---
title: "Distributional Semantics in Technicolor — Bruni 2012"
description: "The paper asks whether word meaning can be modeled better when text-only distributional vectors are supplemented with information taken from images."
authors: ["Elia Bruni", "Gemma Boleda", "Marco Baroni", "Nam-Khanh Tran"]
year: 2012
venue: "Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/P12-1015/"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/bruni-2012-distributional-semantics-technicolor/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/bruni-2012-distributional-semantics-technicolor/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2012](https://md.research.elamur.ai/free/en/papers/2012/) / Distributional Semantics in Technicolor

# Distributional Semantics in Technicolor

**Authors:** [Elia Bruni](https://md.research.elamur.ai/free/en/authors/elia-bruni/), [Gemma Boleda](https://md.research.elamur.ai/free/en/authors/gemma-boleda/), [Marco Baroni](https://md.research.elamur.ai/free/en/authors/marco-baroni/), Nam-Khanh Tran · **Year:** 2012 · **Venue:** Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/P12-1015/) · [PDF](https://aclanthology.org/P12-1015.pdf) · [OpenAlex](https://openalex.org/W2137735870)

**Citations:** 318 citations (openalex-snapshot · 2026-10-14) · [141](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
The paper asks whether word meaning can be modeled better when text-only distributional vectors are supplemented with information taken from images. The authors build several textual models from ukWaC and Wackypedia (Window2, Window20, Document) and also use the existing Distributional Memory (DM) model. They then construct visual word vectors from the tagged ESP-Game image collection, using bag-of-visual-words representations based on SIFT and LAB color descriptors. Multimodal models combine weighted textual and visual vectors, and hybrid models treat co-occurrence of tags on the same image as a context signal. Evaluation covers general semantic relatedness and two color-focused tasks. The second color task requires telling literal color uses apart from nonliteral ones. On general relatedness, visual models trail textual ones. For color terms, however, they match or beat text, even on the harder literal/nonliteral distinction. Vision and text appear to capture complementary facets of meaning, so combining them frequently helps. The study offers early evidence that computer vision can contribute meaningfully to perceptually grounded semantics.

## Key points
- Textual models draw on ukWaC (1.9B tokens) plus Wackypedia (820M tokens), with counts weighted by Local Mutual Information (LMI). Targets are the 20K most frequent nouns, 5K adjectives and 5K verbs, which also serve as context features. DM additionally uses the 100M-word BNC.
- Visual vectors are built from the ESP-Game dataset, which has 100K images, 20,515 distinct tags and about 4 tags per image. The vector for a word is the sum of visual-word counts across all images carrying that tag, again LMI-weighted.
- SIFT vocabularies range from 500 to 2,500 visual words and are combined with a 4×4 spatial grid, giving k×16 dimensions. LAB vocabularies range from 128 to 1,024. LAB beat other color spaces (LUV, HSV, RGB), and edge, texture and shape features did not help on the color tasks.
- Multimodal vectors concatenate normalized text and image vectors, weighted by α and 1−α. The value of α was tuned on 2,000 MEN development pairs and came out near 0.5 for most model combinations.
- Hybrid models ESP-Win and ESP-Doc rely only on tag co-occurrence. ESP-Doc did well on color tasks but is tied to quirks of the labeled data. For example, literal and nonliteral color pairs co-occur in labels at similar rates (89% vs. 86%).

## Interesting ideas
- **Representing a word by aggregating features over all images tagged with it.** This turns any tagged image collection into word vectors that sit in the same framework as text counts. It could be applied to other weakly labeled media, such as audio clips or product photos.
- **Matching the feature type to the semantic property.** Color-only LAB features worked for color terms, while SIFT captured object parts. When grounding a specific attribute, it is worth testing narrow, property-specific features rather than one generic descriptor.
- **Simple, tunable fusion by weighted concatenation.** Normalizing each modality and choosing a single mixing weight on a development set is cheap and easy to interpret. The near-equal optimal weight is itself a useful finding about how much each modality contributes.
- **Using a literal vs. nonliteral discrimination task.** Checking whether a model separates literal color uses from figurative ones probes grounding more sharply than generic similarity benchmarks. Similar targeted evaluations could be designed for other perceptual attributes.
