1 code implementation • 23 Jun 2023 • Lukas Hedegaard
The capabilities and adoption of deep neural networks (DNNs) grow at an exhilarating pace: Vision models accurately classify human actions in videos and identify cancerous tissue in medical scans as precisely than human experts; large language models answer wide-ranging questions, generate code, and write prose, becoming the topic of everyday dinner-table conversations.
1 code implementation • 17 Nov 2022 • Lukas Hedegaard, Aman Alok, Juby Jose, Alexandros Iosifidis
To improve on this, we propose Structured Pruning Adapters (SPAs), a family of compressing, task-switching network adapters, that accelerate and specialize networks using tiny parameter sets and structured pruning.
1 code implementation • 7 Apr 2022 • Lukas Hedegaard, Alexandros Iosifidis
We present Continual Inference, a Python library for implementing Continual Inference Networks (CINs) in PyTorch, a class of Neural Networks designed specifically for efficient inference in both online and batch processing scenarios.
1 code implementation • 21 Mar 2022 • Lukas Hedegaard, Negar Heidari, Alexandros Iosifidis
Graph-based reasoning over skeleton data has emerged as a promising approach for human action recognition.
Ranked #7 on Skeleton Based Action Recognition on Kinetics-Skeleton dataset (GFLOPS per prediction metric)
1 code implementation • 17 Jan 2022 • Lukas Hedegaard, Arian Bakhtiarnia, Alexandros Iosifidis
Transformers in their common form are inherently limited to operate on whole token sequences rather than on one token at a time.
Ranked #4 on Online Action Detection on TVSeries
1 code implementation • 31 May 2021 • Lukas Hedegaard, Alexandros Iosifidis
We introduce Continual 3D Convolutional Neural Networks (Co3D CNNs), a new computational formulation of spatio-temporal 3D CNNs, in which videos are processed frame-by-frame rather than by clip.
Ranked #42 on Action Classification on Charades
1 code implementation • arXiv 2020 • Lukas Hedegaard, Omar Ali Sheikh-Omar, Alexandros Iosifidis
Domain Adaptation is the process of alleviating distribution gaps between data from different domains.
Ranked #28 on Domain Adaptation on Office-31