no code implementations • ECCV 2020 • Ehsan Elhamifar, Dat Huynh
We address the problem of unsupervised procedure learning from instructional videos of multiple tasks using Deep Neural Networks (DNNs).
no code implementations • 23 Apr 2024 • Young Kyun Jang, Donghyun Kim, Zihang Meng, Dat Huynh, Ser-Nam Lim
Composed Image Retrieval (CIR) is a task that retrieves images similar to a query, based on a provided textual modification.
no code implementations • 6 Sep 2023 • Tigran Tchrakian, Mykhaylo Zayats, Alessandra Pascale, Dat Huynh, Pritish Parida, Carla Agurto Rios, Sergiy Zhuk, Jeffrey L. Rogers, ENVISION Studies Physician Author Group, Boston Scientific Research Scientists Consortium
Spinal cord stimulation (SCS) is a therapeutic approach used for the management of chronic pain.
1 code implementation • CVPR 2022 • Dat Huynh, Jason Kuen, Zhe Lin, Jiuxiang Gu, Ehsan Elhamifar
To address this, we propose a cross-modal pseudo-labeling framework, which generates training pseudo masks by aligning word semantics in captions with visual features of object masks in images.
no code implementations • 21 May 2021 • Dat Huynh, Ehsan Elhamifar
In addition, instead of building holistic features for classes, we use our attribute features to form dense representations capable of capturing fine-grained attribute details of classes.
Ranked #2 on Zero-Shot Learning on CUB-200-2011
1 code implementation • ICCV 2021 • Dat Huynh, Ehsan Elhamifar
We study the problem of multi-label zero-shot recognition in which labels are in the form of human-object interactions (combinations of actions on objects), each image may contain multiple interactions and some interactions do not have training images.
Human-Object Interaction Detection Multi-label zero-shot learning +1
no code implementations • NeurIPS 2020 • Dat Huynh, Ehsan Elhamifar
We propose a feature composition framework that learns to extract attribute-based features from training samples and combines them to construct fine-grained features for unseen classes.
1 code implementation • CVPR 2020 • Dat Huynh, Ehsan Elhamifar
Given that optimizing the new loss function over the CNN parameters requires learning similarities among labels and images, which itself depends on knowing the parameters of the CNN, we develop an efficient interactive learning framework in which the two steps of similarity learning and CNN training interact and improve the performance of each another.
1 code implementation • CVPR 2020 • Dat Huynh, Ehsan Elhamifar
Therefore, instead of generating attentions for unseen labels which have unknown behaviors and could focus on irrelevant regions due to the lack of any training sample, we let the unseen labels select among a set of shared attentions which are trained to be label-agnostic and to focus on only relevant/foreground regions through our novel loss.
Ranked #4 on Multi-label zero-shot learning on Open Images V4
no code implementations • CVPR 2020 • Dat Huynh, Ehsan Elhamifar
We address the problem of fine-grained generalized zero-shot recognition of visually similar classes without training images for some classes.