Official Implement of CVPR 2021 paper “Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting”

Overview

RGBT Crowd Counting

Lingbo Liu, Jiaqi Chen, Hefeng Wu, Guanbin Li, Chenglong Li, Liang Lin. "Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting." IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021. [PDF]

Download RGBT-CC Dataset & Models: [Dropbox][BaiduYun (PW: RGBT)]

Our framework can be implemented with various backbone networks. You can refer to this page for implementing BL+IADM. Moreover, the proposed framework can also be applied to RGBD crowd counting and the implementation of CSRNet+IADM is available.

If you use this code and benchmark for your research, please cite our work:

@inproceedings{liu2021cross,
  title={Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting},
  author={Liu, Lingbo and Chen, Jiaqi and Wu, Hefeng and Li, Guanbin and Li, Chenglong and Lin, Liang},
  booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
  year={2021}
}

Introduction

Crowd counting is a fundamental yet challenging task, which desires rich information to generate pixel-wise crowd density maps. 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.

RGBT-CC Benchmark

To promote the future research of this task, we propose a large-scale RGBT Crowd Counting (RGBT-CC) benchmark. Specifically, this benchmark consists of 2,030 pairs of 640x480 RGB-thermal images captured in various scenarios (e.g., malls, streets, playgrounds, train stations, metro stations, etc). Among these samples, 1,013 pairs are captured in the light and 1,017 pairs are in the darkness. A total of 138,389 pedestrians are marked with point annotations, on average 68 people per image. Finally, the proposed RGBT-CC benchmark is randomly divided into three parts: 1030 pairs are used for training, 200 pairs are for validation and 800 pairs are for testing. Compared with those Internet-based datasets with serious bias, our RGBT-CC dataset has closer crowd density distribution to realistic cities, since our images are captured in urban scenes with various densities. Therefore, our dataset has wider applications for urban crowd analysis.

Method

The proposed RGBT crowd counting framework is composed of three parallel backbones and an Information Aggregation-Distribution Module (IADM). Specifically, the top and bottom backbones are developed for modality-specific (i.e. RGB images and thermal images) representation learning, while the middle backbone is designed for modality-shared representation learning. To fully exploit the multimodal complementarities, our IADM dynamically transfers the specific-shared information to collaboratively enhance the modality-specific and modality-shared representations. Consequently, the final modality-shared feature contains comprehensive information and facilitates generating high-quality crowd density maps.

Experiments

More References

Crowd Counting with Deep Structured Scale Integration Network, ICCV 2019 [PDF]

Crowd Counting using Deep Recurrent Spatial-Aware Network, IJCAI 2018 [PDF]

Efficient Crowd Counting via Structured Knowledge Transfer, ACM MM 2020 [PDF]

Deepparse is a state-of-the-art library for parsing multinational street addresses using deep learning

Here is deepparse. Deepparse is a state-of-the-art library for parsing multinational street addresses using deep learning. Use deepparse to Use the pr

GRAAL/GRAIL 192 Dec 20, 2022
Code of TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation

TVT Code of TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation Datasets: Digit: MNIST, SVHN, USPS Object: Office, Office-Home, Vi

37 Dec 15, 2022
DGCNN - Dynamic Graph CNN for Learning on Point Clouds

DGCNN is the author's re-implementation of Dynamic Graph CNN, which achieves state-of-the-art performance on point-cloud-related high-level tasks including category classification, semantic segmentat

Wang, Yue 1.3k Dec 26, 2022
SemiNAS: Semi-Supervised Neural Architecture Search

SemiNAS: Semi-Supervised Neural Architecture Search This repository contains the code used for Semi-Supervised Neural Architecture Search, by Renqian

Renqian Luo 21 Aug 31, 2022
An attempt at the implementation of GLOM, Geoffrey Hinton's paper for emergent part-whole hierarchies from data

GLOM TensorFlow This Python package attempts to implement GLOM in TensorFlow, which allows advances made by several different groups transformers, neu

Rishit Dagli 32 Feb 21, 2022
Norm-based Analysis of Transformer

Norm-based Analysis of Transformer Implementations for 2 papers introducing to analyze Transformers using vector norms: Kobayashi+'20 Attention is Not

Goro Kobayashi 52 Dec 05, 2022
The fastest way to visualize GradCAM with your Keras models.

VizGradCAM VizGradCam is the fastest way to visualize GradCAM in Keras models. GradCAM helps with providing visual explainability of trained models an

58 Nov 19, 2022
Self-Supervised Multi-Frame Monocular Scene Flow (CVPR 2021)

Self-Supervised Multi-Frame Monocular Scene Flow 3D visualization of estimated depth and scene flow (overlayed with input image) from temporally conse

Visual Inference Lab @TU Darmstadt 85 Dec 22, 2022
Learning Temporal Consistency for Low Light Video Enhancement from Single Images (CVPR2021)

StableLLVE This is a Pytorch implementation of "Learning Temporal Consistency for Low Light Video Enhancement from Single Images" in CVPR 2021, by Fan

99 Dec 19, 2022
Dynamic Realtime Animation Control

Our project is targeted at making an application that dynamically detects the user’s expressions and gestures and projects it onto an animation software which then renders a 2D/3D animation realtime

Harsh Avinash 10 Aug 01, 2022
Code for CVPR2021 paper "Robust Reflection Removal with Reflection-free Flash-only Cues"

Robust Reflection Removal with Reflection-free Flash-only Cues (RFC) Paper | To be released: Project Page | Video | Data Tensorflow implementation for

Chenyang LEI 162 Jan 05, 2023
Blind visual quality assessment on 360° Video based on progressive learning

Blind visual quality assessment on omnidirectional or 360 video (ProVQA) Blind VQA for 360° Video via Progressively Learning from Pixels, Frames and V

5 Jan 06, 2023
WSDM2022 "A Simple but Effective Bidirectional Extraction Framework for Relational Triple Extraction"

BiRTE WSDM2022 "A Simple but Effective Bidirectional Extraction Framework for Relational Triple Extraction" Requirements The main requirements are: py

9 Dec 27, 2022
LBK 35 Dec 26, 2022
Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel

Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel This repository is the official PyTorch implementation of BSRDM w

Zongsheng Yue 69 Jan 05, 2023
Generic ecosystem for feature extraction from aerial and satellite imagery

Note: Robosat is neither maintained not actively developed any longer by Mapbox. See this issue. The main developers (@daniel-j-h, @bkowshik) are no l

Mapbox 1.9k Jan 06, 2023
Shape Matching of Real 3D Object Data to Synthetic 3D CADs (3DV project @ ETHZ)

Real2CAD-3DV Shape Matching of Real 3D Object Data to Synthetic 3D CADs (3DV project @ ETHZ) Group Member: Yue Pan, Yuanwen Yue, Bingxin Ke, Yujie He

24 Jun 22, 2022
An official source code for "Augmentation-Free Self-Supervised Learning on Graphs"

Augmentation-Free Self-Supervised Learning on Graphs An official source code for Augmentation-Free Self-Supervised Learning on Graphs paper, accepted

Namkyeong Lee 59 Dec 01, 2022
A Unified Generative Framework for Various NER Subtasks.

This is the code for ACL-ICJNLP2021 paper A Unified Generative Framework for Various NER Subtasks. Install the package in the requirements.txt, then u

177 Jan 05, 2023
A package, and script, to perform imaging transcriptomics on a neuroimaging scan.

Imaging Transcriptomics Imaging transcriptomics is a methodology that allows to identify patterns of correlation between gene expression and some prop

Alessio Giacomel 10 Dec 27, 2022