Deep Multi-patch Aggregation Network for Image Style, Aesthetics, and Quality Estimation

By Xin Lu, Zhe L. Lin, Xiaohui Shen, Radomír Mech, James Zijun Wang. IEEE International Conference on Computer Vision, 2015

318 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Learned perceptual image enhancement (2017, methodology): “Recent learning-based methods [15, 18, 25, 28, 42] demonstrate a significant performance improvement compared to former works based on hand-crafted features [29].”
Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks (2020, unknown): “rain model that depicts rain streak location and rain intensity separately to fill the blank of previous works [1], [21], [51] as follows, O 1⁄4 Bþ S R; (2)”
Image Aesthetic Assessment: An experimental survey (2016, methodology): “State-of-the-art approaches [28], [29], [30], [31] for image aesthetic classification typically adopt multi-column CNNs (Fig.”
A Deep Network Solution for Attention and Aesthetics Aware Photo Cropping (2019, methodology): “More recently, deep learning-based solutions [51], [52], [53],”
Photo Aesthetics Ranking Network with Attributes and Content Adaptation (2016, methodology): “If we fine-tune the whole AlexNet, we obtain 62% classification accuracy.”