8/8
✨ Check out the paper on IJHCS: doi.org/10.1016/j.ij...
🔍 ...and VSGUI10K dataset and the accompanying code repository here: osf.io/hmg9b/
✏️ Thanks to my co-authors: Yue Jiang, Jingchun Zeng, Olli Tammilehto, Jussi P.P. Jokinen and Antti Oulasvirta @oulasvirta.bsky.social
17.03.2025 07:55 — 👍 2 🔁 0 💬 0 📌 0
Figure with three panes with search time on the y-axis and different independent variables on the x-axis. First pane depicts the impact of GUI type and presence/absence of the target: search is fastest with target present and mobile UIs. The second pane shows the impact of cue type and presence/absence of the target: search is fastest with target present and image cues. The final pane shows the impact of visual clutter factor score: again, search is slower when the target is absent and when visual clutter increases.
7/8 The paper also presents analysis of search times; we find that GUI type (mobile, desktop or webpage), absence/presence of the target and whether the target is presented in a textual or image format affect search times more than visual complexity.
17.03.2025 07:48 — 👍 1 🔁 0 💬 1 📌 0
6/8 Confirm: Finally, the user must confirm whether the target was found.
17.03.2025 07:45 — 👍 1 🔁 0 💬 1 📌 0
5/8 Scan: Unlike in free-viewing, attention then gets more selectively deployed based on the structure of the GUI and features of the target.
17.03.2025 07:45 — 👍 1 🔁 0 💬 1 📌 0
4/8 Guess: Regardless of target location, first fixations are directed towards top-left of a GUI, similar to the persistent upper-left bias in free-viewing.
17.03.2025 07:45 — 👍 1 🔁 0 💬 1 📌 0
A figure with three heatmaps showing allocation of fixations on a GUI. The first heatmap depicts a Guess stage where fixations are directed to upper-left, the second a Scan stage where the fixations spread out and the third a Confirmation stage where fixations are concentrated at the target location, which is the lower-left quadrant.
3/8 We synthesize our results in a three-stage pattern of search: Guess, Scan and Confirm.
17.03.2025 07:45 — 👍 1 🔁 0 💬 1 📌 0
2/8 Our new paper addresses this gap as we release an eye-tracking dataset of 10,000+ visual search trials on 900 GUIs with 84 participants.
17.03.2025 07:40 — 👍 1 🔁 0 💬 1 📌 0
1/8 Finding items on GUIs is an important task from the perspective of usability. Therefore, it’s interesting that most of our understanding of visual attention over GUIs during search comes from distinctly different stimuli like symbol matrices and natural scenes, or tasks like free-viewing.
17.03.2025 07:40 — 👍 1 🔁 0 💬 1 📌 0
Thanks to my co-authors Yue Jiang, Jingchun Zeng, Olli Tammilehto, Jussi P.P. Jokinen and @oulasvirta.bsky.social
11.03.2025 06:05 — 👍 0 🔁 0 💬 0 📌 0
Happy to report our paper on understanding visual search in graphical user interfaces is out now in International Journal of Human-Computer Studies!
Take a look 🔍: doi.org/10.1016/j.ij...
11.03.2025 06:04 — 👍 8 🔁 0 💬 1 📌 1
machine learning researcher @Apple | PhD from @CoML_ENS | speech, ml and cognition.
Research group leader at LMU Munich and MCML on ML, NLP & HCI. Also experimenting with lemonade that glows in the dark 🥤 (he/him)
Aalto University (Aalto-yliopisto) is a multidisciplinary university, where science and art meet technology and business. #AaltoYliopisto #AaltoUniversity
Kempner Institute research fellow @Harvard interested in scaling up (deep) reinforcement learning theories of human cognition
prev: deepmind, umich, msr
https://cogscikid.com/
Interested in cognition and artificial intelligence. Research Scientist at Google DeepMind. Previously cognitive science at Stanford. Posts are mine.
lampinen.github.io
Researcher @ Google DeepMind and Honorary Fellow @ U of Edinburgh.
RL, philosophy, foundations, AI.
https://david-abel.github.io
she/her pronounced Ya'elle, not like the university. Comp cog neuro, feminist, activist, mom. Stop the war NOW. End the occupation. Equality will bring security.
Postdoctoral researcher,
Human-in-the-loop Decision making
Aalto University, Finland
PhD: Inria Lille, France
Machine Learning Researcher at Apple MLR • PhD in Human-Centered NLP from University of Amsterdam • MSc AI, BA Linguistics
Pizza lover and international political hustler based in Helsinki. Kaupunginvaltuutettu. Generalsekreterare för Nordisk grön vänster.
Human-Computer Interaction, Human-AI Interaction, Visualization
Postdoc researcher at FCAI and Aalto
https://sdq.github.io
Uusi Juttu on media uteliaille ja aikaansa seuraaville demokratian ystäville. Poimimme puolestasi olennaisen informaatiotulvasta: emme vain kerro, mitä on tapahtunut, vaan myös sen miksi. Liity jäseneksi uusijuttu.fi!
Professor in Computer Science @helsinkiuni.bsky.social Lead of AI and sustainability at the Finnish Center for AI (FCAI)
ELLIS PhD student in Machine Learning at PML group - Aalto University, Finland.
Collaborative AI, Computational Rationality, Theory of Mind, and more.
Neuro prof at Princeton, social media cynic.
University of Bristol. IrrationalityLab. Interested in human decision-making. https://www.ktsetsoslab.net
Behavioral economist and professor at USC Marshall
https://sites.google.com/site/caryfrydman
Computational cognitive scientist interested in learning and decision-making in human and machiches
Research director of the Human Reinforcement Learning team
Ecole Normale Supérieure (ENS)
Institut National de la Santé et Recherche Médicale (INSERM)
