Pith. sign in

Paper Citation Record · LEDGER

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection

As of 9 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 2 inbound Pith citation observations for arXiv:2505.15649.

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

pith.paper-citation-record.v1
2505.15649 v1

Coverage vector

measured 52 of 52 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:17:18.959429Z

measured 54 of 54 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T18:23:26.515073Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-15T04:55:03.034414Z

Reference resolution

52 of 52 outbound references displayed

  • verified exact0
  • verified fuzzy50
  • unresolved2
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3e832748-1fff-488b-862c-2459bdb66a63 · outbound

This paper cites SRFormer: Text detec- tion transformer with incorporated segmentation and regression.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection SRFormer: Text detec- tion transformer with incorporated segmentation and regression

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:28.603244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:14.359257Z digest=sha256:8ff55abb3b7d05a6b5ddc82064a71b977503b1d7fc8a4dcbf853c1e7df805627

Observation 33ad2b9f-c8b7-4b89-8178-820a2b13fd39 · outbound

This paper cites Total-text: A comprehensive dataset for scene text detection and recognition.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Total-text: A comprehensive dataset for scene text detection and recognition

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:28.279486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:14.500656Z digest=sha256:1c2f689fc1d6b5db31100d1158838185c36e4296ecc1266b0610c8f377f0a4e8

Observation 16fb59ba-bcb7-4ee2-85b3-d65714a300d4 · outbound

This paper cites Masked au- toencoders are scalable vision learners.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Masked au- toencoders are scalable vision learners

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:27.181263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:15.080487Z digest=sha256:c5f6ffa099af4a15e1f554729e4a338c1feec5f39ce0364ea51ec11702727571

Observation 0a31c737-153b-4dba-9d1a-20139f31ff7c · outbound

This paper cites Reading text in the wild with convolutional neural networks.International journal of computer vision, 116:1–20,.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Reading text in the wild with convolutional neural networks.International journal of computer vision, 116:1–20,

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:27.031768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:15.159655Z digest=sha256:2f15df40a7cec3484aacdf9e023cd7a5666b557af1f4cfe6e58475c4a2b0e5f4

Observation a85c096a-5b43-46a0-9575-98a3fd104579 · outbound

This paper cites Revisiting scene text recognition: A data perspective.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Revisiting scene text recognition: A data perspective

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:26.909250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:15.234860Z digest=sha256:4b851992362ae89bb459fc29291468d6f926ae8aae851f0cf7fbd63ea9c604bf

Observation cda10c76-4c4a-4f73-a2c2-2262d66136ba · outbound

This paper cites Textboxes++: A single-shot oriented scene text detec- tor.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Textboxes++: A single-shot oriented scene text detec- tor

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:26.457925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:15.632403Z digest=sha256:8086163ba8a5adf2109ec722871cacea79d04bdf25dae08d42144acaf29613e9

Observation 6e40b580-c763-4d87-beed-5b21e0b29784 · outbound

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

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection ABCNet: Real-time scene text spotting with adaptive bezier-curve network

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:26.084354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:15.986897Z digest=sha256:a03ae13de75a6ebfc64b412de0edd28fd7ad2e705350c4e5cf875a74d596d1d0

Observation 9733ad9a-c2bc-42c3-932b-92f63cc484ac · outbound

This paper cites Abcnet v2: Adaptive bezier-curve network for real-time end-to- end text spotting.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Abcnet v2: Adaptive bezier-curve network for real-time end-to- end text spotting

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:25.956668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:16.104892Z digest=sha256:211830c064468a6c8c6ea37a031d93dc45cda1e3710124863897968d23efe4fd

Observation 59851268-cf5a-4d0a-9cbe-e2850f551117 · outbound

This paper cites Pbformer: Capturing com- plex scene text shape with polynomial band Transformer.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Pbformer: Capturing com- plex scene text shape with polynomial band Transformer

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:25.832096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:16.220071Z digest=sha256:0eb1d7581d0dbb12016fe70c686a3b1ae2f2e1205394a4ef83083630065f5d2c

Observation 4a48cc9c-d370-44cb-85cb-aa55dbaf9ffc · outbound

This paper cites Textsnake: A flexible representation for detecting text of arbitrary shapes.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Textsnake: A flexible representation for detecting text of arbitrary shapes

