The influence of calibration method and eye physiology on eyetracking data quality
- M. Nyström, Richard Andersson, K. Holmqvist, J. Weijer
- MedicineBehavior Research Methods
- 1 March 2013
This work systematically investigated how the calibration method, aspects of participants’ eye physiologies, the influences of recording time and gaze direction, and the experience of operators affect the quality of data recorded with a common tower-mounted, video-based eyetracker.
Language input for word discovery
- J. Weijer
- Linguistics
- 1999
Word length, sentence length and frequency: Zipf revisited
- B. Sigurd, Mats Eeg-Olofsson, J. Weijer
- Linguistics
- 1 April 2004
This paper examines data from English, Swedish and German in order to find a theoretical distribution that describes the observed relation between word length and frequency. In Swedish and English,…
Unsupervised Domain Adaptation without Source Data by Casting a BAIT
- Shiqi Yang, Yaxing Wang, J. Weijer, Luis Herranz
- Computer ScienceArXiv
- 23 October 2020
This paper addresses Source-free Unsupervised Domain Adaptation (SFUDA), where the model has no access to any source data during the adaptation period, and proposes a novel framework named BAIT to tackle SFUDA.
Avalanche: an End-to-End Library for Continual Learning
- Vincenzo Lomonaco, Lorenzo Pellegrini, D. Maltoni
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 1 April 2021
The proposed Avalanche, an open-source end-to-end library for continual learning research based on PyTorch is designed to provide a shared and collaborative codebase for fast prototyping, training, and reproducible evaluation of continual learning algorithms.
Foreign accent in adult simultaneous bilinguals
- T. Kupisch, D. Barton, J. Weijer
- Linguistics, Sociology
- 2015
The study reported in this paper examines foreign accent (FA) in adult simultaneous bilinguals (2L1ers). Specifically, we investigate how accent is affected if a first language is acquired as a…
Class-incremental learning: survey and performance evaluation
- Marc Masana, Xialei Liu, Bartlomiej Twardowski, Mikel Menta, Andrew D. Bagdanov, J. Weijer
- Computer ScienceArXiv
- 28 October 2020
This paper provides a complete survey of existing methods for incremental learning, and in particular an extensive experimental evaluation on twelve class-incremental methods, including a comparison of class-increasing methods on multiple large-scale datasets, investigation into small and large domain shifts, and comparison on various network architectures.
Denial outperforms apology in repairing organizational trust despite strong evidence of guilt
- Matteo Fuoli, J. Weijer, Carita Paradis
- Business
- 1 November 2017
Number problems in monolingual and bilingual French-speaking children: A production/comprehension divide?
- Malin Ågren, J. Weijer
- Linguistics
- 2013
The results demonstrate that subject–verb agreement in number is a challenge to all French-speaking children, be it monolingual or bilingual, due to its heterogeneous, partial and lexically restricted nature.
Generative Multi-Label Zero-Shot Learning
- Akshita Gupta, Sanath Narayan, Salman Hameed Khan, F. Khan, Ling Shao, J. Weijer
- Computer ScienceArXiv
- 27 January 2021
This work is the first to tackle the problem of multilabel feature synthesis in the (generalized) zero-shot setting and introduces different fusion approaches at the attribute-level, featurelevel and cross-level (across attribute and feature-levels) for synthesizing multi- label features from their corresponding multi-label class embeddings.
...
...