中文
相关论文

相关论文: Mind the Prompt: A Novel Benchmark for Prompt-base…

200 篇论文

Open-world text-guided class-agnostic counting (CAC) has emerged as a flexible paradigm for counting arbitrary object classes by using natural language prompts. However, current evaluation protocols primarily focus on standard counting…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Giacomo Pacini , Luca Ciampi , Nicola Messina , Nicola Tonellotto , Giuseppe Amato , Fabrizio Falchi

Visual object counting has recently shifted towards class-agnostic counting (CAC), which addresses the challenge of counting objects across arbitrary categories, a crucial capability for flexible and generalizable counting systems. Unlike…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Luca Ciampi , Ali Azmoudeh , Elif Ecem Akbaba , Erdi Sarıtaş , Ziya Ata Yazıcı , Hazım Kemal Ekenel , Giuseppe Amato , Fabrizio Falchi

Class-Agnostic Counting (CAC) seeks to accurately count objects in a given image with only a few reference examples. While previous methods achieving this relied on additional training, recent efforts have shown that it's possible to…

计算机视觉与模式识别 · 计算机科学 2025-01-07 Yuhao Lin , Haiming Xu , Lingqiao Liu , Javen Qinfeng Shi

Existing class-agnostic counting models typically rely on a single type of prompt, e.g., box annotations. This paper aims to establish a comprehensive prompt-based counting framework capable of generating density maps for concerned objects…

计算机视觉与模式识别 · 计算机科学 2024-03-18 Wei Lin , Antoni B. Chan

Class-Agnostic object Counting (CAC) involves counting instances of objects from arbitrary classes within an image. Due to its practical importance, CAC has received increasing attention in recent years. Most existing methods assume a…

计算机视觉与模式识别 · 计算机科学 2026-01-21 Michail Spanakis , Iason Oikonomidis , Antonis Argyros

Class-agnostic counting methods enumerate objects of an arbitrary class, providing tremendous utility in many fields. Prior works have limited usefulness as they require either a set of examples of the type to be counted or that the query…

计算机视觉与模式识别 · 计算机科学 2024-07-15 Michael A. Hobley , Victor A. Prisacariu

Class agnostic counting (CAC) is a vision task that can be used to count the total occurrence number of any given reference objects in the query image. The task is usually formulated as a density map estimation problem through similarity…

计算机视觉与模式识别 · 计算机科学 2024-11-19 Tsung-Han Chou , Brian Wang , Wei-Chen Chiu , Jun-Cheng Chen

Recently, Class-Agnostic Counting (CAC) problem has garnered increasing attention owing to its intriguing generality and superior efficiency compared to Category-Specific Counting (CSC). This paper proposes a novel ExpressCount to enhance…

计算机视觉与模式识别 · 计算机科学 2024-02-09 Mingjie Wang , Jun Zhou , Yong Dai , Eric Buys , Minglun Gong

Class-agnostic counting (CAC) aims to count all instances in a query image given few exemplars. A standard pipeline is to extract visual features from exemplars and match them with query images to infer object counts. Two essential…

计算机视觉与模式识别 · 计算机科学 2022-03-17 Min Shi , Hao Lu , Chen Feng , Chengxin Liu , Zhiguo Cao

Vision-language models (VLMs) offer flexible object detection through natural language prompts but suffer from performance variability depending on prompt phrasing. In this paper, we introduce a method for automated prompt refinement using…

计算机视觉与模式识别 · 计算机科学 2025-05-15 Lucas Choi , Ross Greer

Class-agnostic counting (CAC) has numerous potential applications across various domains. The goal is to count objects of an arbitrary category during testing, based on only a few annotated exemplars. In this paper, we point out that the…

计算机视觉与模式识别 · 计算机科学 2023-07-18 Jingyi Xu , Hieu Le , Dimitris Samaras

Class-agnostic object counting aims to count object instances of an arbitrary class at test time. It is challenging but also enables many potential applications. Current methods require human-annotated exemplars as inputs which are often…

计算机视觉与模式识别 · 计算机科学 2023-09-26 Jingyi Xu , Hieu Le , Dimitris Samaras

We propose a novel framework for interactive class-agnostic object counting, where a human user can interactively provide feedback to improve the accuracy of a counter. Our framework consists of two main components: a user-friendly…

计算机视觉与模式识别 · 计算机科学 2023-09-12 Yifeng Huang , Viresh Ranjan , Minh Hoai

Recent advances in large vision-language models (VLMs) have shown remarkable progress in solving the text-promptable object counting problem. Representative methods typically specify text prompts with object category information in images.…

计算机视觉与模式识别 · 计算机科学 2025-07-10 Miaojing Shi , Xiaowen Zhang , Zijie Yue , Yong Luo , Cairong Zhao , Li Li

Object counting is a fundamental task in computer vision, with broad applicability in many real-world scenarios. Fully-supervised counting methods require costly point-level annotations per object. Few weakly-supervised methods leverage…

计算机视觉与模式识别 · 计算机科学 2026-02-16 Xiaowen Zhang , Zijie Yue , Yong Luo , Cairong Zhao , Qijun Chen , Miaojing Shi

Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve state-of-the-art performance, which however are prone to…

计算机视觉与模式识别 · 计算机科学 2023-08-23 Baoshuo Kan , Teng Wang , Wenpeng Lu , Xiantong Zhen , Weili Guan , Feng Zheng

Continual learning aims to refine model parameters for new tasks while retaining knowledge from previous tasks. Recently, prompt-based learning has emerged to leverage pre-trained models to be prompted to learn subsequent tasks without the…

计算机视觉与模式识别 · 计算机科学 2024-03-19 Jisu Han , Jaemin Na , Wonjun Hwang

The counting task, which plays a fundamental role in numerous applications (e.g., crowd counting, traffic statistics), aims to predict the number of objects with various densities. Existing object counting tasks are designed for a single…

计算机视觉与模式识别 · 计算机科学 2023-07-03 Shengqin Jiang , Qing Wang , Fengna Cheng , Yuankai Qi , Qingshan Liu

Nearly all existing counting methods are designed for a specific object class. Our work, however, aims to create a counting model able to count any class of object. To achieve this goal, we formulate counting as a matching problem, enabling…

计算机视觉与模式识别 · 计算机科学 2018-11-02 Erika Lu , Weidi Xie , Andrew Zisserman

In class-agnostic object counting, the goal is to estimate the total number of object instances in an image without distinguishing between specific categories. Existing methods often predict this count without considering class-specific…

计算机视觉与模式识别 · 计算机科学 2025-02-18 Huilin Zhu , Jingling Yuan , Zhengwei Yang , Yu Guo , Xian Zhong , Shengfeng He
‹ 上一页 1 2 3 10 下一页 ›