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:25.680656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:16.348176Z digest=sha256:272c7a7e29dc06a6f11b14cda87b09d9705448353ffb7db2ec73c82d8ca983f3

Observation a1e14fdc-b92e-4d98-98d2-0a875d4d1aa8 · outbound

This paper cites Towards end-to-end unified scene text de- tection and layout analysis.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Towards end-to-end unified scene text de- tection and layout analysis

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:25.415930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:16.500587Z digest=sha256:37f237d395c0120723af41c513a096646d82d10a0ea4caceb55bea4251b9a1a5

Observation 0c371e8e-4ab3-43a1-834c-bee7c2ad7a80 · outbound

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

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Arbitrary reading order scene text spotter with local semantics guidance

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:25.181207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:16.638599Z digest=sha256:a66ad7b72f43f092502db5aab6dc91e11eebc660ca6a6747e28aaf28dfded063

Observation 40e85057-eac1-4a31-a501-959a0e6dc1a0 · outbound

This paper cites Icdar2019 robust reading challenge on multi-lingual scene text detection and recognition—rrc- mlt-2019.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Icdar2019 robust reading challenge on multi-lingual scene text detection and recognition—rrc- mlt-2019

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:24.888573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:16.947095Z digest=sha256:84b8131d8b74fc4d0e685db798cc5912804c275be9a336fd6a0ba63e6517a704

Observation c9f1bf67-0e73-4311-b494-b2dc71788d0e · outbound

This paper cites Towards robust real-time scene text detec- tion: From semantic to instance representation learning.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Towards robust real-time scene text detec- tion: From semantic to instance representation learning

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:24.759138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:17.053767Z digest=sha256:32a77b73bd4e061a00e4d27a1f083e5f13ab85bc5c91f8e7aa37501695f6d19b

Observation 31d15dfe-1f11-4dc5-994a-9dfb2a9f53fe · outbound

This paper cites Learning transferable visual models from nat- ural language supervision.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Learning transferable visual models from nat- ural language supervision

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T15:17:17.108597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:17:17.108597Z digest=sha256:5ba4a27accefd99218cbe54293661a0b283950aceb523c6bd4cb18ca3b6712c6

Observation c76d7402-5d7e-4241-82b6-83ce9aab1c68 · outbound

This paper cites Transformer-based text detection in the wild.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Transformer-based text detection in the wild

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:24.608083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:17.189474Z digest=sha256:ce3476ea0fbecfc818fd035312d3369e66a5ee9ad98fcbccfdcf8bf6da383a60

Observation 0441dd0b-a292-4661-8b4c-25a539445197 · outbound

This paper cites Divide rows and conquer cells: Towards structure recognition for large tables.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Divide rows and conquer cells: Towards structure recognition for large tables

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:24.502074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:17.269812Z digest=sha256:b06a15b907db96d463c06fcb049437ac8563b22c450176cbf4ec4bfe66a787a1

Observation 6d13b51b-1648-4d39-98ad-6566005ddcc5 · outbound

This paper cites Falcon-UI: Understanding GUI Before Following User Instructions.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Falcon-UI: Understanding GUI Before Following User Instructions

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-07T15:17:17.364341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:17:17.364341Z digest=sha256:0c928f2d62c8c098133ac21909e0e151ec94c35edbe7ff9f3607abefc4d9b391

Observation ed3d3a7f-641f-405c-a112-f7ca9f03fce3 · outbound

This paper cites Textocr: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Textocr: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:24.395580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:17.465026Z digest=sha256:1b2e1587d5f24a791369656fbd845e0a70d76e2847c7a34306ef3c8fc54e7270

Observation d9affe25-b0a0-42b3-b116-7ad0540c6df1 · outbound

This paper cites Lranet: Towards accurate and efficient scene text detection with low-rank approximation network.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Lranet: Towards accurate and efficient scene text detection with low-rank approximation network

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:24.257725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:17.530678Z digest=sha256:97aee9af04b6d59edffd37c5a3a3a5d2d98478477666636cdf94a94c19334fba

Observation 4a93d05d-fee7-428e-8359-0d8d9224ee9f · outbound

This paper cites Icdar 2019 competition on large-scale street view text with par- tial labeling-rrc-lsvt.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Icdar 2019 competition on large-scale street view text with par- tial labeling-rrc-lsvt

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:24.048872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:17.651438Z digest=sha256:51fec89c30af1b4863615c1de349a1436622f70aad06c5a180a33d6621aa97ef

