SOTAVerified

Object Counting

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 158 papers

TitleStatusHype
Class-agnostic-Few-shot-Object-CountingCode1
Learning To Count EverythingCode1
Image Augmentation for Multitask Few-Shot Learning: Agricultural Domain Use-CaseCode1
Heatmap-based Object Detection and Tracking with a Fully Convolutional Neural NetworkCode1
PSGCNet: A Pyramidal Scale and Global Context Guided Network for Dense Object Counting in Remote Sensing ImagesCode1
Synbols: Probing Learning Algorithms with Synthetic DatasetsCode1
Unsupervised Domain Adaptation For Plant Organ CountingCode1
Counting from Sky: A Large-scale Dataset for Remote Sensing Object Counting and A Benchmark MethodCode1
Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd CountingCode1
Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware LearningCode1
From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object CountingCode1
YOLO9000: Better, Faster, StrongerCode1
You Only Look Once: Unified, Real-Time Object DetectionCode1
Car Object Counting and Position Estimation via Extension of the CLIP-EBC FrameworkCode0
OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models—0
Improving Contrastive Learning for Referring Expression CountingCode0
Expanding Zero-Shot Object Counting with Rich Prompts—0
Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?—0
Learning What NOT to Count—0
Marmot: Multi-Agent Reasoning for Multi-Object Self-Correcting in Improving Image-Text Alignment—0
MATHGLANCE: Multimodal Large Language Models Do Not Know Where to Look in Mathematical Diagrams—0
A Causal Lens for Evaluating Faithfulness Metrics—0
Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding—0
FocalCount: Towards Class-Count Imbalance in Class-Agnostic Counting—0
AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis—0
A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approaches—0
Mamba-MOC: A Multicategory Remote Object Counting via State Space Model—0
Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension—0
Vision Transformers for Weakly-Supervised Microorganism EnumerationCode0
Counting Stacked Objects from Multi-View Images—0
Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark—0
Boundary Attention Constrained Zero-Shot Layout-To-Image Generation—0
GCA-SUNet: A Gated Context-Aware Swin-UNet for Exemplar-Free CountingCode0
Dense Center-Direction Regression for Object Counting and Localization with Point SupervisionCode0
Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models—0
Mutually-Aware Feature Learning for Few-Shot Object Counting—0
Learning Spatial Similarity Distribution for Few-shot Object CountingCode0
Overconfidence is Key: Verbalized Uncertainty Evaluation in Large Language and Vision-Language Models—0
ChatGPT and general-purpose AI count fruits in pictures surprisingly well—0
Counting Objects in a Robotic Hand—0
Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-ReferringCode0
TFCounter:Polishing Gems for Training-Free Object Counting—0
OmniCount: Multi-label Object Counting with Semantic-Geometric Priors—0
Effectiveness Assessment of Recent Large Vision-Language Models—0
AFreeCA: Annotation-Free Counting for AllCode0
A Density-Guided Temporal Attention Transformer for Indiscernible Object Counting in Underwater Video—0
Enhancing Zero-shot Counting via Language-guided Exemplar Learning—0
Do Object Detection Localization Errors Affect Human Performance and Trust?—0
Diffusion-based Data Augmentation for Object Counting Problems—0
Real-Time Object Detection in Occluded Environment with Background Cluttering Effects Using Deep Learning—0
Show:102550
← PrevPage 2 of 4Next →
All datasetsFSC147CARPKPascal VOC 2007 count-testCOCO count-testTallyQA-ComplexTallyQA-SimpleHowMany-QAPASCAL VOCOmnicount-191TRANCOS

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FamNetMAE(test)22.08—Unverified
2Omnicount (Open vocabulary, multi-label, without training)MAE(test)18.63—Unverified
3RCCMAE(test)17.12—Unverified
4Counting-DETRMAE(test)16.79—Unverified
5CounTX (uses text descriptions instead of visual exemplars)MAE(test)15.88—Unverified
6LaoNetMAE(test)15.78—Unverified
7BMNet+MAE(test)14.62—Unverified
8SAFECountMAE(test)14.32—Unverified
9GCA-SUNMAE(test)14—Unverified
10SPDCNMAE(test)13.51—Unverified
#ModelMetricClaimedVerifiedStatus
1YOLO (2016)MAE156—Unverified
2YOLO9000opt (2017)MAE130.4—Unverified
3Faster R-CNN (2015)MAE39.88—Unverified
4RetinaNet (2018)MAE24.58—Unverified
5LPN Counting (2017)MAE22.76—Unverified
6One-Look Regression (2016)MAE21.88—Unverified
7RetinaNet (2018)MAE16.62—Unverified
8CounTX (uses arbitrary text input to specify object to count, used "the cars" for CARPK)MAE8.13—Unverified
9Soft-IoU + EM-Merger unitMAE6.77—Unverified
10VLCounterMAE6.46—Unverified
#ModelMetricClaimedVerifiedStatus
1Fast-RCNNm-reIRMSE-nz0.85—Unverified
2glance-noft-2Lm-reIRMSE-nz0.73—Unverified
3LC-PSPNetm-reIRMSE-nz0.7—Unverified
4Seq-sub-ft-3x3m-reIRMSE-nz0.68—Unverified
5ensm-reIRMSE-nz0.65—Unverified
6Supervised Density Mapm-reIRMSE-nz0.61—Unverified
7LC-ResFCNm-reIRMSE-nz0.61—Unverified
8OmnicountmRMSE0—Unverified
#ModelMetricClaimedVerifiedStatus
1Aso-sub-ft-3x3m-reIRMSE0.24—Unverified
2glance-ft-2Lm-reIRMSE0.23—Unverified
3Fast-RCNNm-reIRMSE0.2—Unverified
4LC-ResFCNm-reIRMSE0.19—Unverified
5Seq-sub-ft-3x3m-reIRMSE0.18—Unverified
6Supervised Density Mapm-reIRMSE0.18—Unverified
7ensm-reIRMSE0.18—Unverified
#ModelMetricClaimedVerifiedStatus
1SMoLA-PaLI-X SpecialistAccuracy77.1—Unverified
2PaLI-X-VPDAccuracy76.6—Unverified
3SMoLA-PaLI-X Generalist (0 shot)Accuracy70.7—Unverified
4MoVie-ResNeXtAccuracy56.8—Unverified
5RCNAccuracy56.2—Unverified
6MoVieAccuracy54.1—Unverified
#ModelMetricClaimedVerifiedStatus
1SMoLA-PaLI-X SpecialistAccuracy86.3—Unverified
2PaLI-X-VPDAccuracy86.2—Unverified
3SMoLA-PaLI-X Generalist (0 shot)Accuracy83.3—Unverified
4MoVie-ResNeXtAccuracy74.9—Unverified
5RCNAccuracy71.8—Unverified
6MoVieAccuracy70.8—Unverified
#ModelMetricClaimedVerifiedStatus
1MoVie-ResNeXtAccuracy64—Unverified
2MoVieAccuracy61.2—Unverified
3RCNAccuracy60.3—Unverified
#ModelMetricClaimedVerifiedStatus
1CEOESmRMSE0.42—Unverified
2ILCmRMSE0.29—Unverified
3TFOCmRMSE0.01—Unverified
#ModelMetricClaimedVerifiedStatus
1OmnicountmRMSE0—Unverified
#ModelMetricClaimedVerifiedStatus
1GauNet (ResNet-50)MAE2.1—Unverified