Aesthetic Attributes Assessment of Images with AMANv2 and DPC-CaptionsV2
Not on the map. Why?
Abstract (arXiv)
Image aesthetic quality assessment is popular during the last decade. Besides numerical assessment, nature language assessment (aesthetic captioning) has been proposed to describe the generally aesthetic impression of an image. In this paper, we propose aesthetic attribute assessment, which is the aesthetic attributes captioning, i.e., to assess the aesthetic attributes such as composition, lighting usage and color arrangement. It is a non-trivial task to label the comments of aesthetic attributes, which limit the scale of the corresponding datasets. We construct a novel dataset, named DPC-CaptionsV2, by a semi-automatic way. The knowledge is transferred from a small-scale dataset with full annotations to large-scale professional comments from a photography website. Images of DPC-CaptionsV2 contain comments up to 4 aesthetic attributes: composition, lighting, color, and subject. Then, we propose a new version of Aesthetic Multi-Attributes Networks (AMANv2) based on the BUTD model and the VLPSA model. AMANv2 fuses features of a mixture of small-scale PCCD dataset with full annotations and large-scale DPCCaptionsV2 dataset with full annotations. The experimental results of DPCCaptionsV2 show that our method can predict the comments on 4 aesthetic attributes, which are closer to aesthetic topics than those produced by the previous AMAN model. Through the evaluation criteria of image captioning, the specially designed AMANv2 model is better to the CNN-LSTM model and the AMAN model.
Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 26 of its 47 references that are in the map. First posted on arXiv 9 Aug 2022.
Builds on
26 of 47 references.
References · 26
- 2015Deep Residual Learning for Image Recognitioncited by 51,950
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,588
- 2016Densely Connected Convolutional Networkscited by 6,707
- 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,220
- 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,551
- 2017Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answeringcited by 1,310
- 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,214
- 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 967
- 2019VL-BERT: Pre-training of Generic Visual-Linguistic Representationscited by 954
- 2015Generation and Comprehension of Unambiguous Object Descriptionscited by 898
- 2014Show and Tell: A Neural Image Caption Generatorcited by 878
- 2016SPICE: Semantic Propositional Image Caption Evaluationcited by 820
14 more
- 2014Long-term Recurrent Convolutional Networks for Visual Recognition and Descriptioncited by 483
- 2017NIMA: Neural Image Assessmentcited by 389
- 2016SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioningcited by 219
- 2016Photo Aesthetics Ranking Network with Attributes and Content Adaptationcited by 123
- 2018Discriminability objective for training descriptive captionscited by 67
- 2017Convolutional Image Captioningcited by 52
- 2016Image Aesthetic Assessment: An Experimental Surveycited by 50
- 2017A-Lamp: Adaptive Layout-Aware Multi-Patch Deep Convolutional Neural Network for Photo Aesthetic Assessmentcited by 28
- 2018SemStyle: Learning to Generate Stylised Image Captions using Unaligned Textcited by 27
- 2019Aesthetic Attributes Assessment of Imagescited by 18
- 2019Aesthetic Image Captioning From Weakly-Labelled Photographscited by 12
- 2018Neural Aesthetic Image Reviewercited by 11
- 2017Predicting Aesthetic Score Distribution through Cumulative Jensen-Shannon Divergencecited by 9
- 2020Deep Multimodality Learning for UAV Video Aesthetic Quality Assessmentcited by 9
Built on by
Not cited yet.