- **Treating co-occurrence of image tags as a cheap proxy for vision.** Tag co-occurrence can partly stand in for real visual features, but its behavior depends on how the labels were collected. Any such proxy should therefore be checked for dataset artifacts before it is trusted.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

## Cited by

Cited by

141 papers of our library cite it (of the 140884 whose bibliographies we read); 12 of them have a page here, 129 not yet.

- [Evaluating Word Embeddings on Low-Resource Languages](https://md.research.elamur.ai/free/en/papers/aclbulk-2020-stringham-evaluating-word-embeddings-low-resource/)
- [Analysis Methods in Neural Language Processing: A Survey](https://md.research.elamur.ai/free/en/papers/belinkov-2019-analysis-methods-neural-language-processing/)
- [Experience Grounds Language](https://md.research.elamur.ai/free/en/papers/bisk-2020-experience-grounds-language/)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://md.research.elamur.ai/free/en/papers/chen-2015-microsoft-coco-captions-data-collection/)
- [Problems With Evaluation of Word Embeddings Using Word Similarity Tasks](https://md.research.elamur.ai/free/en/papers/faruqui-2016-problems-evaluation-word-embeddings-word/)
- [Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn't.](https://md.research.elamur.ai/free/en/papers/gladkova-2016-analogy-based-detection-morphological-semantic/)
- [Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change](https://md.research.elamur.ai/free/en/papers/hamilton-2016-diachronic-word-embeddings-reveal-statistical/)
- [SimLex-999: Evaluating Semantic Models With (Genuine) Similarity Estimation](https://md.research.elamur.ai/free/en/papers/hill-2015-simlex-999-evaluating-semantic-models/)
- [Language Is Not All You Need: Aligning Perception with Language Models](https://md.research.elamur.ai/free/en/papers/huang-2023-language-all-need-aligning-perception/)
- [Combining Language and Vision with a Multimodal Skip-gram Model](https://md.research.elamur.ai/free/en/papers/lazaridou-2015-combining-language-vision-multimodal-skip/)
- [One Word Is Not Enough: Simple Prompts Improve Word Embeddings](https://md.research.elamur.ai/free/en/papers/ranjan-2026-one-word-is-not-enough/)
- [Learning Gender-Neutral Word Embeddings](https://md.research.elamur.ai/free/en/papers/zhao-2018-learning-gender-neutral-word-embeddings/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{bruni2012distributional,
  title = {{Distributional Semantics in Technicolor}},
  author = {Bruni, Elia and Boleda, Gemma and Baroni, Marco and Tran, Nam-Khanh},
  booktitle = {Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2012},
  url = {https://aclanthology.org/P12-1015/}
}
```

- [← previous Discrimination between Arabic and Latin from bilingual documents](https://md.research.elamur.ai/free/en/papers/haboubi-2012-discrimination-between-arabic-latin-bilingual/)
- [next → Domain Adaptation for Coreference Resolution: An Adaptive Ensemble Approach](https://md.research.elamur.ai/free/en/papers/yang-2012-domain-adaptation-coreference-resolution-adaptive/)
- [↑ back to papers of 2012](https://md.research.elamur.ai/free/en/papers/2012/)

## References

38 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Marco Baroni and Alessandro Lenci. 2008. Concepts and properties in word spaces. Italian Journal of Linguistics, 20(1):55–88. [find](https://scholar.google.com/scholar?q=Marco+Baroni+and+Alessandro+Lenci%2E+2008%2E+Concepts+and+properties+in+word+spaces%2E+Italian+Journal+of+Linguistics%2C+20%281%29%3A55%E2%80%9388%2E)
