Paper Citation Record · LEDGER

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts

As of 19 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 1 inbound Pith citation observation for arXiv:2506.04999.

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

pith.paper-citation-record.v1
2506.04999 v1

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:34:03.546459Z

measured 59 of 59 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-12T05:51:08.895411Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

58 of 58 outbound references displayed

verified exact0
verified fuzzy50
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 19b7fbcd-7a0e-47a9-91ed-980b563b0049 · outbound

This paper cites Word spotting and recognition with embedded attributes.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Word spotting and recognition with embedded attributes

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:05.370790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8d125acd-11c2-4932-a0cd-de2d8ac1427c · outbound

This paper cites Integrating scene text and visual appearance for fine-grained image classification.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Integrating scene text and visual appearance for fine-grained image classification

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:05.355245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 725917d1-32b0-4003-9e5d-048aed65f324 · outbound

This paper cites Composed image retrieval using contrastive learning and task-oriented clip-based features.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Composed image retrieval using contrastive learning and task-oriented clip-based features

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:05.337860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6ab1ddc1-e6d6-446d-bdd9-94d793bc8a99 · outbound

This paper cites The devil is in fine-tuning and long-tailed problems: A new benchmark for scene text detection.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts The devil is in fine-tuning and long-tailed problems: A new benchmark for scene text detection

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:05.322419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a9ecefec-40c7-452c-aad5-9d1010d67940 · outbound

This paper cites an unresolved cited work.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:34:05.306842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 67c6b5b4-6b3e-42ad-893f-1766c4ca0c3c · outbound

This paper cites an unresolved cited work.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:34:05.289434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7326a63d-173c-49bd-aa02-dfb3177080ea · outbound

This paper cites K., Gomez, L., Karatzas, D., and Valveny, E.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts K., Gomez, L., Karatzas, D., and Valveny, E

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:05.271142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d77fb228-da44-412e-94e4-46a9daa8bf59 · outbound

This paper cites Lsde: Levenshtein space deep embedding for query-by-string word spotting.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Lsde: Levenshtein space deep embedding for query-by-string word spotting

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:05.254671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 967183e2-ec4b-478b-b0b5-0e00341d3fc8 · outbound

This paper cites Single shot scene text retrieval.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Single shot scene text retrieval

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:05.239639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9c1f59e1-cfab-4ed4-b07b-eac0c396bfaa · outbound

This paper cites Synthetic data for text localisation in natural images.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Synthetic data for text localisation in natural images

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:05.224142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7c64ac95-9dbd-4e08-8110-2a4d52a8a483 · outbound

This paper cites Bridging the gap between end-to-end and two-step text spotting.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Bridging the gap between end-to-end and two-step text spotting

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:05.206480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 55c12d19-33a6-49b6-895d-5f8a1cf31640 · outbound

This paper cites Reading text in the wild with convolutional neural networks.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Reading text in the wild with convolutional neural networks

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:05.052301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b8e8a25f-ff91-4dea-a15b-86c46a14cfcd · outbound

This paper cites an unresolved cited work.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:34:05.037243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8ae8f700-b529-44ad-89e1-e9cc258ebd46 · outbound

This paper cites Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:05.021425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 09dc5171-96f9-4610-aa75-d5a0d8a44054 · outbound

This paper cites Mask textspotter v3: Segmentation proposal network for robust scene text spotting.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Mask textspotter v3: Segmentation proposal network for robust scene text spotting

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:05.003389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9bd96913-088a-4be8-9437-307444e8fa51 · outbound

This paper cites Parrot Captions Teach CLIP to Spot Text.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Parrot Captions Teach CLIP to Spot Text

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T10:33:57.108940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0e84eb5-63f5-4cce-abd7-ad5238686dfc · outbound

This paper cites Abcnet: Real-time scene text spotting with adaptive bezier-curve network.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Abcnet: Real-time scene text spotting with adaptive bezier-curve network

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.986619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3394719f-ae53-4136-8686-c37337185e42 · outbound

This paper cites Clip4clip: An empirical study of clip for end-to-end video clip retrieval and captioning.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Clip4clip: An empirical study of clip for end-to-end video clip retrieval and captioning

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.968964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a6f5e436-a131-431e-9444-31d7188beb4e · outbound

This paper cites Visual and semantic guided scene text retrieval.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Visual and semantic guided scene text retrieval

