∙

research

∙ 02/16/2023

MINOTAUR: Multi-task Video Grounding From Multimodal Queries

Video understanding tasks take many forms, from action detection to visu...

0 Raghav Goyal, et al. ∙

research

∙ 02/03/2023

Egocentric Video Task Translation @ Ego4D Challenge 2022

This technical report describes the EgoTask Translation approach that ex...

0 Zihui Xue, et al. ∙

research

∙ 01/05/2023

HierVL: Learning Hierarchical Video-Language Embeddings

Video-language embeddings are a promising avenue for injecting semantics...

0 Kumar Ashutosh, et al. ∙

research

∙ 01/05/2023

What You Say Is What You Show: Visual Narration Detection in Instructional Videos

Narrated "how-to" videos have emerged as a promising data source for a w...

0 Kumar Ashutosh, et al. ∙

research

∙ 01/03/2023

Ego-Only: Egocentric Action Detection without Exocentric Pretraining

We present Ego-Only, the first training pipeline that enables state-of-t...

0 Huiyu Wang, et al. ∙

research

∙ 12/13/2022

Egocentric Video Task Translation

Different video understanding tasks are typically treated in isolation, ...

0 Zihui Xue, et al. ∙

research

∙ 09/13/2022

HistoPerm: A Permutation-Based View Generation Approach for Learning Histopathologic Feature Representations

Recently, deep learning methods have been successfully applied to solve ...

0 Joseph DiPalma, et al. ∙

research

∙ 03/31/2022

Deformable Video Transformer

Video transformers have recently emerged as an effective alternative to ...

0 Jue Wang, et al. ∙

research

∙ 01/28/2022

Calibrating Histopathology Image Classifiers using Label Smoothing

The classification of histopathology images fundamentally differs from t...

0 Jerry Wei, et al. ∙

research

∙ 01/26/2022

Learning To Recognize Procedural Activities with Distant Supervision

In this paper we consider the problem of classifying fine-grained, multi...

1 Xudong Lin, et al. ∙

research

∙ 12/06/2021

Label Hallucination for Few-Shot Classification

Few-shot classification requires adapting knowledge learned from a large...

0 Yiren Jian, et al. ∙

research

∙ 06/17/2021

Long-Short Temporal Contrastive Learning of Video Transformers

Video transformers have recently emerged as a competitive alternative to...

0 Jue Wang, et al. ∙

research

∙ 04/02/2021

Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories

The standard way of training video models entails sampling at each itera...

0 Xitong Yang, et al. ∙

research

∙ 02/11/2021

A Multi-View Approach To Audio-Visual Speaker Verification

Although speaker verification has conventionally been an audio-only task...

0 Leda Sarı, et al. ∙

research

∙ 02/09/2021

Is Space-Time Attention All You Need for Video Understanding?

We present a convolution-free approach to video classification built exc...

0 Gedas Bertasius, et al. ∙

research

∙ 01/29/2021

A Petri Dish for Histopathology Image Analysis

With the rise of deep learning, there has been increased interest in usi...

0 Jerry Wei, et al. ∙

research

∙ 01/28/2021

VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs

We present Vx2Text, a framework for text generation from multimodal inpu...

6 Xudong Lin, et al. ∙

research

∙ 01/16/2021

Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks

In contrast to traditional weight optimization in a continuous space, we...

0 Maxwell Mbabilla Aladago, et al. ∙

research

∙ 01/11/2021

Resolution-Based Distillation for Efficient Histology Image Classification

Developing deep learning models to analyze histology images has been com...

0 Joseph DiPalma, et al. ∙

research

∙ 09/29/2020

Learn like a Pathologist: Curriculum Learning by Annotator Agreement for Histopathology Image Classification

Applying curriculum learning requires both a range of difficulty in data...

0 Jerry Wei, et al. ∙

research

∙ 07/14/2020

COBE: Contextualized Object Embeddings from Narrated Instructional Video

Many objects in the real world undergo dramatic variations in visual app...

1 Gedas Bertasius, et al. ∙

research

∙ 07/09/2020

Generalized Many-Way Few-Shot Video Classification

Few-shot learning methods operate in low data regimes. The aim is to lea...

14 Yongqin Xian, et al. ∙

research

∙ 06/12/2020

Video Understanding as Machine Translation

With the advent of large-scale multimodal video datasets, especially seq...