2. Marco Baroni and Alessandro Lenci. 2010. Distributional Memory: A general framework for corpus-based semantics. Computational Linguistics, 36(4):673–721. [find](https://scholar.google.com/scholar?q=Marco+Baroni+and+Alessandro+Lenci%2E+2010%2E+Distributional+Memory%3A+A+general+framework+for+corpus%2Dbased+semantics%2E+Computational+Linguistics%2C+36%284%29%3A673%E2%80%93721%2E) [our card](https://md.research.elamur.ai/free/en/papers/baroni-2010-distributional-memory-general-framework-corpus/)
3. Shane Bergsma and Randy Goebel. 2011. Using visual information to predict lexical preference. In Proceedings of Recent Advances in Natural Language Processing, pages 399–405, Hissar. [find](https://scholar.google.com/scholar?q=Shane+Bergsma+and+Randy+Goebel%2E+2011%2E+Using+visual+information+to+predict+lexical+preference%2E+In+Proceedings+of+Recent+Advances+in+Natural+Language+Processing%2C+pages+399%E2%80%93405%2C+Hissar%2E)
4. Shane Bergsma and Benjamin Van Durme. 2011. Learning bilingual lexicons using the visual similarity of labeled web images. In Proc. IJCAI, pages 1764–1769, Barcelona, Spain, July. [find](https://scholar.google.com/scholar?q=Shane+Bergsma+and+Benjamin+Van+Durme%2E+2011%2E+Learning+bilingual+lexicons+using+the+visual+similarity+of+labeled+web+images%2E+In+Proc%2E+IJCAI%2C+pages+1764%E2%80%931769%2C+Barcelona%2C+Spain%2C+July%2E)
5. Brent Berlin and Paul Key. 1969. Basic Color Terms: Their Universality and Evolution. University of California Press, Berkeley, CA. [find](https://scholar.google.com/scholar?q=Brent+Berlin+and+Paul+Key%2E+1969%2E+Basic+Color+Terms%3A+Their+Universality+and+Evolution%2E+University+of+California+Press%2C+Berkeley%2C+CA%2E)
6. Anna Bosch, Andrew Zisserman, and Xavier Munoz. 2007. Image Classification using Random Forests and Ferns. In Computer Vision, 2007. [find](https://scholar.google.com/scholar?q=Anna+Bosch%2C+Andrew+Zisserman%2C+and+Xavier+Munoz%2E+2007%2E+Image+Classification+using+Random+Forests+and+Ferns%2E+In+Computer+Vision%2C+2007%2E)
7. ICCV 2007. IEEE 11th International Conference on, pages 1–8. [find](https://scholar.google.com/scholar?q=ICCV+2007%2E+IEEE+11th+International+Conference+on%2C+pages+1%E2%80%938%2E)
8. Elia Bruni, Giang Binh Tran, and Marco Baroni. 2011. Distributional semantics from text and images. In Proceedings of the EMNLP GEMS Workshop, pages 22– 32, Edinburgh. [find](https://scholar.google.com/scholar?q=Elia+Bruni%2C+Giang+Binh+Tran%2C+and+Marco+Baroni%2E+2011%2E+Distributional+semantics+from+text+and+images%2E+In+Proceedings+of+the+EMNLP+GEMS+Workshop%2C+pages+22%E2%80%93+32%2C+Edinburgh%2E)
9. John Canny. 1986. A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell, 36(4):679–698. [find](https://scholar.google.com/scholar?q=John+Canny%2E+1986%2E+A+computational+approach+to+edge+detection%2E+IEEE+Trans%2E+Pattern+Anal%2E+Mach%2E+Intell%2C+36%284%29%3A679%E2%80%93698%2E)
10. Gabriella Csurka, Christopher Dance, Lixin Fan, Jutta Willamowski, and Cédric Bray. 2004. Visual categorization with bags of keypoints. In In Workshop on Statistical Learning in Computer Vision, ECCV, pages 1–22. [find](https://scholar.google.com/scholar?q=Gabriella+Csurka%2C+Christopher+Dance%2C+Lixin+Fan%2C+Jutta+Willamowski%2C+and+Ce%CC%81dric+Bray%2E+2004%2E+Visual+categorization+with+bags+of+keypoints%2E+In+In+Workshop+on+Statistical+Learning+in+Computer+Vision%2C+ECCV)
11. Stefan Evert. 2005. The Statistics of Word Cooccurrences. Dissertation, Stuttgart University. [find](https://scholar.google.com/scholar?q=Stefan+Evert%2E+2005%2E+The+Statistics+of+Word+Cooccurrences%2E+Dissertation%2C+Stuttgart+University%2E)
