# Recent Advances in Scene Image Representation and Classification

arXiv: https://arxiv.org/abs/2206.07326 · HTML: https://mlsanity.com/paper/2206.07326/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 135 references that are in the map.
- First posted on arXiv 15 Jun 2022.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Caffe: Convolutional Architecture for Fast Feature Embedding](https://mlsanity.com/paper/1408.5093/) (2014)
- [Bilinear CNNs for Fine-grained Visual Recognition](https://mlsanity.com/paper/1504.07889/) (2015)
- [Places: An Image Database for Deep Scene Understanding](https://mlsanity.com/paper/1610.02055/) (2016)
- [Semantic-Aware Scene Recognition](https://mlsanity.com/paper/1909.02410/) (2019)
- [Multi-scale Orderless Pooling of Deep Convolutional Activation Features](https://mlsanity.com/paper/1403.1840/) (2014)
- [Multi-scale recognition with DAG-CNNs](https://mlsanity.com/paper/1505.05232/) (2015)
- [Scene Recognition with Prototype-agnostic Scene Layout](https://mlsanity.com/paper/1909.03234/) (2019)
- [Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition](https://mlsanity.com/paper/1609.00153/) (2016)
- [A Discriminative Representation of Convolutional Features for Indoor Scene Recognition](https://mlsanity.com/paper/1506.05196/) (2015)
- [Content and Context Features for Scene Image Representation](https://mlsanity.com/paper/2006.03217/) (2020)
- [Harvesting Discriminative Meta Objects with Deep CNN Features for Scene Classification](https://mlsanity.com/paper/1510.01440/) (2015)
- [A Robust Indoor Scene Recognition Method based on Sparse Representation](https://mlsanity.com/paper/1708.07555/) (2017)
- [Scene Image Representation by Foreground, Background and Hybrid Features](https://mlsanity.com/paper/2006.03199/) (2020)
- [Semantic Fisher Scores for Task Transfer: Using Objects to Classify Scenes](https://mlsanity.com/paper/1905.11539/) (2019)
- [Exemplar Based Deep Discriminative and Shareable Feature Learning for Scene Image Classification](https://mlsanity.com/paper/1508.05306/) (2015)
- [Locally-Supervised Deep Hybrid Model for Scene Recognition](https://mlsanity.com/paper/1601.07576/) (2016)
- [Indoor image representation by high-level semantic features](https://mlsanity.com/paper/1906.04987/) (2019)
- [Tag-based Semantic Features for Scene Image Classification](https://mlsanity.com/paper/1909.09999/) (2019)
- [Unsupervised Deep Features for Privacy Image Classification](https://mlsanity.com/paper/1909.10708/) (2019)
- [HDF: Hybrid Deep Features for Scene Image Representation](https://mlsanity.com/paper/2003.09773/) (2020)

## Built on by (most cited first, 1 of 1)

- [Enhanced Multi-level Features for Very High Resolution Remote Sensing Scene Classification](https://mlsanity.com/paper/2305.00679/) (2023)

## Abstract (arXiv)

With the rise of deep learning algorithms nowadays, scene image representation methods have achieved a significant performance boost in classification. However, the performance is still limited because the scene images are mostly complex having higher intra-class dissimilarity and inter-class similarity problems. To deal with such problems, there have been several methods proposed in the literature with their advantages and limitations. A detailed study of previous works is necessary to understand their advantages and disadvantages in image representation and classification problems. In this paper, we review the existing scene image representation methods that are being widely used for image classification. For this, we, first, devise the taxonomy using the seminal existing methods proposed in the literature to this date {using deep learning (DL)-based, computer vision (CV)-based, and search engine (SE)-based methods}. Next, we compare their performance both qualitatively (e.g., quality of outputs, pros/cons, etc.) and quantitatively (e.g., accuracy). Last, we speculate on the prominent research directions in scene image representation tasks using {keyword growth and timeline analysis.} Overall, this survey provides in-depth insights and applications of recent scene image representation methods under three different methods.