• Home
  • Search
  • Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting
  • Open Access IconOpen Access
  • Cite Icon156
  • https://doi.org/10.1109/cvpr46437.2021.00479Copy DOI Icon

Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting

  • Jun 1, 2021
  • Lingbo Liu +5 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Crowd counting is a fundamental yet challenging task, which desires rich information to generate pixel-wise crowd density maps. However, most previous methods only used the limited information of RGB images and cannot well discover potential pedestrians in unconstrained scenarios. In this work, we find that incorporating optical and thermal information can greatly help to recognize pedestrians. To promote future researches in this field, we introduce a large-scale RGBT Crowd Counting (RGBT-CC) benchmark, which contains 2,030 pairs of RGB-thermal images with 138,389 annotated people. Furthermore, to facilitate the multimodal crowd counting, we propose a cross-modal collaborative representation learning framework, which consists of multiple modality-specific branches, a modality-shared branch, and an Information Aggregation-Distribution Module (IADM) to capture the complementary information of different modalities fully. Specifically, our IADM incorporates two collaborative information transfers to dynamically enhance the modality-shared and modality-specific representations with a dual information propagation mechanism. Extensive experiments conducted on the RGBT-CC benchmark demonstrate the effectiveness of our framework for RGBT crowd counting. Moreover, the proposed approach is universal for multimodal crowd counting and is also capable to achieve superior performance on the ShanghaiTechRGBD [22] dataset. Finally, our source code and benchmark have been released at http://lingboliu.com/RGBT_Crowd_Counting.html.

Similar Papers
  • Research Article
  • Citations13

Adversarial scale-adaptive neural network for crowd counting

  • Apr 13, 2021
  • Neurocomputing
  • Xinyue Chen +4
  • Research Article
  • Citations134

PaDNet: Pan-Density Crowd Counting.

  • Nov 12, 2019
  • IEEE Transactions on Image Processing
  • Yukun Tian +3
  • Research Article
  • Citations22

A cross-modal crowd counting method combining CNN and cross-modal transformer

  • Jan 01, 2023
  • Image and Vision Computing
  • Shihui Zhang +4
  • Research Article

NF-Net: Crowd Counting Based on Near-Far Network and Dynamic Dual Attention Mechanism

  • Jan 01, 2025
  • Journal of Artificial Intelligence Practice
  • Zhang Dongming +4
  • Research Article
  • Citations14

Late better than early: A decision-level information fusion approach for RGB-Thermal crowd counting with illumination awareness

  • May 17, 2024
  • Neurocomputing
  • Jian Cheng +3
  • Conference Article

ACCNet: Attention-based Contextual Convolutional Network for Crowd Counting

  • Nov 06, 2020
  • Yaoying Huang +4
  • Conference Article
  • Citations3

A Single-Column Convolutional Neural Networks for Crowd Counting

  • Dec 01, 2019
  • Phuc Thinh Do +2
  • Research Article
  • Citations476

NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization.

  • May 11, 2021
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Qi Wang +3
  • Research Article
  • Citations6

Increasing Reciprocal Social Interactions Between Children Who Use Augmentative and Alternative Communication and Peers Using a Collaborative Learning Framework.

  • Mar 27, 2024
  • American journal of speech-language pathology
  • Jamie B Boster +2
  • Conference Article
  • Citations100

Group-wise Deep Co-saliency Detection

  • Aug 01, 2017
  • Lina Wei +4
  • Research Article
  • Citations14

Collaborative learning based on centroid-distance-vector for wearable devices

  • Feb 03, 2020
  • Knowledge-Based Systems
  • Dequn Kong +2
  • Book Chapter
  • Citations21

A Constructivist Framework for Online Collaborative Learning

  • Jan 01, 2005
  • Elizabeth Stacey
  • Research Article
  • Citations17

Cross-modal collaborative feature representation via Transformer-based multimodal mixers for RGB-T crowd counting

  • Jun 15, 2024
  • Expert Systems With Applications
  • Weihang Kong +4
  • Research Article
  • Citations29

A Framework for Collaborative and Convenient Learning on Cloud Computing Platforms

  • Apr 01, 2017
  • International Journal of Web-Based Learning and Teaching Technologies
  • Deepika Sharma +1
  • Research Article
  • Citations48

Dynamic Group Formation With Intelligent Tutor Collaborative Learning: A Novel Approach for Next Generation Collaboration

  • Jan 01, 2021
  • IEEE Access
  • Ijaz Ul Haq +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.