# Learning Effective RGB-D Representations for Scene Recognition

arXiv: https://arxiv.org/abs/1809.06269 · HTML: https://mlsanity.com/paper/1809.06269/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2018.

## Built on by (most cited first, 10 of 10)

- [Trusted Multi-View Classification with Dynamic Evidential Fusion](https://mlsanity.com/paper/2204.11423/) (2022)
- [ASK: Adaptively Selecting Key Local Features for RGB-D Scene Recognition](https://mlsanity.com/paper/2110.07703/) (2021)
- [Deep Learning for Scene Classification: A Survey](https://mlsanity.com/paper/2101.10531/) (2021)
- [CGiS-Net: Aggregating Colour, Geometry and Implicit Semantic Features for Indoor Place Recognition](https://mlsanity.com/paper/2202.02070/) (2022)
- [CoMAE: Single Model Hybrid Pre-training on Small-Scale RGB-D Datasets](https://mlsanity.com/paper/2302.06148/) (2023)
- [Self-Supervised Image Representation Learning with Geometric Set Consistency](https://mlsanity.com/paper/2203.15361/) (2022)
- [ShareCMP: Polarization-Aware RGB-P Semantic Segmentation](https://mlsanity.com/paper/2312.03430/) (2023)
- [Multi-Modal RGB-D Scene Recognition Across Domains](https://mlsanity.com/paper/2103.14672/) (2021)
- [Visual Place Representation and Recognition from Depth Images](https://mlsanity.com/paper/2112.13707/) (2021)
- [Exploiting Object-based and Segmentation-based Semantic Features for Deep Learning-based Indoor Scene Classification](https://mlsanity.com/paper/2404.07739/) (2024)

## Abstract (arXiv)

Deep convolutional networks (CNN) can achieve impressive results on RGB scene recognition thanks to large datasets such as Places. In contrast, RGB-D scene recognition is still underdeveloped in comparison, due to two limitations of RGB-D data we address in this paper. The first limitation is the lack of depth data for training deep learning models. Rather than fine tuning or transferring RGB-specific features, we address this limitation by proposing an architecture and a two-step training approach that directly learns effective depth-specific features using weak supervision via patches. The resulting RGB-D model also benefits from more complementary multimodal features. Another limitation is the short range of depth sensors (typically 0.5m to 5.5m), resulting in depth images not capturing distant objects in the scenes that RGB images can. We show that this limitation can be addressed by using RGB-D videos, where more comprehensive depth information is accumulated as the camera travels across the scene. Focusing on this scenario, we introduce the ISIA RGB-D video dataset to evaluate RGB-D scene recognition with videos. Our video recognition architecture combines convolutional and recurrent neural networks (RNNs) that are trained in three steps with increasingly complex data to learn effective features (i.e. patches, frames and sequences). Our approach obtains state-of-the-art performances on RGB-D image (NYUD2 and SUN RGB-D) and video (ISIA RGB-D) scene recognition.