Pith. sign in

Paper Citation Record · LEDGER

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training

As of 11 August 2026, this Paper Citation Record lists 53 of 53 outbound references and 0 inbound Pith citation observations for arXiv:2607.20238.

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

pith.paper-citation-record.v1
2607.20238 v1

Coverage vector

measured 53 of 53 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T10:27:22.676730Z

measured 53 of 53 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+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

53 of 53 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved50
  • parse uncertain0
  • malformed identifier3
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ff2db643-9c88-4e11-b3ec-564fb156c327 · outbound

This paper cites Atmospherictransmissionandthermalinertia induced blind road segmentation with a large-scale dataset tbrsd, in: Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Atmospherictransmissionandthermalinertia induced blind road segmentation with a large-scale dataset tbrsd, in: Proc

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:18.265283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:18.265283Z digest=sha256:838ee960bb2bc9acf1d662c698834ca4587b0298bdf9e451c17178ee9ca26df1

Observation eee635a4-d931-43cc-a82d-7535b52a03c1 · outbound

This paper cites Encoder-decoder with atrous separable convolution for semantic im- age segmentation, in: Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Encoder-decoder with atrous separable convolution for semantic im- age segmentation, in: Proc

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:18.318301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:18.318301Z digest=sha256:318f1e60f64828c868b10298df9e19b12afd5a24d993c347b86cba721203c913

Observation b547d91a-5578-432c-ab04-28266635dad3 · outbound

This paper cites Vision transformer adapter for dense predictions, in: Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Vision transformer adapter for dense predictions, in: Proc

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:18.409860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:18.409860Z digest=sha256:2be2acf9446c9c0c2fe0b6a8319112cfc6c9f41054a7db2d246c32fb83e84cb3

Observation 31ed6fc8-a1a9-41f0-b089-75d97cd8df67 · outbound

This paper cites Masked-attention mask transformer for universal image segmenta- tion,in:Proc.IEEEConf.Comput.Vis.PatternRecognit.,pp.1290– 1299.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Masked-attention mask transformer for universal image segmenta- tion,in:Proc.IEEEConf.Comput.Vis.PatternRecognit.,pp.1290– 1299

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:18.485228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:18.485228Z digest=sha256:82d7ceeca5892bf0a76ab954ff0ec6dfbfb69ee3ecd876372c104c90bcde7197

Observation 68e0748c-5880-4881-9976-e33fe7d6c95c · outbound

This paper cites ViM-VQ: Efficientpost-trainingvectorquantizationforvisualmamba,in:Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training ViM-VQ: Efficientpost-trainingvectorquantizationforvisualmamba,in:Proc

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:18.569473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:18.569473Z digest=sha256:b239156f951775cd108e7135799e04ef0b48b5feb80757cf95466564dc0226be

Observation bb33aeff-da42-48ff-b65c-248da38f822f · outbound

This paper cites Lraf-net: Long-range attention fusion network for visible–infrared object detection.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Lraf-net: Long-range attention fusion network for visible–infrared object detection

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:18.623725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:18.623725Z digest=sha256:4fa9754f20707ab0b700cedb73d6de5bd2df6a1ee499eba59a8d8367cf632ad1

Observation 33560ead-2c15-43e6-bd59-cdfd592e5e45 · outbound

This paper cites Cf- deformable detr: an end-to-end alignment-free model for weakly Qiwei Ma et al.:Preprint submitted to ElsevierPage 11 of 13 aligned visible-infrared object detection, in: Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Cf- deformable detr: an end-to-end alignment-free model for weakly Qiwei Ma et al.:Preprint submitted to ElsevierPage 11 of 13 aligned visible-infrared object detection, in: Proc

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:18.695578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:18.695578Z digest=sha256:ca1ce1dbea2356a631d76bd1e077e734e4030cb5437fc080051d7cfdb31df590

Observation 62a0ac14-92c2-42e8-98df-2dfb775be9b9 · outbound

This paper cites MCMAE: Maskedconvolutionmeetsmaskedautoencoders,in:Proc.Adv.Neu- ral Inf.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training MCMAE: Maskedconvolutionmeetsmaskedautoencoders,in:Proc.Adv.Neu- ral Inf

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:18.783999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:18.783999Z digest=sha256:0814a02fe51cf705b8cd2f8f592f5a7f138f14e4dfec71783ae88fceec681855

Observation 064330e3-cea5-4787-bed3-3f25c7c512b1 · outbound

This paper cites Imagebind:Oneembeddingspacetobindthemall,in: Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Imagebind:Oneembeddingspacetobindthemall,in: Proc

