REVIEW 8 cited by
Recognizing Image Style
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
The style of an image plays a significant role in how it is viewed, but style has received little attention in computer vision research. We describe an approach to predicting style of images, and perform a thorough evaluation of different image features for these tasks. We find that features learned in a multi-layer network generally perform best -- even when trained with object class (not style) labels. Our large-scale learning methods results in the best published performance on an existing dataset of aesthetic ratings and photographic style annotations. We present two novel datasets: 80K Flickr photographs annotated with 20 curated style labels, and 85K paintings annotated with 25 style/genre labels. Our approach shows excellent classification performance on both datasets. We use the learned classifiers to extend traditional tag-based image search to consider stylistic constraints, and demonstrate cross-dataset understanding of style.
Forward citations
Cited by 8 Pith papers
-
ArtSeek: Deep artwork understanding via multimodal in-context reasoning and late interaction retrieval
ArtSeek combines a retrieval-augmented vision-language model with a multitask classifier to interpret artworks from images alone, reporting state-of-the-art style classification and ArtPedia captioning scores.
-
Identifying Prompted Artist Names from Generated Images
A new 1.95M-image benchmark measures how well vision models identify artist names explicitly prompted into text-to-image systems, across artists, prompts, generators, and artist counts.
-
Art Beyond Semantics: Sheaf-Informed Contrastive Learning for Multi-Relational Representations
CANVAS learns a separate embedding subspace for each art-historical relation and, across three art datasets, beats single-space CLIP models on most retrieval and classification benchmarks.
-
SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models
SCFlow learns a reversible style-content merge and then lets the same mapping perform separation without explicit disentanglement training.
-
Recognizing Artistic Style of Archaeological Image Fragments Using Deep Style Extrapolation
A style extrapolation module followed by a transfer-learned classifier achieves state-of-the-art artistic style recognition on archaeological image fragments, validated on a new Pompeii fresco fragment dataset.
-
A LoRA is Worth a Thousand Pictures
LoRA weight vectors, projected with PCA and a per-PC calibration, cluster and retrieve artistic styles more accurately than CLIP, DINO, and style-specialized image features.
-
Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification
Replacing MLP projection heads with Kolmogorov-Arnold Network heads in a dual-teacher self-supervised art-style classifier yields Top-1 accuracy gains of around 0.2 to 1.0 percentage points on WikiArt and Pandora18k, ...
-
Assessing Knee OA Severity with CNN attention-based end-to-end architectures
An end-to-end CNN with trainable attention branches classifies knee OA severity from OAI/MOST X-rays at 64.3% accuracy and 0.63 kappa, without a separate joint localization step.
Discussion (0). Continue with ORCID to comment.