Observation b057df53-84f0-472c-8d87-f100c0a29d45 · outbound

This paper cites Seglink++: De- tecting dense and arbitrary-shaped scene text by instance- aware component grouping.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Seglink++: De- tecting dense and arbitrary-shaped scene text by instance- aware component grouping

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:22.741664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:17.762988Z digest=sha256:efc49a521d8ecd80d140f3a57d2df1e5bebe681253991aea58e86543d7b5d058

Observation b61e9c2c-6d74-4e10-bde3-43c057c6f4ad · outbound

This paper cites Few could be better than all: Feature sampling and grouping for scene text detection.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Few could be better than all: Feature sampling and grouping for scene text detection

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:22.445281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:17.845633Z digest=sha256:eb003fd73affe2a194764783cb703b0c30f89cd548fca6d688d0bec9ee319732

Observation 7de2d136-b389-4cba-97e2-7f60072d2cea · outbound

This paper cites Domain adaptive scene text detection via subcategorization.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Domain adaptive scene text detection via subcategorization

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:22.304928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:17.937441Z digest=sha256:fcbadb2f887fef0e873471b84b59d41a8ccb44ff3b7b6447d6b0d48d26e7ec7b

Observation e02a59e0-460a-4959-89ce-b31d5fb7ad55 · outbound

This paper cites Efficient and accurate arbitrary-shaped text detection with pixel aggregation network.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Efficient and accurate arbitrary-shaped text detection with pixel aggregation network

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:22.171534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:17.993810Z digest=sha256:abb0128c5f8b683392e580de5e60715e4d9e55068466cbcbe9d8406e65b7b65a

Observation 948f75e1-526f-4d48-b6c7-997e019480eb · outbound

This paper cites TextRay: Contour-based geometric modeling for arbitrary-shaped scene text detection.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection TextRay: Contour-based geometric modeling for arbitrary-shaped scene text detection

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:22.055613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:18.027974Z digest=sha256:2c1e5de74226d3a9621f17398aa8df6d619e4722c5c7023cc7879a933c23c383

Observation 2c1f6b8d-177c-41a7-9e7f-8fc009514818 · outbound

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

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection TP- SNet: Reverse thinking of thin plate splines for arbitrary shape scene text representation

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:21.745396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:18.111044Z digest=sha256:9392054049d701678a88cc98af7bd5576ef396390552ed3ac5d685144531ef74

Observation a4e30ffd-77e3-4fa0-a520-62d2bf2294ed · outbound

This paper cites Sequential defor- mation for accurate scene text detection.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Sequential defor- mation for accurate scene text detection

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:20.596599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:18.186839Z digest=sha256:3d3973116d69061370e512422dec0df5e1f89266c242af91c49f2f39978138b8

Observation 717b3925-6848-47cb-b707-30662ae49b2b · outbound

This paper cites Language mat- ters: A weakly supervised vision-language pre-training ap- proach for scene text detection and spotting.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Language mat- ters: A weakly supervised vision-language pre-training ap- proach for scene text detection and spotting

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:20.370748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:18.220278Z digest=sha256:f851433ebcaa628a828fabb8f02c5777617df4532e5a95a05145ab869706234a

Observation f78ab305-6fd4-46cc-9887-15bb0d36f6ba · outbound

This paper cites Textfusenet: Scene text detection with richer fused fea- tures.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Textfusenet: Scene text detection with richer fused fea- tures

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:20.230174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:18.301942Z digest=sha256:ff204fb424730eba0d2d86ff3e34367aa638ac28549d42dfb6e4a285d97b728f

Observation 9149aef8-e884-4e6e-bb2e-da99fc313003 · outbound

This paper cites DPText-DETR: Towards better scene text detection with dynamic points in Transformer.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection DPText-DETR: Towards better scene text detection with dynamic points in Transformer

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:20.021031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:18.357640Z digest=sha256:b927656266462a2fa008e153b800480fff8ae719f06e891c6c5b5e19efb5154b

Observation 45d5024c-b175-45ec-ba7d-bbe80e13f6e2 · outbound

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

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Turning a CLIP model into a scene text detector

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:19.921672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:18.412844Z digest=sha256:337ff0e65c5ca49167e0301f531b3a10ef74ae9234cbd4b41ee77d7fa4f7c9be

