Adrian Bulat

Int. J. Comput. Vis., April, 2024

You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation.

[BibT_eX]

[DOI]

CoRR, 2024

Efficient Vision-Language pre-training via domain-specific learning for human activities.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs.

[BibT_eX]

[DOI]

Yassine Ouali

Proceedings of the Computer Vision - ECCV 2024, 2024

FFF: Fixing Flawed Foundations in contrastive pre-training results in very strong Vision-Language models.

[BibT_eX]

[DOI]

Yassine Ouali

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

A Transfer Learning Approach to Heatmap Regression for Action Unit Intensity Estimation.

[BibT_eX]

[DOI]

Ioanna Ntinou

Enrique Sánchez-Lozano

Michel F. Valstar

IEEE Trans. Affect. Comput., 2023

SimDETR: Simplifying self-supervised pretraining for DETR.

[BibT_eX]

[DOI]

Ioannis Maniadis Metaxas

Ioannis Patras

CoRR, 2023

Black Box Few-Shot Adaptation for Vision-Language models.

[BibT_eX]

[DOI]

Yassine Ouali

Mohammad Mahdi Derakhshani

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Bayesian Prompt Learning for Image-Language Model Generalization.

[BibT_eX]

[DOI]

Victor Guilherme Turrisi da Costa

Cees G. M. Snoek

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

ReGen: A good Generative zero-shot video classifier should be Rewarded.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-training.

[BibT_eX]

[DOI]

Ricardo Guerrero

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models.

[BibT_eX]

[DOI]

Mohammad Mahdi Derakhshani

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

Variational prompt tuning improves generalization of vision-language models.

[BibT_eX]

[DOI]

Victor Guilherme Turrisi da Costa

Cees G. M. Snoek

CoRR, 2022

Language-Aware Soft Prompting for Vision & Language Foundation Models.

[BibT_eX]

[DOI]

CoRR, 2022

REST: REtrieve & Self-Train for generative action recognition.

[BibT_eX]

[DOI]

CoRR, 2022

Efficient Attention-free Video Shift Transformers.

[BibT_eX]

[DOI]

CoRR, 2022

iBoot: Image-bootstrapped Self-Supervised Video Representation Learning.

[BibT_eX]

[DOI]

Fatemeh Sadat Saleh

Fuwen Tan

CoRR, 2022

Knowledge Distillation Meets Open-Set Semi-Supervised Learning.

[BibT_eX]

[DOI]

CoRR, 2022

EdgeViTs: Competing Light-Weight CNNs on Mobile Devices with Vision Transformers.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

Pre-training Strategies and Datasets for Facial Representation Learning.

[BibT_eX]

[DOI]

Enrique Sánchez-Lozano

Proceedings of the Computer Vision - ECCV 2022, 2022

2021

Estimation of continuous valence and arousal levels from faces in naturalistic conditions.

[BibT_eX]

[DOI]

Antoine Toisoul

Nat. Mach. Intell., 2021

Tensor Dropout for Robust Learning.

[BibT_eX]

[DOI]

Arinbjörn Kolbeinsson

Yannis Panagakis

Animashree Anandkumar

Ioanna Tzoulaki

Paul M. Matthews

IEEE J. Sel. Top. Signal Process., 2021

SAIC_Cambridge-HuPBA-FBK Submission to the EPIC-Kitchens-100 Action Recognition Challenge 2021.

[BibT_eX]

[DOI]

Swathikiran Sudhakaran

Juan-Manuel Pérez-Rúa

CoRR, 2021

Pre-training strategies and datasets for facial representation learning.

[BibT_eX]

[DOI]

CoRR, 2021

Space-time Mixing Attention for Video Transformer.

[BibT_eX]

[DOI]

Juan-Manuel Pérez-Rúa

Swathikiran Sudhakaran

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

High-Capacity Expert Binary Networks.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Knowledge distillation via softmax regression representation learning.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Bit-Mixer: Mixed-precision networks with runtime bit-width selection.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Improving Memory Banks for Unsupervised Learning with Large Mini-Batch, Consistency and Hard Negative Mining.

[BibT_eX]

[DOI]

Enrique Sánchez-Lozano

Proceedings of the IEEE International Conference on Acoustics, 2021

Subpixel Heatmap Regression for Facial Landmark Localization.

[BibT_eX]

[DOI]

Proceedings of the 32nd British Machine Vision Conference 2021, 2021

Defensive Tensorization.

[BibT_eX]

[DOI]

Timothy M. Hospedales

Nicholas D. Lane

Proceedings of the 32nd British Machine Vision Conference 2021, 2021

2020

Hierarchical Binary CNNs for Landmark Localization with Limited Resources.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2020

A Transfer Learning approach to Heatmap Regression for Action Unit intensity estimation.

[BibT_eX]

[DOI]

CoRR, 2020

Knowledge distillation via adaptive instance normalization.

[BibT_eX]

[DOI]

CoRR, 2020

Training binary neural networks with real-to-binary convolutions.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Towards Pose-Invariant Lip-Reading.

[BibT_eX]

[DOI]

Shiyang Cheng

Pingchuan Ma

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Toward fast and accurate human pose estimation via soft-gated skip connections.

[BibT_eX]

[DOI]

Proceedings of the 15th IEEE International Conference on Automatic Face and Gesture Recognition, 2020

BATS: Binary ArchitecTure Search.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

Factorized Higher-Order CNNs With an Application to Spatio-Temporal Emotion Estimation.

[BibT_eX]

[DOI]

Timothy M. Hospedales

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Semi-supervised Facial Action Unit Intensity Estimation with Contrastive Learning.

[BibT_eX]

[DOI]

Anestis Zaganidis

Proceedings of the Computer Vision - ACCV 2020 - 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30, 2020

FAN-Face: a Simple Orthogonal Improvement to Deep Face Recognition.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

Incremental Multi-Domain Learning with Network Latent Tensor Factorization.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019

Deep learning for real world face alignment.

[BibT_eX]

[DOI]

PhD thesis, 2019

Efficient N-Dimensional Convolutions via Higher-Order Factorization.

[BibT_eX]

[DOI]

CoRR, 2019

Matrix and tensor decompositions for training binary neural networks.

[BibT_eX]

[DOI]

CoRR, 2019

Improved training of binary networks for human pose estimation and image recognition.

[BibT_eX]

[DOI]

CoRR, 2019

T-Net: Parametrizing Fully Convolutional Nets With a Single High-Order Tensor.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

XNOR-Net++: Improved binary neural networks.

[BibT_eX]

[DOI]

Proceedings of the 30th British Machine Vision Conference 2019, 2019

2018

To Learn Image Super-Resolution, Use a GAN to Learn How to Do Image Degradation First.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2018, 2018

Super-FAN: Integrated Facial Landmark Localization and Super-Resolution of Real-World Low Resolution Faces in Arbitrary Poses With GANs.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

2017

Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression.

[BibT_eX]

[DOI]

Aaron S. Jackson

Vasileios Argyriou

Proceedings of the IEEE International Conference on Computer Vision, 2017

Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Computer Vision, 2017

How Far are We from Solving the 2D & 3D Face Alignment Problem? (and a Dataset of 230, 000 3D Facial Landmarks).

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Computer Vision, 2017

2016

Two-Stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challenge.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2016 Workshops, 2016

Human Pose Estimation via Convolutional Part Heatmap Regression.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2016, 2016

Convolutional aggregation of local evidence for large pose face alignment.

[BibT_eX]

[DOI]