SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.12746 · ICCV · 2021

Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework

Zhengkai Jiang, Ying Tai, Yang Wu, Chengjie Wang, Yabiao Wang, Qingyu Song, Jilin Li, Feiyue Huang, Changan Wang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Localizing individuals in crowds is more in accordance with the practical demands of subsequent high-level crowd analysis tasks than simply counting. However, existing localization based methods relying on intermediate representations (i.e., density maps or pseudo boxes) serving as learning targets are counter-intuitive and error-prone. In this paper, we propose a purely point-based framework for joint crowd counting and individual localization. For this framework, instead of merely reporting the absolute counting error at image level, we propose a new metric, called density Normalized Average Precision (nAP), to provide more comprehensive and more precise performance evaluation. Moreover, we design an intuitive solution under this framework, which is called Point to Point Network (P2PNet). P2PNet discards superfluous steps and directly predicts a set of point proposals to represent heads in an image, being consistent with the human annotation results. By thorough analysis, we reveal the key step towards implementing such a novel idea is to assign optimal learning targets for these proposals. Therefore, we propose to conduct this crucial association in an one-to-one matching manner using the Hungarian algorithm. The P2PNet not only significantly surpasses state-of-the-art methods on popular counting benchmarks, but also achieves promising localization accuracy. The codes will be available at: TencentYoutuResearch/CrowdCounting-P2PNet.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2107.12746")
get_code_for_paper("2107.12746")
have("2107.12746")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2107.12746.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2107.12746.svg)](https://syntology.ai/paper/2107.12746)

Connect an agent — have() is free.