Observation e1588613-4f43-4e12-9230-e48b5a0466df · outbound

This paper cites Filling in the blank: Rationale-augmented prompt tuning for textvqa.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Filling in the blank: Rationale-augmented prompt tuning for textvqa

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:19.764827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:18.537832Z digest=sha256:f2b2c592478f5c722410ee65f3779e4934cf31fd09e02846cfcec0c13c8f9cba

Observation 8aa4ef49-b15e-466a-9df2-972bfe89d4ad · outbound

This paper cites Ga-dan: Geometry-aware domain adaptation network for scene text detection and recognition.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Ga-dan: Geometry-aware domain adaptation network for scene text detection and recognition

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:19.622727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:18.659248Z digest=sha256:1ea60066143aa91f27a42f6ca3a4698069320e4cdb34fadd9584559521d87c54

Observation 7164784f-4f0c-4e2f-beab-45dd434c9f07 · outbound

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

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Linguistics-aware masked image modeling for self- supervised scene text recognition

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:19.506072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:18.791293Z digest=sha256:fda519def7a7f2a6906823ea445203441919bbfcb91f05c28e57be22e707c043

Observation 6b7fd035-cca3-42da-a89c-4dec68851a12 · outbound

This paper cites EAST: an efficient and accurate scene text detector.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection EAST: an efficient and accurate scene text detector

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:19.411011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:18.842386Z digest=sha256:a7990de6773a72c14b2c92dce7e0a8194a048925a5be741b9257eae7cc976e50

Observation 7cb29f70-28ad-45ee-81fc-15c2ef371427 · outbound

This paper cites Deformable DETR: de- formable transformers for end-to-end object detection.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Deformable DETR: de- formable transformers for end-to-end object detection

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:19.320688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:18.864071Z digest=sha256:b52efb18996dd84acd6ef18931afaa90597e573a36e0dcd0964845843c081120

Observation 5b935a92-afe2-48d2-858a-c5cde19b89b9 · outbound

This paper cites reen-fed.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection reen-fed

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:19.228742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:18.888979Z digest=sha256:2d8bc53f88eaaaec1219cb8f66dadb0cf54aa1eac221b8794ac90df2aeb158ec

Observation befed8b8-926e-46e5-bc68-4238d12b5833 · outbound

This paper cites D.2 Detailed Architecture of MAEDet Like other scene text detectors, MAEDet includes tree com- ponents, backbone, neck, and detection head.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection D.2 Detailed Architecture of MAEDet Like other scene text detectors, MAEDet includes tree com- ponents, backbone, neck, and detection head

Reference 100

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:19.069238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:18.959429Z digest=sha256:66bc201fccb911628eba5f73f00465e1382c51a6e372ed88e9a83d654fedb8c6

Observation 313bd219-b932-4a56-97bc-35a979ed4630 · outbound

This paper cites pretraining is conducted with 8 NVIDIA RTX 2080Ti GPUs.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection pretraining is conducted with 8 NVIDIA RTX 2080Ti GPUs

Reference 640

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:19.126050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:18.925729Z digest=sha256:ee42bcd3e00b4a526d3d8e7c77206d2a023274381acc1fce34e99677a39457d1

Observation 42237451-72cd-4d1e-852f-d9394896de6f · outbound

This paper cites Ic- dar 2015 competition on robust reading.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Ic- dar 2015 competition on robust reading

Reference 2013

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:26.676600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:15.426274Z digest=sha256:8924c8c7f4343a090598af4a1627eafa0356b63fff6f4817ec3f977b0fa192bf

Observation 8b73df16-2122-44d1-b53c-af32a2c6c5a1 · outbound

This paper cites Textboxes: A fast text detector with a single deep neural network.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Textboxes: A fast text detector with a single deep neural network

Reference 2015

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:26.560669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:15.529165Z digest=sha256:790eec2eff82a01d3aca05b0e6387bbbcc07be786527d726066775a04876addf

Observation cae7a5e5-9399-4068-8560-c79d9654d8e7 · outbound

This paper cites Mask R-CNN.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Mask R-CNN

Reference 2016

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:27.325696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:14.997676Z digest=sha256:6205a70e9506d5f4bc4039b4808f76624499c98955d54abd5f6a045bf7c495b8

