Summary of RGB-T Salient Object Detection, Semantic segmentation and Crowd Counting

-RGBT-red -Salient Object detection-green - Semantic segmentation-blue -Crowd Counting-yellow

Provide a summary of RGB-T-Salient-Object-Detection, Semantic segmentation and Crowd Counting
(Paper, Code, Dataset, Evaluation and more).


🏃 keep updating. 🏃
🚩2023.2.3 RGBT SOD: Add two papers, RGBT SS: Add two papers.
🚩2022.12.4 Summary of RGBT Crowd Counting could be found here.
🚩 2022.10.11 RGBT SOD: Add one TMM paper, RGBT SS: Add one TCSVT paper.
🚩 2022.7.27 RGBT SOD: Add one paper, RGBT SS: Add one paper.
🚩 2022.6.25 RGBT SOD: Add one TCSVT paper and one TIM paper.
🚩 2022.5.28 RGBT SOD: Add one TIP paper.


Content:

  1. RGB-T Salient Object Detection
  2. RGB-T Semantic segmentation
  3. RGB-T Crowd Counting
  4. Dataset
  5. Evaluation
  6. Other Summary
  7. Acknowledgement

RGB-T Salient Object Detection

2017

No. Pub. Title Links
01 ISCID Learning Multiscale Deep Features and SVM Regressors for Adaptive RGB-T Saliency Detection Paper/Code

2018

No. Pub. Title Links
01 IGTA RGB-T Saliency Detection Benchmark: Dataset, Baselines, Analysis and a Novel Approach Paper/Code

2019

No. Pub. Title Links
01 MIPR M3S-NIR: Multi-Modal Multi-Scale Noise-Insensitive Ranking for RGB-T Saliency Detection Paper/Code
02 TMM RGB-T Image Saliency Detection via Collaborative Graph Learning Paper/Code
03 TCSVT RGBT Salient Object Detection: Benchmark and A Novel Cooperative Ranking Approach Paper/Code

2020

No. Pub. Title Links
01 TIP RGB-T Salient Object Detection via Fusing Multi-Level CNN Features Paper/Code
02 TCSVT Revisiting Feature Fusion for RGB-T Salient Object Detection Paper/Code

2021

No. Pub. Title Links
01 TCSVT ECFFNet: Effective and Consistent Feature Fusion Network for RGB-T Salient Object Detection Paper/Results(pin:tx48)
02 TCSVT Unified Information Fusion Network for Multi-Modal RGB-D and RGB-T Salient Object Detection Paper/Code
03 TCSVT CGFNet: Cross-Guided Fusion Network for RGB-T Salient Object Detection Paper/Code
04 TCSVT Efficient Context-Guided Stacked Refinement Network for RGB-T Salient Object Detection Paper/Code
05 SPL TSFNet: Two-Stage Fusion Network for RGB-T Salient Object Detection Paper/Code
06 TETCI APNet: Adversarial Learning Assistance and Perceived Importance Fusion Network for All-Day RGB-T Salient Object Detection Paper/Code
07 TIP Multi-Interactive Dual-Decoder for RGB-Thermal Salient Object Detection Paper/Code
08 TCSVT SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection Paper/Code
09 TCSVT Multi-graph Fusion and Learning for RGBT Image Saliency Detection Paper/Code
10 CYBER Salient Target Detection in RGB-T Image based on Multi-level Semantic Information Paper/Code

2022

No. Pub. Title Links
01 Applied Intelligence RGB-T salient object detection via CNN feature and result saliency map fusion Paper/Code
02 Neurocomputing Multi-modal Interactive Attention and Dual Progressive Decoding Network for RGB-D/T Salient Object Detection Paper/Code
03 TCSVT CGMDRNet: Cross-Guided Modality Difference Reduction Network for RGB-T Salient Object Detection Paper/Code
04 arixv Glass Segmentation with RGB-Thermal Image Pairs Paper/Code
05 TIP Weakly Alignment-free RGBT Salient Object Detection with Deep Correlation Network Paper/Code
06 TIM Real-time One-stream Semantic-guided Refinement Network for RGB-Thermal Salient Object Detection Paper/Code
07 TCSVT Cross-Collaborative Fusion-Encoder Network for Robust RGB-Thermal Salient Object Detection Paper/Code
08 EAAI Unidirectional RGB-T salient object detection with intertwined driving of encoding and fusion Paper/Code
09 MVA EAF-Net: an enhancement and aggregation–feedback network for RGB-T salient object detection Paper/Code
11 arxiv Mirror Complementary Transformer Network for RGB-thermal Salient Object Detection Paper/Code
12 CVIU Enabling modality interactions for RGB-T salient object detection Paper/Code
13 Applied Intelligence Modal complementary fusion network for RGB-T salient object detection Paper/Code
14 TMM Does Thermal really always matter for RGB-T salient object detection Paper/Code
15 Arxiv Interactive Context-Aware Network for RGB-T Salient Object Detection Paper/Code
16 DSP MFENet: Multitype fusion and enhancement network for detecting salient objects in RGB-T images Paper/Code
17 PR Cross-modal co-feedback cellular automata for RGB-T saliency detection Paper/Code
18 KBS Asymmetric cross-modal activation network for RGB-T salient object detection Paper/Code