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:18.849437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:18.849437Z digest=sha256:b534d3e613f24a87145672e2768a391f6965c7b04cebb61f3799bd08125b9983

Observation 93da5d5b-a715-4e34-8ff8-eabc30a3a674 · outbound

This paper cites an unresolved cited work.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Unresolved cited work

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:18.925361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:18.925361Z digest=sha256:cbf6fc8e71dd9545a1561895de3ddea4493c7535224dfea0cde7cf0d6872f9ce

Observation a2bf234c-2e72-4c9c-a0ef-089ee3787806 · outbound

This paper cites an unresolved cited work.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Unresolved cited work

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:18.987399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:18.987399Z digest=sha256:2ad271eb4d50e578b3a4545666b4d456b43e143fb9d031b61aace26e6cf78bda

Observation 87157311-d29a-45bf-8834-83a9265bc39c · outbound

This paper cites Mfnet: Towards real-time semantic segmentation for autonomous vehicleswithmulti-spectralscenes,in:Proc.Int.Conf.Intell.Robots Systems, pp.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Mfnet: Towards real-time semantic segmentation for autonomous vehicleswithmulti-spectralscenes,in:Proc.Int.Conf.Intell.Robots Systems, pp

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:19.050392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:19.050392Z digest=sha256:0448025fc54824fcd41c9cadcca02d3c69225f6a74d259988f3424ae449dc110

Observation 345eff99-a428-4a86-9f31-eb4cb1fc72f5 · outbound

This paper cites Masked autoencoders are scalable vision learners, in: Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Masked autoencoders are scalable vision learners, in: Proc

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:19.116614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:19.116614Z digest=sha256:6831e43e0306ffe44853b5f000987f99683c831b79f31c2797422af0062b4214

Observation 0ebae3f0-005f-4788-883d-ecc7c77fe3c9 · outbound

This paper cites MaskR-CNN,in: Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training MaskR-CNN,in: Proc

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:19.193579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:19.193579Z digest=sha256:97cad909513645dba222459861b5d62f98a515b478a9716df81cb77916fc1e9c

Observation be8ea54c-377d-47c9-a520-ba96e70005de · outbound

This paper cites Global–local feature fusion networkforvisible–infraredvehicledetection.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Global–local feature fusion networkforvisible–infraredvehicledetection

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:19.269867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:19.269867Z digest=sha256:f47512268861086ad3f996e126d68d68db20d87d3001101cea3bdf88e75f64f3

Observation 33bc0292-05b2-4825-afd0-6c4ccaea521d · outbound

This paper cites Configuring data augmentations to reduce variance shift in positional embedding of vision transformers, in: Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Configuring data augmentations to reduce variance shift in positional embedding of vision transformers, in: Proc

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:19.349071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:19.349071Z digest=sha256:a6b67b859ae8ae8da84ae06a976f2d060bb360afc7a0974896fae62639370e73

Observation 1bb4080d-8076-4cb6-ae22-bb8eb91986ca · outbound

This paper cites Segmentingobjects in day and night: Edge-conditioned cnn for thermal image semantic segmentation.IEEETrans.Neural.Netw.Learn.Syst.32,3069–3082.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Segmentingobjects in day and night: Edge-conditioned cnn for thermal image semantic segmentation.IEEETrans.Neural.Netw.Learn.Syst.32,3069–3082

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:19.425799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:19.425799Z digest=sha256:268c99946bc265e880414f3a9dfe4218037656e1a889674c67eb963fcdf617dc

Observation 09c4f0b6-ee67-4fcc-bbf4-d078f654ae80 · outbound

This paper cites Segmentingobjects in day and night: Edge-conditioned cnn for thermal image semantic segmentation.IEEETrans.Neural.Netw.Learn.Syst.32,3069–3082.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Segmentingobjects in day and night: Edge-conditioned cnn for thermal image semantic segmentation.IEEETrans.Neural.Netw.Learn.Syst.32,3069–3082

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:19.510668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:19.510668Z digest=sha256:78e8bca4d2abd160bf5893be8d01ef108ed9ec1787212bf1223be25dfa9e56f8

Observation f3ed058b-7bbc-403f-8d0e-775424f39fad · outbound

This paper cites an unresolved cited work.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Unresolved cited work

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:19.614178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:19.614178Z digest=sha256:26e3dafcb09e61ab2abb2f3c5951c630e3a1fe5767834ff25547dd713586e79a

Observation 7c004698-9d54-4fd3-9089-04b094b1d160 · outbound

This paper cites Explicit attention-enhanced fusion for rgb-thermal perception tasks.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Explicit attention-enhanced fusion for rgb-thermal perception tasks

