SOTAVerified

Crowd Counting

Crowd Counting is a task to count people in image. It is mainly used in real-life for automated public monitoring such as surveillance and traffic control. Different from object detection, Crowd Counting aims at recognizing arbitrarily sized targets in various situations including sparse and cluttering scenes at the same time.

Source: Deep Density-aware Count Regressor

Papers

Showing 51100 of 371 papers

TitleStatusHype
Uniformity in Heterogeneity: Diving Deep Into Count Interval Partition for Crowd CountingCode1
Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd CountingCode1
Weighing Counts: Sequential Crowd Counting by Reinforcement LearningCode1
CCTrans: Simplifying and Improving Crowd Counting with TransformerCode1
Adaptive Mixture Regression Network with Local Counting Map for Crowd CountingCode1
CLIP-Count: Towards Text-Guided Zero-Shot Object CountingCode1
CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion ModelsCode1
Dropout Injection at Test Time for Post Hoc Uncertainty Quantification in Neural NetworksCode1
ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary TransformerCode1
Deep learning with self-supervision and uncertainty regularization to count fish in underwater imagesCode1
Crowd Counting in the Frequency DomainCode1
Boosting Detection in Crowd Analysis via Underutilized Output FeaturesCode1
Ambient Sound Helps: Audiovisual Crowd Counting in Extreme ConditionsCode1
Completely Self-Supervised Crowd Counting via Distribution MatchingCode1
DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd CountingCode1
Congested Crowd Instance Localization with Dilated Convolutional Swin TransformerCode1
Dense Point Prediction: A Simple Baseline for Crowd Counting and LocalizationCode1
Detection, Tracking, and Counting Meets Drones in Crowds: A BenchmarkCode1
Distribution Matching for Crowd CountingCode1
Domain-General Crowd Counting in Unseen ScenariosCode1
EBC-ZIP: Improving Blockwise Crowd Counting with Zero-Inflated Poisson RegressionCode1
Efficient Crowd Counting via Structured Knowledge TransferCode1
Encoder-Decoder Based Convolutional Neural Network with Multi-Scale-Aware Modules for Crowd CountingCode1
Counting from Sky: A Large-scale Dataset for Remote Sensing Object Counting and A Benchmark MethodCode1
Backdoor Attacks on Crowd CountingCode1
Free Lunch Enhancements for Multi-modal Crowd CountingCode1
FusionCount: Efficient Crowd Counting via Multiscale Feature FusionCode1
Counting People by Estimating People FlowsCode1
AdaCrowd: Unlabeled Scene Adaptation for Crowd CountingCode1
Cross-head Supervision for Crowd Counting with Noisy AnnotationsCode1
Densely Connected Convolutional NetworksCode1
DR.VIC: Decomposition and Reasoning for Video Individual CountingCode1
Leveraging Self-Supervision for Cross-Domain Crowd CountingCode1
Localization in the Crowd with Topological ConstraintsCode1
CrowdCLIP: Unsupervised Crowd Counting via Vision-Language ModelCode1
Bi-level Alignment for Cross-Domain Crowd CountingCode1
A Self-Training Approach for Point-Supervised Object Detection and Counting in CrowdsCode1
RGB-T Multi-Modal Crowd Counting Based on TransformerCode1
Attention Scaling for Crowd Counting0
Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network0
A Lightweight Feature Fusion Architecture For Resource-Constrained Crowd Counting0
Attentional Neural Fields for Crowd Counting0
Crowd Transformer Network0
Attend To Count: Crowd Counting with Adaptive Capacity Multi-scale CNNs0
A Generalized Loss Function for Crowd Counting and Localization0
A Survey on Computer Vision based Human Analysis in the COVID-19 Era0
Crowd Scene Analysis using Deep Learning Techniques0
CCCNet: An Attention Based Deep Learning Framework for Categorized Crowd Counting0
A Flow Base Bi-path Network for Cross-scene Video Crowd Understanding in Aerial View0
Causal Influence in Federated Edge Inference0
Show:102550
← PrevPage 2 of 8Next →

No leaderboard results yet.