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 1120 of 371 papers

TitleStatusHype
CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy RewardCode1
Free Lunch Enhancements for Multi-modal Crowd CountingCode1
Multi-modal Crowd Counting via a Broker ModalityCode1
The Effectiveness of a Simplified Model Structure for Crowd CountingCode1
Gramformer: Learning Crowd Counting via Graph-Modulated TransformerCode1
Semi-Supervised Crowd Counting with Contextual Modeling: Facilitating Holistic Understanding of Crowd ScenesCode1
Boosting Detection in Crowd Analysis via Underutilized Output FeaturesCode1
Point-Query Quadtree for Crowd Counting, Localization, and MoreCode1
DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd CountingCode1
ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary TransformerCode1
Show:102550
← PrevPage 2 of 38Next →

No leaderboard results yet.