Paper Citation Record · LEDGER

Aesthetic Image Captioning with Saliency Enhanced MLLMs

As of 15 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2509.04378.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2509.04378 v3

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T10:15:50.308478Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

46 of 46 outbound references displayed

verified exact22
verified fuzzy8
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6f11d397-4e42-49ab-95f9-492a20b517cc · outbound

This paper cites A model of aesthetic appreciationandaestheticjudgments,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs A model of aesthetic appreciationandaestheticjudgments,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T10:15:50.109062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e9b9129-4b57-4aae-9b67-5b3d269be6ab · outbound

This paper cites Prospectsforacognitiveneuroscienceofvisualaesthetics,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Prospectsforacognitiveneuroscienceofvisualaesthetics,

Reference 2

Resolution: verified exact; doi, observed 2026-08-05T10:15:50.415002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation aa2495ca-a659-4b13-a117-07f58717b411 · outbound

This paper cites Comment-guided semantics-awareimageaestheticsassessment,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Comment-guided semantics-awareimageaestheticsassessment,

Reference 3

Resolution: metadata mismatch; raw_fallback, observed 2026-08-05T10:15:54.700905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a1b23c3b-0495-43b3-bb10-468f20e8cdbf · outbound

This paper cites Confidence-based dynamic cross-modal memory network for image aesthetic assessment,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Confidence-based dynamic cross-modal memory network for image aesthetic assessment,

Reference 5

Resolution: metadata mismatch; raw_fallback, observed 2026-08-05T10:15:54.575311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation dfc814f8-c62b-4cb5-a246-fece044839ed · outbound

This paper cites Aesclip: Multi-attribute contrastive learning for image aesthetics assessment,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Aesclip: Multi-attribute contrastive learning for image aesthetics assessment,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T10:15:50.132876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5046b7c-fc8b-42a7-a329-d100ed516484 · outbound

This paper cites Image aesthetics assessment with attribute-assisted multimodal memory network,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Image aesthetics assessment with attribute-assisted multimodal memory network,

Reference 7

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:54.419039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation af503ce6-6cdb-46a9-acf1-0d76a0eace6b · outbound

This paper cites Enriched Image Captioning based on Knowledge Divergence and Focus,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Enriched Image Captioning based on Knowledge Divergence and Focus,

Reference 8

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:54.242750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation edff4110-ea54-4803-91ac-138a3e6a5012 · outbound

This paper cites Aesthetic image captioning from weakly-labelled photographs,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Aesthetic image captioning from weakly-labelled photographs,

Reference 9

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:53.931430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7de4e57f-187d-4c94-a2fa-3380edaa902b · outbound

This paper cites Generating aesthetic based critique for photographs,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Generating aesthetic based critique for photographs,

Reference 10

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:53.761312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 983ba80a-6ef3-425a-a67e-a8ce5fdd4a7f · outbound

This paper cites UNIAA: A Unified Multi-modal Image Aesthetic Assessment Baseline and Benchmark.

Aesthetic Image Captioning with Saliency Enhanced MLLMs UNIAA: A Unified Multi-modal Image Aesthetic Assessment Baseline and Benchmark

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T10:15:50.154773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0651570-d054-48a1-b57a-895d12acddbd · outbound

This paper cites Studyon the Image Aesthetic Assessment Based on Saliency and Attention,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Studyon the Image Aesthetic Assessment Based on Saliency and Attention,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:15:54.831787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 177129bc-0531-4aa3-9604-7c97d7f39b1b · outbound

This paper cites Eat: An enhancer for aesthetics-oriented transformers,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Eat: An enhancer for aesthetics-oriented transformers,

Reference 13

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:53.559324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8d88295b-f7d6-46e7-b826-4963ca5558df · outbound

This paper cites Multi-Modality Multi-Attribute Contrastive Pre-Training for Image Aesthetics Computing,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Multi-Modality Multi-Attribute Contrastive Pre-Training for Image Aesthetics Computing,

