Pith. sign in

REVIEW 5 cited by

Open-world Text-specified Object Counting

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2306.01851 v2 pith:DSQ3WP3E submitted 2023-06-02 cs.CV

Niki Amini-Naieni , Kiana Amini-Naieni , Tengda Han , Andrew Zisserman This is my paper · ORCID
classification cs.CV
keywords objectclasscountingcountxtextopen-worlddescriptionfsc-147
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Our objective is open-world object counting in images, where the target object class is specified by a text description. To this end, we propose CounTX, a class-agnostic, single-stage model using a transformer decoder counting head on top of pre-trained joint text-image representations. CounTX is able to count the number of instances of any class given only an image and a text description of the target object class, and can be trained end-to-end. In addition to this model, we make the following contributions: (i) we compare the performance of CounTX to prior work on open-world object counting, and show that our approach exceeds the state of the art on all measures on the FSC-147 benchmark for methods that use text to specify the task; (ii) we present and release FSC-147-D, an enhanced version of FSC-147 with text descriptions, so that object classes can be described with more detailed language than their simple class names. FSC-147-D and the code are available at https://www.robots.ox.ac.uk/~vgg/research/countx.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Depth-Guided Video Object Counting in Crowded Scenes

    cs.CV 2026-08 conditional novelty 7.0 of 10

    A RGB-D video counting method with depth-based feature fusion and occlusion-adaptive tracking reduces counting errors in crowded scenes, validated on a new dataset.

  2. Vision as Unified Multimodal Generation

    cs.CV 2026-07 conditional novelty 7.0 of 10

    A single unified multimodal model matches leading task-specialized vision systems across detection, segmentation, dense geometry, and multi-view 3D by casting all outputs as native text or image generation.

  3. Improving Contrastive Learning for Referring Expression Counting

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A contrastive training loss that groups the image regions most similar to a referring expression, using the true object count, improves counting accuracy by over 22% on REC-8K.

  4. Single Domain Generalization for Few-Shot Counting via Universal Representation Matching

    cs.CV 2025-05 conditional novelty 6.0 of 10

    URM distills CLIP vision-language representations into learnable prototypes for few-shot counting, improving single-domain generalization on unseen datasets.

  5. Expanding Zero-Shot Object Counting with Rich Prompts

    cs.CV 2025-05 conditional novelty 5.0 of 10

    RichCount improves zero-shot object counting by enriching text prompts with MLLM-generated descriptions and aligning them to CLIP visual features, achieving state-of-the-art mean absolute error on three counting benchmarks.

Pith tools