Alert button
Picture for Carl Doersch

Carl Doersch

Alert button

Derek

BootsTAP: Bootstrapped Training for Tracking-Any-Point

Feb 01, 2024
Carl Doersch, Yi Yang, Dilara Gokay, Pauline Luc, Skanda Koppula, Ankush Gupta, Joseph Heyward, Ross Goroshin, João Carreira, Andrew Zisserman

Viaarxiv icon

Learning from One Continuous Video Stream

Dec 01, 2023
João Carreira, Michael King, Viorica Pătrăucean, Dilara Gokay, Cătălin Ionescu, Yi Yang, Daniel Zoran, Joseph Heyward, Carl Doersch, Yusuf Aytar, Dima Damen, Andrew Zisserman

Figure 1 for Learning from One Continuous Video Stream
Figure 2 for Learning from One Continuous Video Stream
Figure 3 for Learning from One Continuous Video Stream
Figure 4 for Learning from One Continuous Video Stream
Viaarxiv icon

RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation

Aug 31, 2023
Mel Vecerik, Carl Doersch, Yi Yang, Todor Davchev, Yusuf Aytar, Guangyao Zhou, Raia Hadsell, Lourdes Agapito, Jon Scholz

Figure 1 for RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation
Figure 2 for RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation
Figure 3 for RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation
Figure 4 for RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation
Viaarxiv icon

TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement

Jun 14, 2023
Carl Doersch, Yi Yang, Mel Vecerik, Dilara Gokay, Ankush Gupta, Yusuf Aytar, Joao Carreira, Andrew Zisserman

Figure 1 for TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement
Figure 2 for TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement
Figure 3 for TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement
Figure 4 for TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement
Viaarxiv icon

Perception Test: A Diagnostic Benchmark for Multimodal Video Models

May 23, 2023
Viorica Pătrăucean, Lucas Smaira, Ankush Gupta, Adrià Recasens Continente, Larisa Markeeva, Dylan Banarse, Skanda Koppula, Joseph Heyward, Mateusz Malinowski, Yi Yang, Carl Doersch, Tatiana Matejovicova, Yury Sulsky, Antoine Miech, Alex Frechette, Hanna Klimczak, Raphael Koster, Junlin Zhang, Stephanie Winkler, Yusuf Aytar, Simon Osindero, Dima Damen, Andrew Zisserman, João Carreira

Figure 1 for Perception Test: A Diagnostic Benchmark for Multimodal Video Models
Figure 2 for Perception Test: A Diagnostic Benchmark for Multimodal Video Models
Figure 3 for Perception Test: A Diagnostic Benchmark for Multimodal Video Models
Figure 4 for Perception Test: A Diagnostic Benchmark for Multimodal Video Models
Viaarxiv icon

TAP-Vid: A Benchmark for Tracking Any Point in a Video

Nov 07, 2022
Carl Doersch, Ankush Gupta, Larisa Markeeva, Adrià Recasens, Lucas Smaira, Yusuf Aytar, João Carreira, Andrew Zisserman, Yi Yang

Figure 1 for TAP-Vid: A Benchmark for Tracking Any Point in a Video
Figure 2 for TAP-Vid: A Benchmark for Tracking Any Point in a Video
Figure 3 for TAP-Vid: A Benchmark for Tracking Any Point in a Video
Figure 4 for TAP-Vid: A Benchmark for Tracking Any Point in a Video
Viaarxiv icon

Kubric: A scalable dataset generator

Mar 07, 2022
Klaus Greff, Francois Belletti, Lucas Beyer, Carl Doersch, Yilun Du, Daniel Duckworth, David J. Fleet, Dan Gnanapragasam, Florian Golemo, Charles Herrmann, Thomas Kipf, Abhijit Kundu, Dmitry Lagun, Issam Laradji, Hsueh-Ti, Liu, Henning Meyer, Yishu Miao, Derek Nowrouzezahrai, Cengiz Oztireli, Etienne Pot, Noha Radwan, Daniel Rebain, Sara Sabour, Mehdi S. M. Sajjadi, Matan Sela, Vincent Sitzmann, Austin Stone, Deqing Sun, Suhani Vora, Ziyu Wang, Tianhao Wu, Kwang Moo Yi, Fangcheng Zhong, Andrea Tagliasacchi

Figure 1 for Kubric: A scalable dataset generator
Figure 2 for Kubric: A scalable dataset generator
Figure 3 for Kubric: A scalable dataset generator
Figure 4 for Kubric: A scalable dataset generator
Viaarxiv icon

Input-level Inductive Biases for 3D Reconstruction

Dec 06, 2021
Wang Yifan, Carl Doersch, Relja Arandjelović, João Carreira, Andrew Zisserman

Figure 1 for Input-level Inductive Biases for 3D Reconstruction
Figure 2 for Input-level Inductive Biases for 3D Reconstruction
Figure 3 for Input-level Inductive Biases for 3D Reconstruction
Figure 4 for Input-level Inductive Biases for 3D Reconstruction
Viaarxiv icon

Perceiver IO: A General Architecture for Structured Inputs & Outputs

Aug 02, 2021
Andrew Jaegle, Sebastian Borgeaud, Jean-Baptiste Alayrac, Carl Doersch, Catalin Ionescu, David Ding, Skanda Koppula, Daniel Zoran, Andrew Brock, Evan Shelhamer, Olivier Hénaff, Matthew M. Botvinick, Andrew Zisserman, Oriol Vinyals, João Carreira

Figure 1 for Perceiver IO: A General Architecture for Structured Inputs & Outputs
Figure 2 for Perceiver IO: A General Architecture for Structured Inputs & Outputs
Figure 3 for Perceiver IO: A General Architecture for Structured Inputs & Outputs
Figure 4 for Perceiver IO: A General Architecture for Structured Inputs & Outputs
Viaarxiv icon

Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs

Jun 26, 2021
Dan Rosenbaum, Marta Garnelo, Michal Zielinski, Charlie Beattie, Ellen Clancy, Andrea Huber, Pushmeet Kohli, Andrew W. Senior, John Jumper, Carl Doersch, S. M. Ali Eslami, Olaf Ronneberger, Jonas Adler

Figure 1 for Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs
Figure 2 for Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs
Figure 3 for Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs
Figure 4 for Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs
Viaarxiv icon