Pith. sign in

REVIEW 7 cited by

FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval

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 2503.21309 v1 pith:OMZ3LIVN submitted 2025-03-27 cs.CV cs.AI

Zixu Li , Zhiheng Fu , Yupeng Hu , Zhiwei Chen , Haokun Wen , Liqiang Nie This is my paper
classification cs.CVcs.AI
keywords fine-grainedmodificationretrievalfinecirdatasetsimagetextcaptures
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Composed Image Retrieval (CIR) facilitates image retrieval through a multimodal query consisting of a reference image and modification text. The reference image defines the retrieval context, while the modification text specifies desired alterations. However, existing CIR datasets predominantly employ coarse-grained modification text (CoarseMT), which inadequately captures fine-grained retrieval intents. This limitation introduces two key challenges: (1) ignoring detailed differences leads to imprecise positive samples, and (2) greater ambiguity arises when retrieving visually similar images. These issues degrade retrieval accuracy, necessitating manual result filtering or repeated queries. To address these limitations, we develop a robust fine-grained CIR data annotation pipeline that minimizes imprecise positive samples and enhances CIR systems' ability to discern modification intents accurately. Using this pipeline, we refine the FashionIQ and CIRR datasets to create two fine-grained CIR datasets: Fine-FashionIQ and Fine-CIRR. Furthermore, we introduce FineCIR, the first CIR framework explicitly designed to parse the modification text. FineCIR effectively captures fine-grained modification semantics and aligns them with ambiguous visual entities, enhancing retrieval precision. Extensive experiments demonstrate that FineCIR consistently outperforms state-of-the-art CIR baselines on both fine-grained and traditional CIR benchmark datasets. Our FineCIR code and fine-grained CIR datasets are available at https://github.com/SDU-L/FineCIR.git.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

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

  1. Dual Latent Memory for Visual Multi-agent System

    cs.AI 2026-01 conditional novelty 6.0 of 10

    L2-VMAS replaces text-based inter-agent communication in visual multi-agent systems with decoupled latent perception and thinking memories, improving accuracy by 2.7–5.4% and cutting token use by 21.3–44.8%.

  2. Language-Guided Long Horizon Manipulation with LLM-based Planning and Visual Perception

    cs.RO 2025-09 conditional novelty 5.0 of 10

    A robot folds cloth from spoken language by decomposing instructions with GPT-4o and grounding each step with a SigLIP2-based pick-and-place perception module.

  3. Dual form Complementary Masking for Domain-Adaptive Image Segmentation

    cs.CV 2025-07 reject novelty 5.0 of 10

    The paper proposes complementary masking consistency for UDA segmentation and reports empirical gains, but its theoretical proof contains a direct internal contradiction.

  4. CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentation

    eess.IV 2025-06 conditional novelty 5.0 of 10

    A text-guided SAM2 variant with cross-modal attention, semantic prompt generation, and a similarity-sorted memory bank achieves top Dice and surface scores on seven public multi-organ CT datasets.

  5. Radial Neighborhood Smoothing Recommender System

    cs.LG 2025-07 reject novelty 4.0 of 10

    The proposed Radial Neighborhood Estimator uses SVD-based distance estimation with a variance correction and kernel smoothing over radial neighbors, but the consistency theorems are not supported by the supplied proofs.

  6. A Multimodal Deep Learning Framework for Early Diagnosis of Liver Cancer via Optimized BiLSTM-AM-VMD Architecture

    cs.LG 2025-09 reject novelty 3.0 of 10

    The paper claims a BiLSTM-AM-VMD model achieves AUC 0.963 for early HCC diagnosis, but the evidence is undermined by contradictory dataset descriptions and missing artifacts.

  7. Multi-Modal Machine Learning Framework for Predicting Early Recurrence of Brain Tumors Using MRI and Clinical Biomarkers

    cs.LG 2025-09 reject novelty 3.0 of 10

    XGBoost combining MRI radiomics and clinical biomarkers reportedly reaches C-index 0.782 for early brain tumor recurrence, but the paper's methods describe a liver-cancer cohort and no evaluation of its claimed tempor...

Pith tools