Browsing School of Electronic Engineering and Computer Science by Author "Bulat, A"
Now showing items 1-18 of 18
-
BATS: Binary ArchitecTure Search
Bulat, A; Martinez, B; Tzimiropoulos, G; European Conference on Computer Vision (ECCV) (2020-08-24) -
Bayesian Prompt Learning for Image-Language Model Generalization
Derakhshani, MM; Sanchez, E; Bulat, A; Turrisi da Costa, VG; Snoek, CGM; Tzimiropoulos, G; Martinez, B; International Conference on Computer Vision (International Conference on Computer Vision, 2023-10-02)Foundational image-language models have generated considerable interest due to their efficient adaptation to downstream tasks by prompt learning. Prompt learning treats part of the language model input as trainable while ... -
Bit-Mixer: Mixed-precision networks with runtime bit-width selection
Bulat, A; Tzimiropoulos, G (2021) -
Black Box Few-Shot Adaptation for Vision-Language models
Ouali, Y; Bulat, A; Martinez, B; Tzimiropoulos, G; International Conference on Computer Vision (2023-10-02) -
EdgeViTs: Competing Light-Weight CNNs on Mobile Devices with Vision Transformers
Pan, J; Bulat, A; Tan, F; Zhu, X; Dudziak, L; Li, H; Tzimiropoulos, G; Martinez, B (2022) -
Fs-detr: Few-shot detection transformer with prompting and without re-training
Bulat, A; Guerrero, R; Martinez, B; Tzimiropoulos, G; International Conference on Computer Vision (IEEE, 2023-10-02)This paper is on Few-Shot Object Detection (FSOD), where given a few templates (examples) depicting a novel class (not seen during training), the goal is to detect all of its occurrences within a set of images. From a ... -
Hierarchical Binary CNNs for Landmark Localization with Limited Resources
Bulat, A; Tzimiropoulos, G (2020-02) -
High-Capacity Expert Binary Networks
Bulat, A; Martinez, B; Tzimiropoulos, G; International Conference on Learning Representations (ICLR) (International Conference on Learning Representations (ICLR), 2021-05-04) -
How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)
Bulat, A; Tzimiropoulos, G; IEEE (2017) -
Human Pose Estimation via Convolutional Part Heatmap Regression
Bulat, A; Tzimiropoulos, G (2016) -
Knowledge distillation via softmax regression representation learning
Yang, J; Martinez, B; Bulat, A; Tzimiropoulos, G; International Conference on Learning Representations (ICLR) (International Conference on Learning Representations (ICLR), 2021-05-04) -
Language-Aware Soft Prompting: Text-to-Text Optimization for Fewand Zero-Shot Adaptation of V&L Models
Bulat, A; Tzimiropoulos, G (Springer, 2023-10-26)Soft prompt learning has emerged as a promising direction for adapting V &L models to a downstream task using a few training examples. However, current methods significantly overfit the training data suffering from large ... -
Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression
Jackson, AS; Bulat, A; Argyriou, V; Tzimiropoulos, G; IEEE (2017) -
LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models
Bulat, A; Tzimiropoulos, G; IEEE/CVF Conference on Computer Vision and Pattern Recognition -
Pre-training Strategies and Datasets for Facial Representation Learning
Bulat, A; Cheng, S; Yang, J; Garbett, A; Sanchez, E; Tzimiropoulos, G (2022) -
ReGen: A good Generative zero-shot video classifier should be Rewarded
Bulat, A; Sanchez, E; Martinez, B; Tzimiropoulos, G; International Conference on Computer Vision (IEEE, 2023-10-02)This paper sets out to solve the following problem: How can we turn a generative video captioning model into an open-world video/action classification model? Video captioning models can naturally produce open-ended ... -
Space-time Mixing Attention for Video Transformer
Bulat, A; Perez-Rua, J-M; Sudhakaran, S; Martinez, B; Tzimiropoulos, G (2021) -
A Transfer Learning approach to Heatmap Regression for Action Unit intensity estimation
Ntinou, IN; Sanchez, E; Bulat, A; Tzimiropoulos, G; Valstar, MAction Units (AUs) are geometrically-based atomic facial muscle movements known to produce appearance changes at specific facial locations. Motivated by this observation we propose a novel AU modelling problem that consists ...