no code implementations • PVLAM (LREC) 2022 • Fangjun Li, David C. Hogg, Anthony G. Cohn
GLIDE is a generative neural network that can synthesize (inpaint) masked areas of an image, conditioned on a short piece of text.
1 code implementation • 8 Jan 2024 • Fangjun Li, David C. Hogg, Anthony G. Cohn
We analyze GPT's spatial reasoning performance on the rectified benchmark, identifying proficiency in mapping natural language text to spatial relations but limitations in multi-hop reasoning.
no code implementations • 13 Sep 2023 • Rebecca S. Stone, Pedro E. Chavarrias-Solano, Andrew J. Bulpitt, David C. Hogg, Sharib Ali
While several previous studies have devised methods for segmentation of polyps, most of these methods are not rigorously assessed on multi-center datasets.
no code implementations • CVPR 2023 • Thomas P. Ilett, Omer Yuval, Thomas Ranner, Netta Cohen, David C. Hogg
3D shape reconstruction typically requires identifying object features or textures in multiple images of a subject.
no code implementations • 9 Sep 2022 • Mohammed M. Alghamdi, He Wang, Andrew J. Bulpitt, David C. Hogg
We train a recurrent neural network to map from speech utterances to displacements in the latent space of the image generator.
no code implementations • 1 Aug 2022 • Fangjun Li, David C. Hogg, Anthony G. Cohn
GLIDE is a generative neural network that can synthesize (inpaint) masked areas of an image, conditioned on a short piece of text.
no code implementations • 17 Oct 2018 • Leo Pauly, Wisdom C. Agboh, David C. Hogg, Raul Fuentes
The distance between the action vectors from the observed third-person demonstration and trial robot executions is used as a reward for reinforcement learning of the demonstrated task.
no code implementations • 11 Sep 2017 • Jawad Tayyub, Majd Hawasly, David C. Hogg, Anthony G. Cohn
This paper introduces a novel activity dataset which exhibits real-life and diverse scenarios of complex, temporally-extended human activities and actions.
no code implementations • WS 2017 • Muhannad Alomari, Paul Duckworth, Majd Hawasly, David C. Hogg, Anthony G. Cohn
This is achieved by first learning a set of visual {`}concepts{'} that abstract the visual feature spaces into concepts that have human-level meaning.