Universal Aesthetics (Multimodal Focus): Difference between revisions
Jump to navigation
Jump to search
Jiajun.shen (talk | contribs) (→Data) |
Jiajun.shen (talk | contribs) (→Data) |
||
| Line 5: | Line 5: | ||
== Data == | == Data == | ||
As for the convergence of language models, we need both plain texts and aesthetic texts. For simplicity, we reuse this [https://huggingface.co/datasets/minhuh/prh/tree/wit_1024 text-image dataset], which is also used in Huh et al.'s paper<ref>{{cite | As for the convergence of language models, we need both plain texts and aesthetic texts. For simplicity, we reuse this [https://huggingface.co/datasets/minhuh/prh/tree/wit_1024 text-image dataset], which is also used in Huh et al.'s paper<ref>{{cite journal | ||
| title = The Platonic Representation Hypothesis | | title = The Platonic Representation Hypothesis | ||
| author1 = Minyoung Huh | | author1 = Minyoung Huh | ||
| Line 12: | Line 12: | ||
| author4 = Phillip Isola | | author4 = Phillip Isola | ||
| year = 2024 | | year = 2024 | ||
| | | journal = arXiv preprint arXiv:2405.07987 | ||
| url = https://arxiv.org/abs/2405.07987 | | url = https://arxiv.org/abs/2405.07987 | ||
}}</ref> | }}</ref> | ||
=== Plain Text === | === Plain Text === | ||
=== Peoms === | === Peoms === | ||
For poems, we use the [https://www.kaggle.com/datasets/michaelarman/poemsdataset/data Poems dataset] from Kaggle, and categorize the poems into 135 types based on their form (haiku, sonnet, etc.). | For poems, we use the [https://www.kaggle.com/datasets/michaelarman/poemsdataset/data Poems dataset] from Kaggle, and categorize the poems into 135 types based on their form (haiku, sonnet, etc.). | ||
== References == | == References == | ||
<references /> | <references /> | ||
Revision as of 21:18, 27 November 2025
Introduction
Methods
Data
As for the convergence of language models, we need both plain texts and aesthetic texts. For simplicity, we reuse this text-image dataset, which is also used in Huh et al.'s paper[1]
Plain Text
Peoms
For poems, we use the Poems dataset from Kaggle, and categorize the poems into 135 types based on their form (haiku, sonnet, etc.).