11 Bruno Korbar, et al. ∙

research

∙ 03/01/2020

Stein Variational Inference for Discrete Distributions

Gradient-based approximate inference methods, such as Stein variational ...

15 Jun Han, et al. ∙

research

∙ 12/10/2019

Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation

We introduce a method for simultaneously classifying, segmenting and tra...

26 Gedas Bertasius, et al. ∙

research

∙ 12/10/2019

Listen to Look: Action Recognition by Previewing Audio

In the face of the video data deluge, today's expensive clip-level class...

9 Ruohan Gao, et al. ∙

research

∙ 11/28/2019

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

The visual and audio modalities are highly correlated yet they contain d...

25 Humam Alwassel, et al. ∙

research

∙ 07/19/2019

Only Time Can Tell: Discovering Temporal Data for Temporal Modeling

Understanding temporal information and how the visual world changes over...

1 Laura Sevilla-Lara, et al. ∙

research

∙ 06/10/2019

UniDual: A Unified Model for Image and Video Understanding

Although a video is effectively a sequence of images, visual perception ...

4 Yufei Wang, et al. ∙

research

∙ 06/07/2019

Video Modeling with Correlation Networks

Motion is a salient cue to recognize actions in video. Modern action rec...

0 Heng Wang, et al. ∙

research

∙ 06/06/2019

Learning Temporal Pose Estimation from Sparsely-Labeled Videos

Modern approaches for multi-person pose estimation in video require larg...

0 Gedas Bertasius, et al. ∙

research

∙ 04/10/2019

Attentive Action and Context Factorization

We propose a method for human action recognition, one that can localize ...

0 Yang Wang, et al. ∙

research

∙ 04/08/2019

SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition

While many action recognition datasets consist of collections of brief, ...

0 Bruno Korbar, et al. ∙

research

∙ 04/04/2019

Video Classification with Channel-Separated Convolutional Networks

Group convolution has been shown to offer great computational savings in...

0 Du Tran, et al. ∙

research

∙ 01/26/2019

DistInit: Learning Video Representations without a Single Labeled Video

Video recognition models have progressed significantly over the past few...

0 Rohit Girdhar, et al. ∙

research

∙ 12/11/2018

Learning Discriminative Motion Features Through Detection

Despite huge success in the image domain, modern detection models such a...

0 Gedas Bertasius, et al. ∙

research

∙ 07/28/2018

MaskConnect: Connectivity Learning by Gradient Descent

Although deep networks have recently emerged as the model of choice for ...

0 Karim Ahmed, et al. ∙

research

∙ 06/30/2018

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

There is a natural correlation between the visual and auditive elements ...

0 Bruno Korbar, et al. ∙

research

∙ 03/15/2018

Object Detection in Video with Spatiotemporal Sampling Networks

We propose a Spatiotemporal Sampling Network (STSN) that uses deformable...

0 Gedas Bertasius, et al. ∙

research

∙ 12/26/2017

SLAC: A Sparsely Labeled Dataset for Action Classification and Localization

This paper describes a procedure for the creation of large-scale video d...

0 Hang Zhao, et al. ∙

research

∙ 12/26/2017

Detect-and-Track: Efficient Pose Estimation in Videos

This paper addresses the problem of estimating and tracking human body k...

0 Rohit Girdhar, et al. ∙

research

∙ 11/30/2017

A Closer Look at Spatiotemporal Convolutions for Action Recognition

In this paper we discuss several forms of spatiotemporal convolutions fo...

0 Du Tran, et al. ∙

research

∙ 09/27/2017

Connectivity Learning in Multi-Branch Networks

While much of the work in the design of convolutional networks over the ...

0 Karim Ahmed, et al. ∙

research

∙ 09/26/2017

Learning to Inpaint for Image Compression

We study the design of deep architectures for lossy image compression. W...

0 Mohammad Haris Baig, et al. ∙

research

∙ 03/05/2017

Deep-Learning for Classification of Colorectal Polyps on Whole-Slide Images

Histopathological characterization of colorectal polyps is an important ...

0 Bruno Korbar, et al. ∙

research

∙ 06/23/2016

VideoMCC: a New Benchmark for Video Comprehension

While there is overall agreement that future technology for organizing, ...

0 Du Tran, et al. ∙

research

∙ 06/20/2016

Multiple Hypothesis Colorization

In this work we focus on the problem of colorization for image compressi...

0 Mohammad Haris Baig, et al. ∙

Lorenzo Torresani

Featured Co-authors