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:19.745491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:19.745491Z digest=sha256:a206f083e14ebf00130e2d2181caa73d2f73151cc4bd6c46e87964ee79ae919e

Observation d141cd76-7a91-4cff-aa25-3c1a4f06d185 · outbound

This paper cites COMO:Cross- mamba interaction and offset-guided fusion for multimodal object detection.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training COMO:Cross- mamba interaction and offset-guided fusion for multimodal object detection

Reference 21

Resolution
malformed identifier
no resolver link, observed 2026-08-01T10:27:19.821947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:19.821947Z digest=sha256:340eff7404741fe6b9ae66630b7617612554869af8a18e605ade3a0041aed539

Observation 301d9679-52a1-4449-b6fc-035a114c0e56 · outbound

This paper cites an unresolved cited work.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Unresolved cited work

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:19.898322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:19.898322Z digest=sha256:e11e6ec82139971bd915f6572996db21246557bf32ac44281a112a39ef46be9b

Observation 3a0d1908-62b9-4436-8521-e99e0d725874 · outbound

This paper cites InfMAE: A foundation model in the infrared modality, in: Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training InfMAE: A foundation model in the infrared modality, in: Proc

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:20.112586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:20.112586Z digest=sha256:ccb1b09cdfbbc53460556eb8bc7ea68c9335d99b88777b336cd0412457db458c

Observation d3c9fc40-235a-4be8-b278-89d27801d598 · outbound

This paper cites an unresolved cited work.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Unresolved cited work

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:20.187421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:20.187421Z digest=sha256:a0b7d79b5f945911150db3186910e7b99de6e390d94700ea599e1aefc06e488a

Observation 0bf4be3a-c3a1-4b6c-86ae-4f0225c30439 · outbound

This paper cites Bridging rgb-t image fusion and semantic segmentation via multi-task collaborative learning.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Bridging rgb-t image fusion and semantic segmentation via multi-task collaborative learning

Reference 25

Resolution
malformed identifier
no resolver link, observed 2026-08-01T10:27:20.269171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:20.269171Z digest=sha256:e5a4cd1e0035a1befcf2aedb49d1956cc4e83ebfe027de2dec13462f4c6e356d

Observation 4d1e1789-98e9-47ab-b09b-c4f0a76c867c · outbound

This paper cites an unresolved cited work.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Unresolved cited work

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:20.322005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:20.322005Z digest=sha256:3d56718726b5d39faf6fa2589c1290f0bdfc5d1fcacde271dcc32c2ecc795bdb

Observation 8f6249ea-4837-4b18-833e-f9f41fcddbe7 · outbound

This paper cites Visualizing data using t-SNE.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Visualizing data using t-SNE

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:20.495079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:20.495079Z digest=sha256:27f7e5271ed5579a1ce1dd6f93e68cb41bb536b4f063285e974864e515f29c1a

Observation 5d2a49d0-3772-4110-b706-4cb64ef106b9 · outbound

This paper cites UNIV: Unified Foundation Model for Infrared and Visible Modalities.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training UNIV: Unified Foundation Model for Infrared and Visible Modalities

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:20.578105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:20.578105Z digest=sha256:018b600153eaac73ac91734aab5218a8dff5710e273dc9ee1eba0f0198aacaed

Observation 97ff8a2c-1069-4011-acb2-b5762047d4bc · outbound

This paper cites Suppresscontentshift:Betterdiffusionfeaturesviaoff-the-shelfgen- eration techniques.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Suppresscontentshift:Betterdiffusionfeaturesviaoff-the-shelfgen- eration techniques

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:20.686848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:20.686848Z digest=sha256:dff8c1cbf5f19ad80c4fd9c0ccd61f69c3f4e9ce96f6ac45ebbd355b9aa73f20

Observation 6ec6c76f-e384-493d-829e-0a57f808a015 · outbound

This paper cites Connecting joint-embedding predictive architecture with contrastive self-supervised learning.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Connecting joint-embedding predictive architecture with contrastive self-supervised learning

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:20.770514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:20.770514Z digest=sha256:e192f720cabc2e7d1d33c5fd4947c2c64c7000d55a1d8937b3c22f65e5f0b60e

Observation 68deaa24-f4f5-4111-8402-ebf498505d14 · outbound

This paper cites Attributefilterbased infrared and visible image fusion.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Attributefilterbased infrared and visible image fusion

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:20.837725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:20.837725Z digest=sha256:63173f83854b30f4c69e3b8e920f4b922623278045ea7f5a9dc13b3c9b9b3867