2023

No. Pub. Title Links
01 TCSVT Cross-Modality Double Bidirectional Interaction and Fusion Network for RGB-T Salient Object Detection Paper/Code
02 TIP LSNet: Lightweight Spatial Boosting Network for Detecting Salient Objects in RGB-Thermal Images Paper/Code

RGB-T Semantic segmentation

2017

No. Pub. Title Links
01 IROS MFNet: Towards Real-Time Semantic Segmentation for Autonomous Vehicles with Multi-Spectral Scenes Paper/Code

2019

No. Pub. Title Links
01 RAL RTFNet: RGB-Thermal Fusion Network for Semantic Segmentation of Urban Scenes Paper/Code

2020

No. Pub. Title Links
01 ICRA PST900: RGB-Thermal Calibration, Dataset and Segmentation Network Paper/Code
02 TASE FuseSeg: Semantic Segmentation of Urban Scenes Based on RGB and Thermal Data Fusion Paper/Code
02 CINE Using thermal intensities to build conditional random fields for object segmentation at night Paper/Code

2021

No. Pub. Title Links
🚩01 TIP GMNet: Graded-Feature Multilabel-Learning Network for RGB-Thermal Urban Scene Semantic Segmentation Paper/Code
🚩02 CVPR ABMDRNet: Adaptive-weighted Bi-directional Modality Difference Reduction Network for RGB-T Semantic Segmentation Paper/Code
03 IROS FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation Paper/Code
04 Measurement Robust semantic segmentation based on RGB-thermal in variable lighting scenes Paper/Code
05 TMM MFFENet: Multiscale Feature Fusion and Enhancement Network for RGBThermal Urban Road Scene Parsing Paper/Code
06 Applied Intelligence MMNet: Multi-modal multi-stage network for RGB-T image semantic segmentation Paper/Code
07 Neurocomputing CCAFFMNet: Dual-spectral semantic segmentation network with channel-coordinate attention feature fusion module Paper/Code
08 IROS HeatNet: Bridging the Day-Night Domain Gap in Semantic Segmentation with Thermal Images Paper/Code

2022

No. Pub. Title Links
🚩01 AAAI Edge-aware guidance fusion network for RGB–thermal scene parsing Paper/Code
02 TIV MTANet: Multitask-Aware Network with Hierarchical Multimodal Fusion for RGB-T Urban Scene Understanding Paper/Code
🚩 03 arixv CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers Paper/Code
03 ACPR ARTSeg: Employing Attention for Thermal Images Semantic Segmentation Paper/Code
04 Neurocomputing GCNet: Grid-Like Context-Aware Network for RGB-Thermal Semantic Segmentation Paper/Code
05 TCSVT RGB-T Semantic Segmentation with Location, Activation, and Sharpening Paper/Code
06 SPL GEBNet: Graph-Enhancement Branch Network for RGB-T Scene Parsing Paper/Code
07 TCSVT A Feature Divide-and-Conquer Network for RGB-T Semantic Segmentation Paper/Code

2023

No. Pub. Title Links
01 TITS Embedded Control Gate Fusion and Attention Residual Learning for RGB–Thermal Urban Scene Parsing Paper/Code

RGB-T Crowd Counting

2021

No. Pub. Title Links
🚩01 CVPR Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting Paper/Code
02 IC-NIDC I-MMCCN: Improved MMCCN for RGB-T Crowd Counting of Drone Images Paper/Code

2022

No. Pub. Title Links
🚩01 TITS DEFNet: Dual-Branch Enhanced Feature Fusion Network for RGB-T Crowd Counting Paper/Code
02 ISCAS TAFNet: A Three-Stream Adaptive Fusion Network for RGB-T Crowd Counting Paper/Code
03 ACCV Spatio-channel Attention Blocks for Cross-modal Crowd Counting Paper/Code

Dataset

RGBT SOD Saliency Dataset(VT821,VT1000,VT5000)
You can found in VT800,VT1000,VT5000.
RGBT Semantic segmentation Dataset(MFNet,PST900)
You can found in MFNet and PST900.
RGBT Crowd Counting Dataset(RGBT-CC)
You can found in RBGT-CC


Evaluation

RGBT SOD Saliency Evaluation
Python version: here(CPU) and here(GPU).
Matlab version: here(include weighted F) and here.
RGBT Semantic segmentation Evaluation
Recommend the evaluation toolbox of RTFNet or GMNet.
RGBT Crowd Counting
Recommend the evaluation toolbox of DEFNet or BL+IADM


Other Summary

RGBD SOD Summary1: https://github.com/jiwei0921/SOD-CNNs-based-code-summary-.
RGBD SOD Summary2: https://github.com/taozh2017/RGBD-SODsurvey.
RGBT SOD Summary: https://github.com/lz118/RGBT-Salient-Object-Detection.


Acknowledgement

The collection of this summary is thanks to Zhun Li , jinfu Liu and Yi Pan.
The summary template comes from ji wei.


🏳️‍🌈 Thanks to the above authors for their excellent work!