Publications

The Llama 3 Herd of Models

State-of-the-Art open-source LLM with multimodal capabilities

Llama3 team (co-lead the video recognition efforts)

The Llama 3 Herd of Models

SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos

Self-supervised embedding to learn how actions sound from narrated in-the-wild egocentric videos.

Changan Chen, Ashutosh Kumar, Rohit Girdhar, David Harwath, Kristen Grauman

InstanceDiffusion: Instance-level Control for Image Generation

SOTA instance-conditioned diffusion model for image generation.

Xudong Wang, Trevor Darrell, Sai Saketh Rambhatla, Rohit Girdhar, Ishan Misra

InstanceDiffusion: Instance-level Control for Image Generation

Generating Illustrated Instructions

Introducing a new task of generating instructions for the task you want to solve with illustrations, and a LLM + Diffusion model based solution.

Sachit Menon, Ishan Misra, Rohit Girdhar

Generating Illustrated Instructions

VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation

SOTA unsupervised video segmentation using CutLER.

Xudong Wang, Ishan Misra, Ziyun Zeng, Rohit Girdhar, Trevor Darrell

Motion-Conditioned Image Animation for Video Editing

Image animation FTW again! SOTA video editing results by animating the first frame with motion conditioning.

Wilson Yan, Andrew Brown, Pieter Abbeel, Rohit Girdhar, Samaneh Azadi

Motion-Conditioned Image Animation for Video Editing

Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning

A simple and effective approach to high-quality video generation by learning to animate high quality images.

Rohit Girdhar, Mannat Singh, Andrew Brown, Quentin Duval, Samaneh Azadi, Sai Saketh Rambhatla, Akbar Shah, Xi Yin, Devi Parikh, Ishan Misra

Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning

ImageBind: One Embedding Space To Bind Them All

One embedding space for 6 different modalities, enables zero-shot recognition on all modalities!

Rohit Girdhar, Alaaeldin El-Nouby, Zhuang Liu, Mannat Singh, Kalyan Vasudev Alwala, Armand Joulin, Ishan Misra

ImageBind: One Embedding Space To Bind Them All

The effectiveness of MAE pre-pretraining for billion-scale pretraining

Scaling up MAE pre-pretraining, followed by weakly supervised pretraining, leads to strong representations.

Mannat Singh, Quentin Duval, Kalyan Vasudev Alwala, Haoqi Fan, Vaibhav Aggarwal, Aaron Adcock, Armand Joulin, Piotr Dollár, Christoph Feichtenhofer, Ross Girshick, Rohit Girdhar, Ishan Misra

The effectiveness of MAE pre-pretraining for billion-scale pretraining

CutLER: Cut and Learn for Unsupervised Object Detection and Instance Segmentation

Discovering objects using DINO features, and learning an unsupervised detection + segmentation model

Xudong Wang, Rohit Girdhar, Stella X. Yu, Ishan Misra

HierVL: Learning Hierarchical Video-Language Embeddings

Video-language embeddings are a promising avenue for injecting semantics into visual representations, but existing methods capture only short-term associations between seconds-long video clips and their accompanying text. We propose HierVL, a novel hierarchical video-language embedding that simultaneously accounts for both long-term and short-term associations.

Kumar Ashutosh, Rohit Girdhar, Lorenzo Torresani, Kristen Grauman

HierVL: Learning Hierarchical Video-Language Embeddings

Learning Video Representations from Large Language Models

Leveraging LLMs to auto-annotate videos for representation learning.

Yue Zhao, Ishan Misra, Philipp Krähenbühl, Rohit Girdhar

Learning Video Representations from Large Language Models

Omnivore: A Single Model for Many Visual Modalities

A single model for images, video and single-view 3D.

Rohit Girdhar, Mannat Singh, Nikhila Ravi, Laurens van der Maaten, Armand Joulin, Ishan Misra

OmniMAE: Single Model Masked Pretraining on Images and Videos

Single self-supervised representation for images and videos.

Rohit Girdhar, Alaaeldin El-Nouby, Mannat Singh, Kalyan Vasudev Alwala, Armand Joulin, Ishan Misra

Ego4D: Around the World in 3,000 Hours of Egocentric Video

The largest egocentric video dataset.