Reference 14

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:53.341093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e898eb77-c809-420a-b88f-2f6530d5b01d · outbound

This paper cites Aesthetic critiques generation for photos,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Aesthetic critiques generation for photos,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T10:15:50.171559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cf81da5-bbe3-484d-8ae7-3d72392ec80a · outbound

This paper cites Neural aesthetic image reviewer,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Neural aesthetic image reviewer,

Reference 16

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:52.967030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0be009b3-4e2e-4000-9190-cdf3aaf1e701 · outbound

This paper cites Latent dirichlet allocation,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Latent dirichlet allocation,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:15:54.817454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2033a8ee-6b0b-4c0b-8be1-59e90cf2d985 · outbound

This paper cites Aesthetic Attributes Assessment of Images,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Aesthetic Attributes Assessment of Images,

Reference 18

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:52.749788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d413741d-c9f9-40ea-a8f8-e61fdbbfa0d7 · outbound

This paper cites Towards personalized aesthetic image caption,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Towards personalized aesthetic image caption,

Reference 19

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:52.542569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a5fe8234-6e7b-4c1d-9dba-0f7f394a62ff · outbound

This paper cites Understanding aesthetics with language: A photo critique dataset for aesthetic assessment,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Understanding aesthetics with language: A photo critique dataset for aesthetic assessment,

Reference 20

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:52.353366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5112d0de-53cd-4969-9089-3a4d41121a0c · outbound

This paper cites Aesexpert: Towards multi-modality foundation model for image aesthetics perception,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Aesexpert: Towards multi-modality foundation model for image aesthetics perception,

Reference 30

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:52.154196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b17190f5-f994-4969-b1cc-13bd0668cd91 · outbound

This paper cites Saliency-enhanced image aesthetics class prediction,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Saliency-enhanced image aesthetics class prediction,

Reference 31

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:51.999098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b36771c3-7a0c-4686-9a30-a4fde45023e3 · outbound

This paper cites Research on Image Aesthetic Evaluation using Image Scene and Saliency Information,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Research on Image Aesthetic Evaluation using Image Scene and Saliency Information,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:15:54.802642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 15b830e8-0db4-48f3-b9b0-4617787b8936 · outbound

This paper cites Research on image quality assessment and improvement algorithm based on aesthetics,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Research on image quality assessment and improvement algorithm based on aesthetics,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:15:54.786835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7e62b708-cc44-4d22-b0c2-c0cdf586e280 · outbound

This paper cites Imageaestheticsassessment based on multi-stream CNN architecture and saliency features,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Imageaestheticsassessment based on multi-stream CNN architecture and saliency features,

Reference 34

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:51.820763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f87e9ba4-8e15-4375-bf0a-f79379a9b89f · outbound

This paper cites Co-salient object detectionwithco-representationpurification,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Co-salient object detectionwithco-representationpurification,

Reference 35

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:51.622802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e1ac556f-088c-4b9e-9fc0-fa60b5e5f8cf · outbound

This paper cites Associating inter-image salient instances for weakly supervised semantic segmentation,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Associating inter-image salient instances for weakly supervised semantic segmentation,

Reference 36

Resolution: verified exact; doi, observed 2026-08-05T10:15:50.392512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0cb6c15e-8831-4993-bce9-f71d70e7a4ab · outbound

This paper cites Texture-guidedsaliency distillingfor unsupervisedsalientobjectdetection,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Texture-guidedsaliency distillingfor unsupervisedsalientobjectdetection,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T10:15:50.226237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51f568d5-315a-4e29-a447-415ce2c8273c · outbound

This paper cites Human detection using a mobile platform and novel features derived from a visual saliency mechanism,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Human detection using a mobile platform and novel features derived from a visual saliency mechanism,

Reference 38

Resolution: verified exact; doi, observed 2026-08-05T10:15:50.377998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 07a8bc35-86bd-40f9-8883-dc8755b5c61c · outbound

This paper cites Rethinking Image AestheticsAssessment:Models,DatasetsandBenchmarks,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Rethinking Image AestheticsAssessment:Models,DatasetsandBenchmarks,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-05T10:15:50.235093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93ee8013-6225-4958-9218-d895a46981e5 · outbound

This paper cites ‘Special Relativity’ of Image Aesthetics Assessment: a Preliminary Empirical Perspective,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs ‘Special Relativity’ of Image Aesthetics Assessment: a Preliminary Empirical Perspective,

Reference 40

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:51.356940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4e5b42c3-1eff-4485-8534-549d3254f274 · outbound

This paper cites How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites.