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.952098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1290ac95-3c8d-498c-8fba-e6136ab610f2 · outbound

This paper cites Arbitrary reading order scene text spotter with local semantics guidance.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Arbitrary reading order scene text spotter with local semantics guidance

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.935312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ca4dca92-f899-4c60-a392-a58de153c75d · outbound

This paper cites TextBlockV2 : Towards precise-detection-free scene text spotting with pre-trained language model.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts TextBlockV2 : Towards precise-detection-free scene text spotting with pre-trained language model

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.917434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 67d2aaff-0a84-42d9-97d3-b142b693894c · outbound

This paper cites F., Gomez, L., and Karatzas, D.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts F., Gomez, L., and Karatzas, D

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.896657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation adf89f9b-e367-484c-a52c-d6b0c15db0ad · outbound

This paper cites Real-time lexicon-free scene text retrieval.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Real-time lexicon-free scene text retrieval

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.879134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9a27e253-a92b-4800-904f-084ab52987a0 · outbound

This paper cites Disentangling visual and written concepts in clip.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Disentangling visual and written concepts in clip

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.861704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0fd555bc-2131-47b9-91f9-7effe32c3009 · outbound

This paper cites Word spotting and recognition via a joint deep embedding of image and text.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Word spotting and recognition via a joint deep embedding of image and text

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.845036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 494d4877-9c19-4f90-8df1-26544445e99c · outbound

This paper cites Image retrieval using textual cues.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Image retrieval using textual cues

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.824192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 43fdc69e-fd6a-441f-96d4-c51a7af8dabd · outbound

This paper cites Text perceptron: Towards end-to-end arbitrary-shaped text spotting.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Text perceptron: Towards end-to-end arbitrary-shaped text spotting

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.800334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 33c759fe-ff90-40e3-899c-695a9e8c2622 · outbound

This paper cites SEED : Semantics enhanced encoder-decoder framework for scene text recognition.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts SEED : Semantics enhanced encoder-decoder framework for scene text recognition

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.777621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 26669bf7-34ac-4dc0-9a7a-bb1f1fda7196 · outbound

This paper cites PIMNet : A parallel, iterative and mimicking network for scene text recognition.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts PIMNet : A parallel, iterative and mimicking network for scene text recognition

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.757899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c812f105-6f83-4140-90a6-86a2dcbe04b7 · outbound

This paper cites W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.739445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 29099d5c-5d3b-49fd-8f8e-2455b3566cfd · outbound

This paper cites Pic2word: Mapping pictures to words for zero-shot composed image retrieval.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Pic2word: Mapping pictures to words for zero-shot composed image retrieval

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.721235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3193a5a6-dac0-43c3-8005-6a8100dfc4d0 · outbound

This paper cites Laion-5b: An open large-scale dataset for training next generation image-text models.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Laion-5b: An open large-scale dataset for training next generation image-text models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.700159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d5948cc0-dc9a-4651-a9cd-0024258b43a4 · outbound

This paper cites LDP : Generalizing to multilingual visual information extraction by language decoupled pretraining.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts LDP : Generalizing to multilingual visual information extraction by language decoupled pretraining

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.677264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 36a0a6c3-4e20-452e-bf5d-7be37736e743 · outbound

This paper cites and Yang, S.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts and Yang, S

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.655824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bb09becc-0361-4559-98c8-9d9091963ae1 · outbound

This paper cites What does clip know about a red circle? visual prompt engineering for vlms.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts What does clip know about a red circle? visual prompt engineering for vlms

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.633680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3b8b2a52-613f-4fa0-b765-416e8b945def · outbound

This paper cites Perceiving ambiguity and semantics without recognition: An efficient and effective ambiguous scene text detector.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Perceiving ambiguity and semantics without recognition: An efficient and effective ambiguous scene text detector

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.612274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7582d782-bcc6-4193-a654-25ce888f7cbe · outbound

This paper cites Visual Text Processing: A Comprehensive Review and Unified Evaluation.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Visual Text Processing: A Comprehensive Review and Unified Evaluation

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:00.263138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8afb498f-98dd-4c1a-a222-54ea38e52ad3 · outbound

This paper cites Text siamese network for video textual keyframe detection.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Text siamese network for video textual keyframe detection

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.592910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0b702319-8127-42fb-ab6a-b59835d7f895 · outbound