Observation 54520e64-a796-42ef-96bc-e732a0d4bd15 · outbound

This paper cites Interactive visible and infrared image fusion and segmentation.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Interactive visible and infrared image fusion and segmentation

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:20.915569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:20.915569Z digest=sha256:ebfe2b54dd2877fd0cc6f3f44b1b0db7cc37996e604463865f1708d45b283c3c

Observation d57e5170-2cb5-4f7e-8f38-39ae2e7d57a6 · outbound

This paper cites Learning by aligning: Visible-infrared person re-identification using cross-modal corre- spondences, in: Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Learning by aligning: Visible-infrared person re-identification using cross-modal corre- spondences, in: Proc

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:20.993008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:20.993008Z digest=sha256:cc8552356f6c4e10ac77f7913c8e1b837eae0cf58771d40a08cdcc3dc8f65aa7

Observation e45e87e3-4118-4ce3-bc7a-1bafd87df7de · outbound

This paper cites Learning transferable visual models from natural language supervision, in: Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Learning transferable visual models from natural language supervision, in: Proc

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:21.093403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:21.093403Z digest=sha256:8fd66dd8b95f0e8259ffb77d313db9ecfdd1a47685014a04c63e3a60b3fa9d05

Observation e08fe7ba-3352-467b-8096-c9f70f5ad206 · outbound

This paper cites Drone-based rgb- infraredcross-modalityvehicledetectionviauncertainty-awarelearn- ing.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Drone-based rgb- infraredcross-modalityvehicledetectionviauncertainty-awarelearn- ing

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:21.185934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:21.185934Z digest=sha256:086c061ee88768e13b209016a1ce7c154bdda09f177ef2bddc5fa46af2a734e0

Observation 1e2431d5-b060-4a5b-b87e-df83d9fd8ff6 · outbound

This paper cites PIAFusion: A progressive infrared and visible image fusion network based on illumination aware.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training PIAFusion: A progressive infrared and visible image fusion network based on illumination aware

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:21.197222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:21.197222Z digest=sha256:3969b48747f2757aa11efadb9e0c83694ed38d96a1551319f8912c8b042661cd

Observation ab31d01c-b522-40dd-a5a9-db63bb971f22 · outbound

This paper cites Yolov8: A novel object detection algorithm with enhanced performance and robustness, in: Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Yolov8: A novel object detection algorithm with enhanced performance and robustness, in: Proc

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:21.295300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:21.295300Z digest=sha256:55b05171ca03e5929f4f3af7260b09d8232774a6318a8ea94002e6147caabb58

Observation 404d715b-7dcc-4922-9efb-94a032394fe2 · outbound

This paper cites Unifiedperceptual parsing for scene understanding, in: Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Unifiedperceptual parsing for scene understanding, in: Proc

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:21.419172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:21.419172Z digest=sha256:6b0581e2bd337a092b13fd37554cd63f1bc1d6f5c5248fe0246353f2477c3d78

Observation 08a489e4-a965-4bbd-a11f-bcbb2aa2d257 · outbound

This paper cites SegFormer: Simple and efficient design for semantic segmentationwithtransformers.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training SegFormer: Simple and efficient design for semantic segmentationwithtransformers

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:21.550350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:21.550350Z digest=sha256:2b20e55b60a7dcaed2aa586c898684342f21cafdb0e42a9e83864f9ce40dcced

Observation ce49cce2-9df9-4610-9309-1c4761b62027 · outbound

This paper cites MCNet:Multi-levelcorrectionnet- work for thermal image semantic segmentation of nighttime driving scene.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training MCNet:Multi-levelcorrectionnet- work for thermal image semantic segmentation of nighttime driving scene

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:21.664367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:21.664367Z digest=sha256:42a6b8eaac655c7c6ac63dc7ec93817cb0c52cec0d8ce9bcd09a653405b5deb3

Observation c939e05a-4923-4f22-a071-64debfa929de · outbound

This paper cites Fast and robust matching for multimodal remote sensing image registration.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Fast and robust matching for multimodal remote sensing image registration

Reference 41

Resolution
malformed identifier
no resolver link, observed 2026-08-01T10:27:21.750883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:21.750883Z digest=sha256:35ed59aaa1faf04cff1db6fd4fd59719ef6db05cee547d21a5972487db716458

Observation 78c615da-a0ac-401f-8ea7-9c66682dca63 · outbound

This paper cites SPGFusion: Semantic prior guided infrared and visible image fusion via pretrained vision models.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training SPGFusion: Semantic prior guided infrared and visible image fusion via pretrained vision models

