mlsanityData to 14 Oct 2026

CountGD++: Generalized Prompting for Open-World Counting

arXiv 2512.23351 ↗First posted 29 Dec 2025cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

The flexibility and accuracy of methods for automatically counting objects in images and videos are limited by the way the object can be specified. While existing methods allow users to describe the target object with text and visual examples, the visual examples must be manually annotated inside the image, and there is no way to specify what not to count. To address these gaps, we introduce novel capabilities that expand how the target object can be specified. Specifically, we extend the prompt to enable what not to count to be described with text and/or visual examples, introduce the concept of `pseudo-exemplars' that automate the annotation of visual examples at inference, and extend counting models to accept visual examples from both natural and synthetic external images. We also use our new counting model, CountGD++, as a vision expert agent for an LLM. Together, these contributions expand the prompt flexibility of multi-modal open-world counting and lead to significant improvements in accuracy, efficiency, and generalization across multiple datasets. Code is available at https://github.com/niki-amini-naieni/CountGDPlusPlus.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 46 of its 65 references that are in the map. First posted on arXiv 29 Dec 2025.

Builds on

46 of 65 references.

References · 46

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2023Segment Anythingcited by 8,234
  6. 2017Mask R-CNNcited by 7,277
  7. 2025Qwen2.5-VL Technical Reportcited by 5,587
  8. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  9. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  10. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  11. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 603
  12. 2025Seed1.5-VL Technical Reportcited by 373
34 more
  1. 2023Scaling Open-Vocabulary Object Detectioncited by 343
  2. 2024VideoAgent: Long-form Video Understanding with Large Language Model as Agentcited by 332
  3. 2024Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Modelscited by 329
  4. 2022Simple Open-Vocabulary Object Detection with Vision Transformerscited by 305
  5. 2021Towards Open World Object Detectioncited by 297
  6. 2024Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Modelscited by 268
  7. 2014Towards Open World Recognitioncited by 226
  8. 2017Drone-based Object Counting by Spatially Regularized Regional Proposal Networkcited by 156
  9. 2021Learning To Count Everythingcited by 150
  10. 2016A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learningcited by 86
  11. 2023CLIP-Count: Towards Text-Guided Zero-Shot Object Countingcited by 83
  12. 2022CounTR: Transformer-based Generalised Visual Countingcited by 79
  13. 2025Vision-Language Models Do Not Understand Negationcited by 72
  14. 2022A Low-Shot Object Counting Network With Iterative Prototype Adaptationcited by 65
  15. 2024CountGD: Multi-Modal Open-World Countingcited by 59
  16. 2023Zero-shot Object Countingcited by 57
  17. 2022Few-shot Object Counting and Detectioncited by 55
  18. 2024Understanding the Impact of Negative Prompts: When and How Do They Take Effect?cited by 51
  19. 2024DAVE -- A Detect-and-Verify Paradigm for Low-Shot Countingcited by 49
  20. 2023Modular Visual Question Answering via Code Generationcited by 48
  21. 2023VLCounter: Text-aware Visual Representation for Zero-Shot Object Countingcited by 45
  22. 2024Learning Transferable Negative Prompts for Out-of-Distribution Detectioncited by 43
  23. 2023Open-world Text-specified Object Countingcited by 41
  24. 2023Point, Segment and Count: A Generalized Framework for Object Countingcited by 39
  25. 2024Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillationcited by 37
  26. 2023Training-free Object Counting with Promptscited by 34
  27. 2020Completely Self-Supervised Crowd Counting via Distribution Matchingcited by 22
  28. 2024A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentationcited by 21
  29. 2024OmniCount: Multi-label Object Counting with Semantic-Geometric Priorscited by 16
  30. 2024Mind the Prompt: A Novel Benchmark for Prompt-based Class-Agnostic Countingcited by 11
  31. 2025Open-World Object Counting in Videoscited by 11
  32. 2025Exploring Contextual Attribute Density in Referring Expression Countingcited by 10
  33. 2025Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluationcited by 7
  34. 2025Demystifying Numerosity in Diffusion Models -- Limitations and Remediescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026Count Anything at Any Granularitycited by 1
  2. 2026The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Countingcited by 1
  3. 2026AdaCount: Training-Free Similarity-Guided Spatial and Feature Adaptation for Zero-Shot Object Countingcited by 1
  4. 2026Are Image Generators Zero-Shot Perceivers? A Rigorous Evaluationcited by 1
  5. 2026Count Anythingcited by 0
  6. 2026ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generationcited by 0
  7. 2026RECOUNT: Reference-guided Counting with Synthetic Visual Exemplarscited by 0
  8. 2026Object Counting Across Modalities: Taxonomies, Benchmarks, Applications, and Open Challengescited by 0