no code implementations • 18 Jun 2022 • Yu Cui, Moshiur Farazi
Visual Relationship Detection (VRD) impels a computer vision model to 'see' beyond an individual object instance and 'understand' how different objects in a scene are related.
no code implementations • 17 Jun 2022 • Sameera Ramasinghe, Lachlan MacDonald, Moshiur Farazi, Hemanth Saratchandran, Simon Lucey
Characterizing the remarkable generalization properties of over-parameterized neural networks remains an open problem.
no code implementations • 26 Feb 2021 • Ce Wang, Moshiur Farazi, Nick Barnes
We propose a recursive training scheme to supervise the retraining of a semantic segmentation model for a zero-shot setting using a pseudo-feature representation.
1 code implementation • 21 Feb 2021 • Shafkat Farabi, Hasibul Himel, Fakhruddin Gazzali, Md. Bakhtiar Hasan, Md. Hasanul Kabir, Moshiur Farazi
We assess the effects of the depth and input clip size of the convolutional neural network on the quality of action score predictions.
Ranked #6 on Action Quality Assessment on MTL-AQA
1 code implementation • 21 Feb 2021 • Zahidul Islam, Mohammad Rukonuzzaman, Raiyan Ahmed, Md. Hasanul Kabir, Moshiur Farazi
Evaluation of the proposed methods was done on three standard public datasets.
Ranked #4 on Activity Recognition on RWF-2000
1 code implementation • NeurIPS 2021 • Sameera Ramasinghe, Moshiur Farazi, Salman Khan, Nick Barnes, Stephen Gould
Conditional GANs (cGAN), in their rudimentary form, suffer from critical drawbacks such as the lack of diversity in generated outputs and distortion between the latent and output manifolds.
no code implementations • 5 Oct 2020 • Moshiur Farazi, Salman Khan, Nick Barnes
Humans explain inter-object relationships with semantic labels that demonstrate a high-level understanding required to perform complex Vision-Language tasks such as Visual Question Answering (VQA).