Papers with Code 아카이브
Object Counting
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 10
- 보존된 평가 기록
- 69
The goal of Object Counting task is to count the number of object instances in a single image or video sequence. It has many real-world applications such as traffic flow monitoring, crowdedness estimation, and product counting.
Source: Learning to Count Objects with Few Exemplar Annotations
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models
Improving Contrastive Learning for Referring Expression Counting
Expanding Zero-Shot Object Counting with Rich Prompts
InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition
Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?
VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning
Learning What NOT to Count
Marmot: Multi-Agent Reasoning for Multi-Object Self-Correcting in Improving Image-Text Alignment
MATHGLANCE: Multimodal Large Language Models Do Not Know Where to Look in Mathematical Diagrams
A Causal Lens for Evaluating Faithfulness Metrics
Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding
FocalCount: Towards Class-Count Imbalance in Class-Agnostic Counting
AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis
A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approaches
Mamba-MOC: A Multicategory Remote Object Counting via State Space Model
Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension
Vision Transformers for Weakly-Supervised Microorganism Enumeration
Counting Stacked Objects from Multi-View Images
GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks
Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark
Boundary Attention Constrained Zero-Shot Layout-To-Image Generation
A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation
Mind the Prompt: A Novel Benchmark for Prompt-based Class-Agnostic Counting
GCA-SUNet: A Gated Context-Aware Swin-UNet for Exemplar-Free Counting
Dense Center-Direction Regression for Object Counting and Localization with Point Supervision
Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models
Mutually-Aware Feature Learning for Few-Shot Object Counting
Zero-shot Object Counting with Good Exemplars
CountGD: Multi-Modal Open-World Counting
RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent
Learning Spatial Similarity Distribution for Few-shot Object Counting
Overconfidence is Key: Verbalized Uncertainty Evaluation in Large Language and Vision-Language Models
DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting
ChatGPT and general-purpose AI count fruits in pictures surprisingly well
Counting Objects in a Robotic Hand
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.