no code implementations • 19 Dec 2023 • Korrawe Karunratanakul, Konpat Preechakul, Emre Aksan, Thabo Beeler, Supasorn Suwajanakorn, Siyu Tang
We propose Diffusion Noise Optimization (DNO), a new method that effectively leverages existing motion diffusion models as motion priors for a wide range of motion-related tasks.
no code implementations • ICCV 2023 • Korrawe Karunratanakul, Konpat Preechakul, Supasorn Suwajanakorn, Siyu Tang
Denoising diffusion models have shown great promise in human motion synthesis conditioned on natural language descriptions.
1 code implementation • NeurIPS 2021 • Konpat Preechakul, Chawan Piansaddhayanon, Burin Naowarat, Tirasan Khandhawit, Sira Sriswasdi, Ekapol Chuangsuwanich
Set prediction tasks require the matching between predicted set and ground truth set in order to propagate the gradient signal.
2 code implementations • CVPR 2022 • Konpat Preechakul, Nattanat Chatthee, Suttisak Wizadwongsa, Supasorn Suwajanakorn
Our key idea is to use a learnable encoder for discovering the high-level semantics, and a DPM as the decoder for modeling the remaining stochastic variations.
1 code implementation • 22 Oct 2020 • Konpat Preechakul, Sira Sriswasdi, Boonserm Kijsirikul, Ekapol Chuangsuwanich
In medical imaging, Class-Activation Map (CAM) serves as the main explainability tool by pointing to the region of interest.
1 code implementation • 24 Dec 2019 • Konpat Preechakul, Boonserm Kijsirikul
When the past gradients agree on direction, CProp keeps the original learning rate.