Aesthetic Image Captioning with Saliency Enhanced MLLMs How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T10:15:50.243414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0207f54-105a-452c-8826-2e21c06192cd · outbound

This paper cites an unresolved cited work.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-05T10:15:54.771981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f14f4882-d36e-4e59-aea2-dcf53c76e976 · outbound

This paper cites InternLM2 Technical Report.

Aesthetic Image Captioning with Saliency Enhanced MLLMs InternLM2 Technical Report

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-05T10:15:50.252054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e9a5f02-9040-4a22-96e3-4f73bf33597d · outbound

This paper cites Layercam: Exploring hierarchical class activation maps for localization,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Layercam: Exploring hierarchical class activation maps for localization,

Reference 44

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:51.149303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 378f623b-3cb7-441f-a5a5-92615f60a3f9 · outbound

This paper cites Bleu: a method for automatic evaluation of machine translation,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Bleu: a method for automatic evaluation of machine translation,

Reference 45

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:50.976914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b842ae43-fce6-474b-98e0-49c11cde3333 · outbound

This paper cites Rouge: A package for automatic evaluation of summaries,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Rouge: A package for automatic evaluation of summaries,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:15:54.757754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 53beb283-050a-423d-adf2-fb476ca875a0 · outbound

This paper cites METEOR: An automatic metric for MT evaluation with improved correlation with human judgments,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs METEOR: An automatic metric for MT evaluation with improved correlation with human judgments,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:15:54.743961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 72945644-bc34-4efa-a7d8-9508602fe0ae · outbound

This paper cites Cider: Consensus-based imagedescriptionevaluation,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Cider: Consensus-based imagedescriptionevaluation,

Reference 48

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:50.804643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 04c925cf-71f6-484e-9e63-028be0ae81ef · outbound

This paper cites Spice: Semantic propositional image caption evaluation,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Spice: Semantic propositional image caption evaluation,

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-05T10:15:50.277593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d278ab02-5f3e-467d-8b7e-ffa54c9f4d57 · outbound

This paper cites [Online].

Aesthetic Image Captioning with Saliency Enhanced MLLMs [Online]

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:15:54.729336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6a81dc45-306c-4d5a-9d07-c195f26cfae1 · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-05T10:15:50.285815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ac92598-d328-4961-9832-cf950c168724 · outbound

This paper cites The Llama 3 Herd of Models.

Aesthetic Image Captioning with Saliency Enhanced MLLMs The Llama 3 Herd of Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-05T10:15:50.290461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9302a986-4fef-4103-a691-a55c9e1c126c · outbound

This paper cites Improved Baselines with Visual InstructionTuning,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Improved Baselines with Visual InstructionTuning,

Reference 53

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-05T10:15:50.615011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0913bc48-a0bf-460e-a289-d19558f33f32 · outbound

This paper cites mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models.

Aesthetic Image Captioning with Saliency Enhanced MLLMs mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-05T10:15:50.299374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9d83025-6180-41d2-896d-ad21f1ed39d8 · outbound

This paper cites Microsoft COCO Captions: Data Collection and Evaluation Server.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Microsoft COCO Captions: Data Collection and Evaluation Server

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-05T10:15:50.303995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6062d0bf-4da3-4113-84d4-ed2aef6d3676 · outbound

This paper cites Show and tell: A neural image caption generator,.

Aesthetic Image Captioning with Saliency Enhanced MLLMs Show and tell: A neural image caption generator,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:15:54.714965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

No inbound Pith citation observations are available.