# Spatio-channel Attention Blocks for Cross-modal Crowd Counting

arXiv: https://arxiv.org/abs/2210.10392 · HTML: https://mlsanity.com/paper/2210.10392/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 66 references that are in the map.
- First posted on arXiv 19 Oct 2022.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [Attention Bottlenecks for Multimodal Fusion](https://mlsanity.com/paper/2107.00135/) (2021)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Asymmetric Non-local Neural Networks for Semantic Segmentation](https://mlsanity.com/paper/1908.07678/) (2019)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [Bayesian Loss for Crowd Count Estimation with Point Supervision](https://mlsanity.com/paper/1908.03684/) (2019)
- [CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.06165/) (2021)
- [Visual Translation Embedding Network for Visual Relation Detection](https://mlsanity.com/paper/1702.08319/) (2017)
- [UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders](https://mlsanity.com/paper/2004.05763/) (2020)
- [JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection](https://mlsanity.com/paper/2004.08515/) (2020)
- [Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection](https://mlsanity.com/paper/2007.06227/) (2020)
- [Leveraging Unlabeled Data for Crowd Counting by Learning to Rank](https://mlsanity.com/paper/1803.03095/) (2018)
- [Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs](https://mlsanity.com/paper/1708.00953/) (2017)
- [CrowdNet: A Deep Convolutional Network for Dense Crowd Counting](https://mlsanity.com/paper/1608.06197/) (2016)
- [Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting](https://mlsanity.com/paper/2012.04529/) (2020)
- [DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation](https://mlsanity.com/paper/1712.06679/) (2017)
- [Revisiting Perspective Information for Efficient Crowd Counting](https://mlsanity.com/paper/1807.01989/) (2018)
- [CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting](https://mlsanity.com/paper/1707.09605/) (2017)
- [Trear: Transformer-based RGB-D Egocentric Action Recognition](https://mlsanity.com/paper/2101.03904/) (2021)
- [Counting with Focus for Free](https://mlsanity.com/paper/1903.12206/) (2019)
- [FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras](https://mlsanity.com/paper/1707.09476/) (2017)
- [Leveraging Crowdsourced GPS Data for Road Extraction from Aerial Imagery](https://mlsanity.com/paper/1905.01447/) (2019)
- [Analyzing Worldwide Social Distancing through Large-Scale Computer Vision](https://mlsanity.com/paper/2008.12363/) (2020)
- [VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results](https://mlsanity.com/paper/2107.08766/) (2021)
- [Depth Information Guided Crowd Counting for Complex Crowd Scenes](https://mlsanity.com/paper/1803.02256/) (2018)

## Built on by (most cited first, 12 of 12)

- [Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks](https://mlsanity.com/paper/2303.15710/) (2023)
- [Multi-modal Crowd Counting via a Broker Modality](https://mlsanity.com/paper/2407.07518/) (2024)
- [RGB-D Indiscernible Object Counting in Underwater Scenes](https://mlsanity.com/paper/2304.11677/) (2023)
- [Grasping Deformable Objects via Reinforcement Learning with Cross-Modal Attention to Visuo-Tactile Inputs](https://mlsanity.com/paper/2504.15595/) (2025)
- [ZOO-Prune: Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language Models](https://mlsanity.com/paper/2509.24837/) (2025)
- [Multi-modal Crowd Counting via Modal Emulation](https://mlsanity.com/paper/2407.19491/) (2024)
- [RA-Touch: Retrieval-Augmented Touch Understanding with Enriched Visual Data](https://mlsanity.com/paper/2505.14270/) (2025)
- [FusionCounting: Robust visible-infrared image fusion guided by crowd counting via multi-task learning](https://mlsanity.com/paper/2508.20817/) (2025)
- [SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation](https://mlsanity.com/paper/2412.19098/) (2024)
- [Multimodal Fusion for Sim2real Transfer in Visual Reinforcement Learning](https://mlsanity.com/paper/2507.09180/) (2025)
- [A Dual-Modulation Framework for RGB-T Crowd Counting via Spatially Modulated Attention and Adaptive Fusion](https://mlsanity.com/paper/2509.17079/) (2025)
- [Thermal-Only Crowd Counting with Deployment-Time Privacy Protection](https://mlsanity.com/paper/2605.17042/) (2026)

## Abstract (arXiv)

Crowd counting research has made significant advancements in real-world applications, but it remains a formidable challenge in cross-modal settings. Most existing methods rely solely on the optical features of RGB images, ignoring the feasibility of other modalities such as thermal and depth images. The inherently significant differences between the different modalities and the diversity of design choices for model architectures make cross-modal crowd counting more challenging. In this paper, we propose Cross-modal Spatio-Channel Attention (CSCA) blocks, which can be easily integrated into any modality-specific architecture. The CSCA blocks first spatially capture global functional correlations among multi-modality with less overhead through spatial-wise cross-modal attention. Cross-modal features with spatial attention are subsequently refined through adaptive channel-wise feature aggregation. In our experiments, the proposed block consistently shows significant performance improvement across various backbone networks, resulting in state-of-the-art results in RGB-T and RGB-D crowd counting.