no code implementations • 26 Jan 2024 • Hanz Cuevas-Velasquez, Charlie Hewitt, Sadegh Aliakbarian, Tadas Baltrušaitis
This presents a challenging scenario, as parts of the body often fall outside of the image or are occluded.
Ranked #5 on Egocentric Pose Estimation on UnrealEgo
no code implementations • ICCV 2023 • Zenghao Chai, Tianke Zhang, Tianyu He, Xu Tan, Tadas Baltrušaitis, HsiangTao Wu, Runnan Li, Sheng Zhao, Chun Yuan, Jiang Bian
3D Morphable Models (3DMMs) demonstrate great potential for reconstructing faithful and animatable 3D facial surfaces from a single image.
Ranked #1 on 3D Face Reconstruction on REALY (side-view)
no code implementations • 3 Jan 2023 • Charlie Hewitt, Tadas Baltrušaitis, Erroll Wood, Lohit Petikam, Louis Florentin, Hanz Cuevas Velasquez
Recent work has shown the benefits of synthetic data for use in computer vision, with applications ranging from autonomous driving to face landmark detection and reconstruction.
1 code implementation • ICCV 2021 • Erroll Wood, Tadas Baltrušaitis, Charlie Hewitt, Sebastian Dziadzio, Matthew Johnson, Virginia Estellers, Thomas J. Cashman, Jamie Shotton
We demonstrate that it is possible to perform face-related computer vision in the wild using synthetic data alone.
Ranked #2 on Face Parsing on Helen (using extra training data)
2 code implementations • ECCV 2020 • Marek Kowalski, Stephan J. Garbin, Virginia Estellers, Tadas Baltrušaitis, Matthew Johnson, Jamie Shotton
Our ability to sample realistic natural images, particularly faces, has advanced by leaps and bounds in recent years, yet our ability to exert fine-tuned control over the generative process has lagged behind.
2 code implementations • 3 Feb 2018 • Minghai Chen, Sen Wang, Paul Pu Liang, Tadas Baltrušaitis, Amir Zadeh, Louis-Philippe Morency
In this paper, we propose the Gated Multimodal Embedding LSTM with Temporal Attention (GME-LSTM(A)) model that is composed of 2 modules.
no code implementations • 23 Nov 2017 • Wenjie Pei, Hamdi Dibeklioğlu, Tadas Baltrušaitis, David M. J. Tax
In this paper, we present an end-to-end architecture for age estimation, called Spatially-Indexed Attention Model (SIAM), which is able to simultaneously learn both the appearance and dynamics of age from raw videos of facial expressions.
no code implementations • 23 Jun 2017 • Abhilasha Ravichander, Shruti Rijhwani, Rajat Kulshreshtha, Chirag Nagpal, Tadas Baltrušaitis, Louis-Philippe Morency
In this work, we focus on improving learning for such hierarchical models and demonstrate our method on the task of speaker trait prediction.
no code implementations • 26 May 2017 • Tadas Baltrušaitis, Chaitanya Ahuja, Louis-Philippe Morency
Our experience of the world is multimodal - we see objects, hear sounds, feel texture, smell odors, and taste flavors.
1 code implementation • CVPR 2017 • Wenjie Pei, Tadas Baltrušaitis, David M. J. Tax, Louis-Philippe Morency
An important advantage of our approach is interpretability since the temporal attention weights provide a meaningful value for the salience of each time step in the sequence.
1 code implementation • 26 Nov 2016 • Amir Zadeh, Tadas Baltrušaitis, Louis-Philippe Morency
In our work, we present a novel local detector -- Convolutional Experts Network (CEN) -- that brings together the advantages of neural architectures and mixtures of experts in an end-to-end framework.