Observation 742fe496-8cc6-47b1-8c44-a781054b4f8f · outbound

This paper cites Ic- dar2019 robust reading challenge on arbitrary-shaped text- rrc-art.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Ic- dar2019 robust reading challenge on arbitrary-shaped text- rrc-art

Reference 2017

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:28.044937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:14.605554Z digest=sha256:cd250072f4b3a520b7811ad0fa64dbdd1bd73b40dc238c5a27c83a2367a70689

Observation 6e9b4de0-5521-474b-af11-507a18c8a410 · outbound

This paper cites Real-time scene text detec- tion with differentiable binarization.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Real-time scene text detec- tion with differentiable binarization

Reference 2018

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:26.344782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:15.728644Z digest=sha256:98281479e53de4ef5e229f0287eac8b9c686a902c6e275e924c579291b233e63

Observation 8750a83b-1612-42fb-93f5-4ea3c1a69a24 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection An image is worth 16x16 words: Transformers for image recognition at scale

Reference 2019

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:27.758381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:14.712053Z digest=sha256:c5bfa83bab17505a0eeb0b954523fd470b2a083ead8d2c1ce0e07ca10918dedb

Observation 2ada117b-4c47-419a-a94e-fc8582068dcc · outbound

This paper cites Detecting curve text in the wild: New dataset and new solution.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Detecting curve text in the wild: New dataset and new solution

Reference 2020

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:26.195049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:15.847577Z digest=sha256:c28538c9aed704a910a372ee28c83bac9e5e1c0c84ba205d07fb6232209e9596

Observation feb003e1-f0dd-4446-859f-d878b709b152 · outbound

This paper cites I3CL: Intra-and inter-instance collaborative learning for arbitrary-shaped scene text detection.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection I3CL: Intra-and inter-instance collaborative learning for arbitrary-shaped scene text detection

Reference 2021

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:27.579139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:14.814052Z digest=sha256:c17abed8e8021ead228244edceceecc07aef8fe62217ce51a09deb3012e72296

Observation f221c6e2-fbba-40f4-870d-b79b08e6fe18 · outbound

This paper cites Synthetic data for text localization in nat- ural images.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Synthetic data for text localization in nat- ural images

Reference 2022

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:27.454525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:14.898997Z digest=sha256:f4d38bbc6ecb068c187af65f9d00206e3bbe78dab0740c88551fd448b6b035a8

Observation dce1e83f-05f7-4a46-aaf9-253ef57e7aaf · outbound

This paper cites Icdar 2013 robust reading competition.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Icdar 2013 robust reading competition

Reference 2023

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:26.798798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:15.337174Z digest=sha256:672f932ab78eeb8c06b5949d19aa8ac3a7efb775074e997d253a322669bf8d89

Observation 3cd94855-4466-4b91-be4a-fca7565a97ba · outbound

This paper cites Textdiffuser: Diffusion models as text painters.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Textdiffuser: Diffusion models as text painters

Reference 2024

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:28.429754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:14.409999Z digest=sha256:8da7e5c759bad2c67d90f9dec29847da727a838b0a341bef8f447ab042d26e16

Observation adeb3dc0-8a1a-4e00-befb-1db5fda2aed9 · outbound

This paper cites Icdar2017 robust reading challenge on multi-lingual scene text detection and script identification-rrc-mlt.

The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection Icdar2017 robust reading challenge on multi-lingual scene text detection and script identification-rrc-mlt

Reference 2025

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T15:17:25.025580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T15:17:16.793994Z digest=sha256:0d201e93317dae5f6755c2defe98f1793b8eff8936bd87eaac958fd42f9eeed4

Pith citing papers

Observation 60d920da-3ac4-4aa7-9f69-33cbecf20565 · inbound

StyleTextGen: Style-Conditioned Multilingual Scene Text Generation cites this paper.

StyleTextGen: Style-Conditioned Multilingual Scene Text Generation The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection

Reference 2

Resolution
verified exact
arxiv_id, observed 2026-05-15T04:55:03.039023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-05-15T04:54:52.729257Z digest=sha256:b2bbdea1e1049925b303524ac26951fc2235648e29beb8b6f070cb5b457ce13f

Observation f76869ce-3856-4891-93de-23eed28679f3 · inbound

Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection cites this paper.

Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-01T18:23:26.515073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T18:23:26.515073Z digest=sha256:3ccc8153ea1714fd14a7d9eb8284d6843f55549a5e49f710cf2c1e9cd6a4e79d