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:21.865518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:21.865518Z digest=sha256:76fb153b9316c136c2e172eed034d31e52f01b282d7a38d6bbe729a921fcce95

Observation b479e1a6-cf76-4135-ae47-abdb663ee2df · outbound

This paper cites CR2PQ:Continuousrelativerotarypositionalqueryfordense visual representation learning, in: Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training CR2PQ:Continuousrelativerotarypositionalqueryfordense visual representation learning, in: Proc

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:21.928737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:21.928737Z digest=sha256:e954d02f9e532810afa9ad69d8989e95ecae36fd78b2e466dd96d4fa08f5c836

Observation 94649f7a-e071-418f-9afe-9ef4a378fc63 · outbound

This paper cites an unresolved cited work.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Unresolved cited work

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:22.022033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:22.022033Z digest=sha256:22658ec1e9b9c1a56b704da0e7d64b54474dcf067415e3b9b1c980780f65c2e7

Observation def11a75-4f83-4086-b1f9-48ac89f6eb86 · outbound

This paper cites UNIP:Rethinkingpre-trainedattentionpatternsforinfraredsemantic segmentation, in: Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training UNIP:Rethinkingpre-trainedattentionpatternsforinfraredsemantic segmentation, in: Proc

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:22.258844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:22.258844Z digest=sha256:fa9853037a77cd549193b0ec80432057ff1221793257716c8229b930a9bf9faa

Observation aa878abd-0705-444a-bc09-afb5f1006c32 · outbound

This paper cites IEEE Conf.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training IEEE Conf

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:22.363617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:22.363617Z digest=sha256:2c82f885696862677ec106d6bfc7f4f1a592c5e5979ef413913297cc7583c8a2

Observation 2befc47d-c8a5-43e6-a4bd-080fe08beb49 · outbound

This paper cites Cddfuse:Correlation-drivendual-branchfeature decompositionformulti-modalityimagefusion,in:Proc.IEEEConf.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Cddfuse:Correlation-drivendual-branchfeature decompositionformulti-modalityimagefusion,in:Proc.IEEEConf

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:22.431436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:22.431436Z digest=sha256:3370fcabb21beefc2b6a653dc1b751dbc1f553537a6842cb522ee960b2157486

Observation 00decbcf-c16d-443d-bf09-321064fe01c3 · outbound

This paper cites PAD: Self-Supervised Pre-Training with Patchwise-Scale Adapter for Infrared Images.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training PAD: Self-Supervised Pre-Training with Patchwise-Scale Adapter for Infrared Images

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:22.146255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:22.146255Z digest=sha256:c59ec37948ed8412beb4f3eef1937c8427d2425e57ac034c3802e469bc49e77f

Observation 36a90e57-ddaa-4614-93dd-a6ec33365e1e · outbound

This paper cites Semantic understanding of scenes through the ade20k dataset.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Semantic understanding of scenes through the ade20k dataset

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:22.676730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:22.676730Z digest=sha256:dfb2be19cc08419c42ba43dd90328ab294d8db20518862b4ef9171af8a078dee

Observation e6f9f5bd-afb0-45c8-8ef5-0f39d4d16465 · outbound

This paper cites Equivariant multi-modality image fusion, in: Proc.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training Equivariant multi-modality image fusion, in: Proc

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:22.542679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:22.542679Z digest=sha256:730429599eb4b8cf2010bfad6bcadf6219a881ba7b0e14e492e1d29fb3833351

Observation 1bc95a16-04b3-4cc4-85cf-b963b94b5d3f · outbound

This paper cites IEEE Trans.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training IEEE Trans

Reference 2021

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:20.009555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:20.009555Z digest=sha256:2e1d305a7fdc5584428cef06d0e09bade5a01d4e466694bd31e6cface8ba7d70

Observation e31b036c-36df-45b5-9fd3-554a3b9de4d2 · outbound

This paper cites IEEE Conf.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training IEEE Conf

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:19.690005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:19.690005Z digest=sha256:cfe0fb2c4ea3872ccb0911f6e681925f7384684a8579cf85f1fb1f4688a752e0

Observation 079263cd-40ce-46ee-95bf-fd2d8cb81b38 · outbound

This paper cites SARVLM: A Vision Language Foundation Model for Semantic Understanding in SAR Imagery.

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training SARVLM: A Vision Language Foundation Model for Semantic Understanding in SAR Imagery

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-01T10:27:20.420271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:27:20.420271Z digest=sha256:2a142bb0e3cf8221feb616f92cdfdce7b6494b595934435b1f9c8099f8273f0d

Pith citing papers

No inbound Pith citation observations are available.