mlsanityData to 14 Oct 2026

TAFNet: A Three-Stream Adaptive Fusion Network for RGB-T Crowd Counting

arXiv 2202.08517 ↗First posted 17 Feb 2022cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a three-stream adaptive fusion network named TAFNet, which uses paired RGB and thermal images for crowd counting. Specifically, TAFNet is divided into one main stream and two auxiliary streams. We combine a pair of RGB and thermal images to constitute the input of main stream. Two auxiliary streams respectively exploit RGB image and thermal image to extract modality-specific features. Besides, we propose an Information Improvement Module (IIM) to fuse the modality-specific features into the main stream adaptively. Experiment results on RGBT-CC dataset show that our method achieves more than 20% improvement on mean average error and root mean squared error compared with state-of-the-art method. The source code will be publicly available at https://github.com/TANGHAIHAN/TAFNet.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 12 of its 24 references that are in the map. First posted on arXiv 17 Feb 2022.

Builds on

12 of 24 references.

References · 12

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  5. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  6. 2018CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenescited by 267
  7. 2019Bayesian Loss for Crowd Count Estimation with Point Supervisioncited by 162
  8. 2016CrowdNet: A Deep Convolutional Network for Dense Crowd Countingcited by 52
  9. 2020Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Countingcited by 52
  10. 2017A Unified RGB-T Saliency Detection Benchmark: Dataset, Baselines, Analysis and A Novel Approachcited by 51
  11. 2020CNN-based Density Estimation and Crowd Counting: A Surveycited by 43
  12. 2020A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowdscited by 36

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 4; 2024: 2; 2025: 2; 2026: 2.

15 papers.

Sort:

  1. 2025Infrared and Visible Image Fusion: From Data Compatibility to Task Adaptioncited by 46
  2. 2023Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Taskscited by 41
  3. 2022Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectivescited by 16
  4. 2024Multi-modal Crowd Counting via a Broker Modalitycited by 11
  5. 2023RGB-T Multi-Modal Crowd Counting Based on Transformercited by 7
  6. 2022CLIP: Train Faster with Less Datacited by 4
  7. 2022DroneNet: Crowd Density Estimation using Self-ONNs for Dronescited by 3
  8. 2023ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformercited by 3
  9. 2024Multi-modal Crowd Counting via Modal Emulationcited by 3
  10. 2023Why Existing Multimodal Crowd Counting Datasets Can Lead to Unfulfilled Expectations in Real-World Applicationscited by 1
  11. 2025Depth-Assisted Network for Indiscernible Marine Object Counting with Adaptive Motion-Differentiated Feature Encodingcited by 1
  12. 2022MAFNet: A Multi-Attention Fusion Network for RGB-T Crowd Countingcited by 0
3 more
  1. 2022Crowd Density Estimation using Imperfect Labelscited by 0
  2. 2026Thermal-Only Crowd Counting with Deployment-Time Privacy Protectioncited by 0
  3. 2026Multi-Modal Hyper-Graph Fusion for Low-Light Crowd Countingcited by 0