12. Mark D. Fairchild. 2005. Status of cie color appearance models. [find](https://scholar.google.com/scholar?q=Mark+D%2E+Fairchild%2E+2005%2E+Status+of+cie+color+appearance+models%2E)
13. A. Farhadi, M. Hejrati, M. Sadeghi, P. Young, C. Rashtchian, J. Hockenmaier, and D. Forsyth. 2010. Every picture tells a story: Generating sentences from images. In Proceedings of ECCV. [find](https://scholar.google.com/scholar?q=A%2E+Farhadi%2C+M%2E+Hejrati%2C+M%2E+Sadeghi%2C+P%2E+Young%2C+C%2E+Rashtchian%2C+J%2E+Hockenmaier%2C+and+D%2E+Forsyth%2E+2010%2E+Every+picture+tells+a+story%3A+Generating+sentences+from+images%2E+In+Proceedings+of+ECCV%2E)
14. Yansong Feng and Mirella Lapata. 2010. Visual information in semantic representation. In Proceedings of HLT-NAACL, pages 91–99, Los Angeles, CA. [find](https://scholar.google.com/scholar?q=Yansong+Feng+and+Mirella+Lapata%2E+2010%2E+Visual+information+in+semantic+representation%2E+In+Proceedings+of+HLT%2DNAACL%2C+pages+91%E2%80%9399%2C+Los+Angeles%2C+CA%2E)
15. Lev Finkelstein, Evgeniy Gabrilovich, Yossi Matias, Ehud Rivlin, Zach Solan, Gadi Wolfman, and Eytan Ruppin. 2002. Placing search in context: The concept revisited. ACM Transactions on Information Systems, 20(1):116–131. [find](https://scholar.google.com/scholar?q=Lev+Finkelstein%2C+Evgeniy+Gabrilovich%2C+Yossi+Matias%2C+Ehud+Rivlin%2C+Zach+Solan%2C+Gadi+Wolfman%2C+and+Eytan+Ruppin%2E+2002%2E+Placing+search+in+context%3A+The+concept+revisited%2E+ACM+Transactions+on+Information+Sys)
16. Kristen Grauman and Trevor Darrell. 2005. The pyramid match kernel: Discriminative classification with sets of image features. In In ICCV, pages 1458–1465. [find](https://scholar.google.com/scholar?q=Kristen+Grauman+and+Trevor+Darrell%2E+2005%2E+The+pyramid+match+kernel%3A+Discriminative+classification+with+sets+of+image+features%2E+In+In+ICCV%2C+pages+1458%E2%80%931465%2E)
17. G. Kulkarni, V. Premraj, S. Dhar, S. Li, Y. Choi, A. Berg, and T. Berg. 2011. Baby talk: Understanding and generating simple image descriptions. In Proceedings of CVPR. [find](https://scholar.google.com/scholar?q=G%2E+Kulkarni%2C+V%2E+Premraj%2C+S%2E+Dhar%2C+S%2E+Li%2C+Y%2E+Choi%2C+A%2E+Berg%2C+and+T%2E+Berg%2E+2011%2E+Baby+talk%3A+Understanding+and+generating+simple+image+descriptions%2E+In+Proceedings+of+CVPR%2E)
18. Thomas Landauer and Susan Dumais. 1997. A solution to Plato’s problem: The latent semantic analysis theory of acquisition, induction, and representation of knowledge. Psychological Review, 104(2):211–240. [find](https://scholar.google.com/scholar?q=Thomas+Landauer+and+Susan+Dumais%2E+1997%2E+A+solution+to+Plato%E2%80%99s+problem%3A+The+latent+semantic+analysis+theory+of+acquisition%2C+induction%2C+and+representation+of+knowledge%2E+Psychological+Review%2C+104%282%29%3A211%E2%80%93)
19. Svetlana Lazebnik, Cordelia Schmid, and Jean Ponce. 2006. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2, CVPR 2006, pages 2169–2178, Washing… [find](https://scholar.google.com/scholar?q=Svetlana+Lazebnik%2C+Cordelia+Schmid%2C+and+Jean+Ponce%2E+2006%2E+Beyond+bags+of+features%3A+Spatial+pyramid+matching+for+recognizing+natural+scene+categories%2E+In+Proceedings+of+the+2006+IEEE+Computer+Society+C)
20. Chee Wee Leong and Rada Mihalcea. 2011. Going beyond text: A hybrid image-text approach for measuring word relatedness. In Proceedings of IJCNLP, pages 1403–1407, Chiang Mai, Thailand. [find](https://scholar.google.com/scholar?q=Chee+Wee+Leong+and+Rada+Mihalcea%2E+2011%2E+Going+beyond+text%3A+A+hybrid+image%2Dtext+approach+for+measuring+word+relatedness%2E+In+Proceedings+of+IJCNLP%2C+pages+1403%E2%80%931407%2C+Chiang+Mai%2C+Thailand%2E)
