Call for Encyclopaedia of Smell History and Heritage ‘Entries’

The sense of smell: a man lying in bed smells flowers as another lights some incense, above, a priest stands before a burning sacrifice of a lamb. Engraving after G. Collaert, 1630, after N. van der Horst. Credit: Wellcome Collection. Public Domain Mark.

One of the exciting outputs of the Odeuropa project will be a free, publicly-available, Encyclopaedia of Smell History and Heritage. This will be composed of 120 ‘Entries’ written by smell-history, -culture, and -heritage experts and a series of 24 ‘Storylines’ that explore the links between smells and key themes over time. 

In the first two years of the project, we have developed fantastic tools for identifying and collecting references to smell events in historical texts and images from the 1600s to the 1920s. We have gathered an extensive range of data available through our dedicated Smell Explorer (some 218903 text extracts and 4690 images, with more being added!). 

It has now got to the point where we are beginning to write Entries and Storylines for the Encyclopaedia using this wide-ranging, multi-lingual, material. This is where we want to offer an opportunity to smell researchers interested in Europe’s smell history to get involved. There is a world of expertise on smell and its pasts out there (as testified to by our own PastScent group and the Odeuropa network). We want to draw on that expertise.

We are therefore asking for expressions of interest in writing an Entry for the Encyclopaedia.  We are particularly looking for entries on smells (e.g gunpowder; civet; smog), smellscapes/places (e.g coffee-houses; gas-works; ships), emotional responses to smells (e.g disgust, fear, nostalgia) and noses/olfactory expertise (e.g apothecaries; sanitarians; artists). Each entry can be between 2,000-5,000 words long and will also incorporate multiple images. 

We have an existing list of potential entries but are also open to ideas for entries based on researchers’ expertise and what they can find in our data. The only stipulation is that the entries should look at the period between 1600 to 1925 (or a period within it), that they should focus on Europe (or a place within it, including its global connections), and that they should draw (though not exclusively) on the data in the Odeuropa Smell Explorer.

All entries will be reviewed by two other researchers and the projected timeline from commissioning an entry to the final draft is expected to be 2-3 months. The Encyclopaedia will be published online in late 2023 near the end of the Odeuropa project. If you are interested in writing for the Encyclopaedia then please email will.tullett@york.ac.uk, who can share a sample entry, an entry-writing form, and a list of suggested entries. If you have any questions, please do not hesitate to email him!

MUSTI Challenge: Multimodal Understanding of Smells in Texts and Images

Image source: https://rkd.nl/explore/images/278792

Calling all NLP & Computer Vision researchers to take on our new challenge: Multimodal Understanding of Smells in Texts and Images !

In the context of the MediaEval Multimedia Evaluation benchmark, we have developed a task that brings together recognition of visual and textual information regarding smells. We have set up 2 subtasks:

  1. Classification: Predict whether a text passage and an image evoke the same smell source or not.
  2. Detection: identify the common smell source(s) between the text passages and images. Smell sources include persons, objects or places that have a specific smell, or that produce odors (e.g. plant, animal, perfume, human)

This task is driven by the following research questions:

  • What does it mean for a text passage and an image to be related in terms of smell?
  • Do different text and image genres reference smell differently?
  • Do different languages reference smell differently?
  • How do references to smell in texts and images change over time?
  • How do relationships between smell references in texts and images change over time?

Data & Evaluation
We have put together a set of copyright-free texts and images. It contains texts in English, German, Italian, and French that participants are to match to the images. The images are annotated with 80+ categories of smell objects and gestures such as flowers, food, animals, sniffing and holding the nose. The object categories are organised in a two-level taxonomy.

The Odeuropa text and image benchmark datasets are available as training data to the participants. The image dataset consists of ~3000 images with 20,000 associated object annotations and 600 gesture annotations.

Submissions will be evaluated on a held-out dataset of roughly 1,200 images with associated texts in the four languages. We will evaluate using multiple statistics as each provides a slightly different perspective on the results. Main Task: Predicting whether an image and a text passage evoke the same smell source or not

Important Dates

  • 23 November 2022: Results returned
  • 28 November 2022: Working notes paper
  • 12-13 January 2023: 13th Annual MediaEval Workshop, Collocated with MMM 2023 in Bergen, Norway & online.

More information and registration:

https://multimediaeval.github.io/editions/2022/tasks/musti/