Crowd Counting
137 papers with code • 10 benchmarks • 19 datasets
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.
Libraries
Use these libraries to find Crowd Counting models and implementationsDatasets
Latest papers
DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting
Domain adaptation is commonly employed in crowd counting to bridge the domain gaps between different datasets.
Improved Knowledge Distillation for Crowd Counting on IoT Device
This is comparable to state-of-the-art deep crowd counting models, but at a fraction of the original model size and complexity, thus making the solution suitable for IoT devices.
ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformer
Specifically, unlike existing methods that over-specialize in a single task or a subset of tasks, ComPtr starts from the more general concept of bi-source dense prediction.
CLIP-Count: Towards Text-Guided Zero-Shot Object Counting
Specifically, we propose CLIP-Count, the first end-to-end pipeline that estimates density maps for open-vocabulary objects with text guidance in a zero-shot manner.
CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model
To the best of our knowledge, CrowdCLIP is the first to investigate the vision language knowledge to solve the counting problem.
Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks
Specifically, we consider the following cases: i) both RGB data and thermal data, ii) only one of the types of data, and iii) none of them generate discriminative features.
$CrowdDiff$: Multi-hypothesis Crowd Density Estimation using Diffusion Models
Furthermore, as the intermediate time steps of the diffusion process are noisy, we incorporate a regression branch for direct crowd estimation only during training to improve the feature learning.
Cross-head Supervision for Crowd Counting with Noisy Annotations
To alleviate the negative impact of noisy annotations, we propose a novel crowd counting model with one convolution head and one transformer head, in which these two heads can supervise each other in noisy areas, called Cross-Head Supervision.
Super-Resolution Information Enhancement For Crowd Counting
As the proposed method requires SR labels, we further propose a Super-Resolution Crowd Counting dataset (SR-Crowd).
HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining
Specifically, we propose a \textbf{HumanBench} based on existing datasets to comprehensively evaluate on the common ground the generalization abilities of different pretraining methods on 19 datasets from 6 diverse downstream tasks, including person ReID, pose estimation, human parsing, pedestrian attribute recognition, pedestrian detection, and crowd counting.