21. Max Louwerse. 2011. Symbol interdependency in symbolic and embodied cognition. Topics in Cognitive Science, 3:273–302. [find](https://scholar.google.com/scholar?q=Max+Louwerse%2E+2011%2E+Symbol+interdependency+in+symbolic+and+embodied+cognition%2E+Topics+in+Cognitive+Science%2C+3%3A273%E2%80%93302%2E)
22. David Lowe. 1999. Object Recognition from Local Scale-Invariant Features. Computer Vision, IEEE International Conference on, 2:1150–1157 vol.2, August. [find](https://scholar.google.com/scholar?q=David+Lowe%2E+1999%2E+Object+Recognition+from+Local+Scale%2DInvariant+Features%2E+Computer+Vision%2C+IEEE+International+Conference+on%2C+2%3A1150%E2%80%931157+vol%2E2%2C+August%2E)
23. David Lowe. 2004. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), November. [find](https://scholar.google.com/scholar?q=David+Lowe%2E+2004%2E+Distinctive+image+features+from+scale%2Dinvariant+keypoints%2E+International+Journal+of+Computer+Vision%2C+60%282%29%2C+November%2E)
24. Kevin Lund and Curt Burgess. 1996. Producing high-dimensional semantic spaces from lexical co-occurrence. Behavior Research Methods, 28:203–208. [find](https://scholar.google.com/scholar?q=Kevin+Lund+and+Curt+Burgess%2E+1996%2E+Producing+high%2Ddimensional+semantic+spaces+from+lexical+co%2Doccurrence%2E+Behavior+Research+Methods%2C+28%3A203%E2%80%93208%2E)
25. Saif Mohammad. 2011. Colourful language: Measuring word-colour associations. In Proceedings of the 2nd Workshop on Cognitive Modeling and Computational Linguistics, pages 97–106, Portland, Oregon. [find](https://scholar.google.com/scholar?q=Saif+Mohammad%2E+2011%2E+Colourful+language%3A+Measuring+word%2Dcolour+associations%2E+In+Proceedings+of+the+2nd+Workshop+on+Cognitive+Modeling+and+Computational+Linguistics%2C+pages+97%E2%80%93106%2C+Portland%2C+Oregon%2E)
26. Raymond J. Mooney. 2008. Learning to connect language and perception. [find](https://scholar.google.com/scholar?q=Raymond+J%2E+Mooney%2E+2008%2E+Learning+to+connect+language+and+perception%2E)
27. David Nister and Henrik Stewenius. 2006. Scalable recognition with a vocabulary tree. In Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2, CVPR ’06, pages 2161–2168. [find](https://scholar.google.com/scholar?q=David+Nister+and+Henrik+Stewenius%2E+2006%2E+Scalable+recognition+with+a+vocabulary+tree%2E+In+Proceedings+of+the+2006+IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition+%2D+Volume+2%2C)
28. Aude Oliva and Antonio Torralba. 2001. Modeling the shape of the scene: A holistic representation of the spatial envelope. Int. J. Comput. Vision, 42:145–175. [find](https://scholar.google.com/scholar?q=Aude+Oliva+and+Antonio+Torralba%2E+2001%2E+Modeling+the+shape+of+the+scene%3A+A+holistic+representation+of+the+spatial+envelope%2E+Int%2E+J%2E+Comput%2E+Vision%2C+42%3A145%E2%80%93175%2E)
29. Gözde Özbal, Carlo Strapparava, Rada Mihalcea, and Daniele Pighin. 2011. A comparison of unsupervised methods to associate colors with words. In Proceedings of ACII, pages 42–51, Memphis, TN. [find](https://scholar.google.com/scholar?q=Go%CC%88zde+O%CC%88zbal%2C+Carlo+Strapparava%2C+Rada+Mihalcea%2C+and+Daniele+Pighin%2E+2011%2E+A+comparison+of+unsupervised+methods+to+associate+colors+with+words%2E+In+Proceedings+of+ACII%2C+pages+42%E2%80%9351%2C+Memphis%2C+TN%2E)