Kristen Grauman, Andrew Westbury, Rohit Girdhar, et al

Ego4D: Around the World in 3,000 Hours of Egocentric Video

Detecting Twenty-thousand Classes using Image-level Supervision

Leverages image classification data to build an object detector

Xingyi Zhou, Rohit Girdhar, Armand Joulin, Philipp Krähenbühl, Ishan Misra

Detecting Twenty-thousand Classes using Image-level Supervision

Mask2Former for Video Instance Segmentation

SOTA video segmentation using Mask2Former.

Bowen Cheng, Anwesa Choudhuri, Ishan Misra, Alexander Kirillov, Rohit Girdhar, Alexander G. Schwing

Mask2Former for Video Instance Segmentation

Masked-attention Mask Transformer for Universal Image Segmentation

Single architecture state-of-the-art in instance, semantic and panoptic segmentation.

Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar

Masked-attention Mask Transformer for Universal Image Segmentation

3DETR: An End-to-End Transformer Model for 3D Object Detection

First Transformer based detection architecture for 3D data.

Ishan Misra, Rohit Girdhar, Armand Joulin

Anticipative Video Transformer

An autoregressive video transformer architecture for action anticipation in videos.

Rohit Girdhar, Kristen Grauman

Anticipative Video Transformer

Self-Supervised Pretraining of 3D Features on any Point-Cloud

SOTA 3D detection/segmentation results by learning contrastive representations on 3D data

Zaiwei Zhang, Rohit Girdhar, Armand Joulin, Ishan Misra

3D Spatial Recognition without Spatially Labeled 3D

WyPR can detect and segment objects in a 3D scene without needing any spatial labels at all!

Zhongzheng Ren, Ishan Misra, Alexander G. Schwing, Rohit Girdhar

Physical Reasoning Using Dynamics Aware Embeddings

Self-supervised representations for physical reasoning.

Eltayeb Ahmed, Anton Bakhtin, Laurens van der Maaten, Rohit Girdhar

Forward Prediction for Physical Reasoning

Forward prediction for PHYRE benchmark.

Rohit Girdhar, Laura Gustafson, Aaron Adcock, Laurens van der Maaten

Forward Prediction for Physical Reasoning

MetaPix: Few-Shot Video Retargeting

A dataset to evaluate temporal reasoning in video models.

Jessica Lee, Deva Ramanan, Rohit Girdhar

MetaPix: Few-Shot Video Retargeting

CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning

A dataset to evaluate temporal reasoning in video models.

Rohit Girdhar, Deva Ramanan

CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning

DistInit: Learning Video Representations Without a Single Labeled Video

Distilling representations from image models to video models.

Rohit Girdhar, Du Tran, Lorenzo Torresani, Deva Ramanan

DistInit: Learning Video Representations Without a Single Labeled Video

Video Action Transformer Network

Among the first applications of Transformers to model videos. SOTA results: close 2nd at AVA Challenge, CVPR'18.

Rohit Girdhar, João Carreira, Carl Doersch, Andrew Zisserman

Detect-and-Track: Efficient Pose Estimation in Videos

Human keypoint tracking approach that ranked first in ICCV 2017 PoseTrack keypoint tracking challenge!

Rohit Girdhar, Georgia Gkioxari, Lorenzo Torresani, Manohar Paluri, Du Tran

Detect-and-Track: Efficient Pose Estimation in Videos

Attentional Pooling for Action Recognition

Among the first applications of attention for contemporary video/action understanding.

Rohit Girdhar, Deva Ramanan

Attentional Pooling for Action Recognition

ActionVLAD: Learning spatio-temporal aggregation for action classification

Aggregating visual features for action recognition.

Rohit Girdhar, Deva Ramanan, Abhinav Gupta, Josef Sivic, Bryan Russell

ActionVLAD: Learning spatio-temporal aggregation for action classification

Learning a Predictable and Generative Vector Representation for Objects

A single embedding space, good for both generating and understanding 3D models

Rohit Girdhar, David F. Fouhey, Mikel Rodriguez, Abhinav Gupta

Binge Watching: Scaling Affordance Learning from Sitcoms

Learning how humans interact with their environment by watching TV.

Xiaolong Wang, Rohit Girdhar, Abhinav Gupta

Binge Watching: Scaling Affordance Learning from Sitcoms