no code implementations • 24 Mar 2024 • Hui Lu, Hu Jian, Ronald Poppe, Albert Ali Salah
The FTP framework adds four feature processors that focus on specific aspects of human action in videos: action category, action components, action description, and context information.
1 code implementation • 18 Mar 2024 • Hui Lu, Albert Ali Salah, Ronald Poppe
A key challenge in continuous sign language recognition (CSLR) is to efficiently capture long-range spatial interactions over time from the video input.
Ranked #5 on Sign Language Recognition on CSL-Daily
1 code implementation • 11 Dec 2023 • Hui Lu, Albert Ali Salah, Ronald Poppe
We argue that the denoising process is crucially limited by an accumulation of the reconstruction error due to an initial inaccurate reconstruction of the target data.
Ranked #16 on Image Generation on CIFAR-10
1 code implementation • 1 Nov 2021 • Alexandros Stergiou, Ronald Poppe
We evaluate adaUnPool on image and video super-resolution and frame interpolation.
1 code implementation • CVPR 2021 • Dan Andrei Ganea, Bas Boom, Ronald Poppe
We learn discriminative embeddings for object instances that are merged into class representatives.
3 code implementations • ICCV 2021 • Alexandros Stergiou, Ronald Poppe, Grigorios Kalliatakis
Convolutional Neural Networks (CNNs) use pooling to decrease the size of activation maps.
1 code implementation • 8 Nov 2020 • Alexandros Stergiou, Ronald Poppe
To address this challenge, we present a novel spatio-temporal convolution block that is capable of extracting spatio-temporal patterns at multiple temporal resolutions.
Action Recognition In Videos Temporal Action Localization +1
1 code implementation • 15 Jun 2020 • Alexandros Stergiou, Ronald Poppe
Generalizing over temporal variations is a prerequisite for effective action recognition in videos.
Ranked #3 on Action Recognition on HACS
no code implementations • 7 Feb 2020 • Alexandros Stergiou, Ronald Poppe, Remco C. Veltkamp
We show that using Class Regularization blocks in state-of-the-art CNN architectures for action recognition leads to systematic improvement gains of 1. 8%, 1. 2% and 1. 4% on the Kinetics, UCF-101 and HMDB-51 datasets, respectively.
no code implementations • 30 Sep 2019 • Alexandros Stergiou, Ronald Poppe
Motivated by the often distinctive temporal characteristics of actions in either horizontal or vertical direction, we introduce a novel convolution block for CNN architectures with video input.
1 code implementation • 18 Sep 2019 • Alexandros Stergiou, Georgios Kapidis, Grigorios Kalliatakis, Christos Chrysoulas, Ronald Poppe, Remco Veltkamp
We demonstrate the method on six state-of-the-art 3D convolution neural networks (CNNs) on three action recognition (Kinetics-400, UCF-101, and HMDB-51) and two egocentric action recognition datasets (EPIC-Kitchens and EGTEA Gaze+).
no code implementations • 15 Sep 2019 • Georgios Kapidis, Ronald Poppe, Elsbeth van Dam, Lucas Noldus, Remco Veltkamp
We employ this idea to tackle action recognition in egocentric videos by introducing additional supervised tasks.
2 code implementations • 19 Jun 2019 • Jun Zhang, Yamei Liu, Shengping Zhang, Ronald Poppe, Meng Wang
Light field imaging presents an attractive alternative to RGB imaging because of the recording of the direction of the incoming light.
no code implementations • 2 May 2019 • Georgios Kapidis, Ronald Poppe, Elsbeth van Dam, Lucas P. J. J. Noldus, Remco C. Veltkamp
We acknowledge that the presence of objects is significant for the execution of actions by humans and in general for the description of a scene.
1 code implementation • 4 Feb 2019 • Alexandros Stergiou, Georgios Kapidis, Grigorios Kalliatakis, Christos Chrysoulas, Remco Veltkamp, Ronald Poppe
Deep learning approaches have been established as the main methodology for video classification and recognition.
no code implementations • 5 Nov 2018 • Sophie van der Zee, Ronald Poppe, Alice Havrileck, Aurelien Baillon
Our results demonstrate the power of linguistic analysis in real-world deception research when applied at the individual level and provide evidence that factually incorrect tweets are not random mistakes of the sender.
1 code implementation • 31 Jul 2018 • Alexandros Stergiou, Ronald Poppe
The main challenges stem from dealing with the considerable variation in recording setting, the appearance of the people depicted and the coordinated performance of their interaction.
no code implementations • LREC 2014 • Bayu Rahayudi, Ronald Poppe, Dirk Heylen
This paper introduces a multimodal discussion corpus for the study into head movement and turn-taking patterns in debates.