30. Ekaterina Shutova. 2010. Models of metaphor in NLP. In Proceedings of ACL, pages 688–697, Uppsala, Sweden. [find](https://scholar.google.com/scholar?q=Ekaterina+Shutova%2E+2010%2E+Models+of+metaphor+in+NLP%2E+In+Proceedings+of+ACL%2C+pages+688%E2%80%93697%2C+Uppsala%2C+Sweden%2E)
31. Josef Sivic and Andrew Zisserman. 2003. Video Google: A text retrieval approach to object matching in videos. In Proceedings of the International Conference on Computer Vision, volume 2, pages 1470–1477, October. [find](https://scholar.google.com/scholar?q=Josef+Sivic+and+Andrew+Zisserman%2E+2003%2E+Video+Google%3A+A+text+retrieval+approach+to+object+matching+in+videos%2E+In+Proceedings+of+the+International+Conference+on+Computer+Vision%2C+volume+2%2C+pages+1470%E2%80%9314)
32. Richard Szeliski. 2010. Computer Vision : Algorithms and Applications. Springer-Verlag New York Inc. [find](https://scholar.google.com/scholar?q=Richard+Szeliski%2E+2010%2E+Computer+Vision+%3A+Algorithms+and+Applications%2E+Springer%2DVerlag+New+York+Inc%2E)
33. Peter Turney and Patrick Pantel. 2010. From frequency to meaning: Vector space models of semantics. Journal of Artificial Intelligence Research, 37:141–188. [find](https://scholar.google.com/scholar?q=Peter+Turney+and+Patrick+Pantel%2E+2010%2E+From+frequency+to+meaning%3A+Vector+space+models+of+semantics%2E+Journal+of+Artificial+Intelligence+Research%2C+37%3A141%E2%80%93188%2E)
34. Peter Turney, Yair Neuman, Dan Assaf, and Yohai Cohen. 2011. Literal and metaphorical sense identification through concrete and abstract context. In Proceedings of EMNLP, pages 680–690, Edinburgh, UK. [find](https://scholar.google.com/scholar?q=Peter+Turney%2C+Yair+Neuman%2C+Dan+Assaf%2C+and+Yohai+Cohen%2E+2011%2E+Literal+and+metaphorical+sense+identification+through+concrete+and+abstract+context%2E+In+Proceedings+of+EMNLP%2C+pages+680%E2%80%93690%2C+Edinburgh%2C+UK%2E) [our card](https://md.research.elamur.ai/free/en/papers/turney-2011-literal-metaphorical-sense-identification-through/)
35. Andrea Vedaldi and Brian Fulkerson. 2008. VLFeat: An open and portable library of computer vision algorithms. [http://www.vlfeat.org/](http://www.vlfeat.org/). [↗](http://www.vlfeat.org/)
36. Luis von Ahn and Laura Dabbish. 2004. Labeling images with a computer game. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pages 319–326, Vienna, Austria. [find](https://scholar.google.com/scholar?q=Luis+von+Ahn+and+Laura+Dabbish%2E+2004%2E+Labeling+images+with+a+computer+game%2E+In+Proceedings+of+the+SIGCHI+Conference+on+Human+Factors+in+Computing+Systems%2C+pages+319%E2%80%93326%2C+Vienna%2C+Austria%2E)
37. Jun Yang, Yu-Gang Jiang, Alexander G. Hauptmann, and Chong-Wah Ngo. 2007. Evaluating bag-of-visual-words representations in scene classification. In Multimedia Information Retrieval, pages 197–206. [find](https://scholar.google.com/scholar?q=Jun+Yang%2C+Yu%2DGang+Jiang%2C+Alexander+G%2E+Hauptmann%2C+and+Chong%2DWah+Ngo%2E+2007%2E+Evaluating+bag%2Dof%2Dvisual%2Dwords+representations+in+scene+classification%2E+In+Multimedia+Information+Retrieval%2C+pages+197%E2%80%93206%2E)
38. Song Chun Zhu, Cheng en Guo, Ying Nian Wu, and Yizhou Wang. 2002. What are textons? In Computer Vision - ECCV 2002, 7th European Conference on Computer Vision, Copenhagen, Denmark, May 28-31, 2002, Proceedings, Part IV, pages 793–807. Springer. [find](https://scholar.google.com/scholar?q=Song+Chun+Zhu%2C+Cheng+en+Guo%2C+Ying+Nian+Wu%2C+and+Yizhou+Wang%2E+2002%2E+What+are+textons%3F+In+Computer+Vision+%2D+ECCV+2002%2C+7th+European+Conference+on+Computer+Vision%2C+Copenhagen%2C+Denmark%2C+May+28%2D31%2C+2002%2C+Pr)