This paper cites ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:00.550841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bab5433-11c0-4b08-a4fa-649066da084a · outbound

This paper cites Alpha-clip: A clip model focusing on wherever you want.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Alpha-clip: A clip model focusing on wherever you want

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.567265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6208d676-89e0-4553-b63e-49921c64e1d4 · outbound

This paper cites Scene text retrieval via joint text detection and similarity learning.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Scene text retrieval via joint text detection and similarity learning

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.550844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 98b0e76a-9b63-4201-90b8-5e6fa7dcc40b · outbound

This paper cites and Belongie, S.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts and Belongie, S

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.533936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0230ef5f-da59-4ce7-8441-fa8aa021f513 · outbound

This paper cites TPSNet : Reverse thinking of thin plate splines for arbitrary shape scene text representation.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts TPSNet : Reverse thinking of thin plate splines for arbitrary shape scene text representation

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.509147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 840cf871-9a2c-4b19-9ba7-38f7781a32d6 · outbound

This paper cites TextBlock : Towards scene text spotting without fine-grained detection.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts TextBlock : Towards scene text spotting without fine-grained detection

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.492576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 05d1d8c1-31d6-442f-aadd-fb08bb350c8a · outbound

This paper cites Visual matching is enough for scene text retrieval.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Visual matching is enough for scene text retrieval

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.475436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d868ad56-f596-4837-bcc9-a5ae60c5d046 · outbound

This paper cites and Brun, A.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts and Brun, A

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.452994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7787ef5a-3a50-4eac-af92-27cb0176e811 · outbound

This paper cites Bridging semantic gaps for language-supervised semantic segmentation.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Bridging semantic gaps for language-supervised semantic segmentation

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.434978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f1967491-8899-4f2d-85a9-d16e43bfea0e · outbound

This paper cites Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:01.936414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d672d0c0-2f1d-46bb-81ac-1a78f2cbf2ed · outbound

This paper cites IPAD : Iterative, parallel, and diffusion-based network for scene text recognition.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts IPAD : Iterative, parallel, and diffusion-based network for scene text recognition

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.415705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 329c6e7e-26df-4a66-af7f-658495b5cf18 · outbound

This paper cites Turning a clip model into a scene text detector.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Turning a clip model into a scene text detector

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.393041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ebecad2c-826a-4bac-b244-797a5e3837c7 · outbound

This paper cites Beyond OCR + VQA : Towards end-to-end reading and reasoning for robust and accurate textvqa.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Beyond OCR + VQA : Towards end-to-end reading and reasoning for robust and accurate textvqa

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.372619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0b96d416-462b-4063-8ac6-9952abdee07c · outbound

This paper cites Focus, distinguish, and prompt: Unleashing CLIP for efficient and flexible scene text retrieval.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Focus, distinguish, and prompt: Unleashing CLIP for efficient and flexible scene text retrieval

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.345456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3cec4b21-caac-42c8-99a8-3e5dc85313e0 · outbound

This paper cites TextCtrl : Diffusion-based scene text editing with prior guidance control.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts TextCtrl : Diffusion-based scene text editing with prior guidance control

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.314377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f22ec2ea-6ebf-4912-a5cb-199b77e2db53 · outbound

This paper cites Icdar 2019 robust reading challenge on reading chinese text on signboard.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Icdar 2019 robust reading challenge on reading chinese text on signboard

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.285972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 108619cb-9a22-4768-9e8b-9aa182cd25cf · outbound

This paper cites Linguistics-aware masked image modeling for self-supervised scene text recognition.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts Linguistics-aware masked image modeling for self-supervised scene text recognition

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.257084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2457c7fe-0a2f-45d4-bcff-032fe5305315 · outbound

This paper cites C., and Dai, B.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts C., and Dai, B

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:04.142177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7934d71d-86ab-4dcf-8d81-aed4847aa900 · outbound

This paper cites C., and Liu, Z.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts C., and Liu, Z

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:03.908191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ca56f343-47b7-4f98-b6f0-f9d6456a2e1a · outbound

This paper cites write newline.

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts write newline

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:03.546459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation dad30a42-fba3-4c1c-b7a1-f2edd0a12c4e · inbound

MORE: A Multilingual Document Parsing Benchmark and Evaluation cites this paper.

MORE: A Multilingual Document Parsing Benchmark and Evaluation Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-12T05:51:08.895411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.