Pith. sign in

Paper Citation Record · LEDGER

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion

As of 10 August 2026, this Paper Citation Record lists 76 of 76 outbound references and 0 inbound Pith citation observations for arXiv:2506.00625.

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

pith.paper-citation-record.v1
2506.00625 v2

Coverage vector

measured 76 of 76 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:07:46.025831Z

measured 76 of 76 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 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

76 of 76 outbound references displayed

  • verified exact0
  • verified fuzzy74
  • unresolved2
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3e8351c2-5557-4760-96b6-583a0437e91c · outbound

This paper cites Long-tail learning with foundation model: Heavy fine-tuning hurts,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Long-tail learning with foundation model: Heavy fine-tuning hurts,

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:02.817966Z

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=2026-08-07T12:07:39.373374Z digest=sha256:8287f98e2cce450b0ecf1f92422a1b91734c45e3190721a37193b063f09a0104

Observation fa9f4e46-5cf2-450b-a333-b61f5d0816c7 · outbound

This paper cites The pareto, zipf and other power laws,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion The pareto, zipf and other power laws,

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:02.689450Z

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=2026-08-07T12:07:39.459755Z digest=sha256:ad7037db7f395689085fe739c097f6653b2fc8992d9e3b27f013bcc60058f2d0

Observation aa9bc264-66d7-48ba-8c05-26ebc93cf09b · outbound

This paper cites Large-scale long-tailed recognition in an open world,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Large-scale long-tailed recognition in an open world,

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:02.572537Z

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=2026-08-07T12:07:39.543638Z digest=sha256:d9bf07dbf879b74ac0f19110c88e8518e7400ad11f852aee61a5e62d57661cd2

Observation 25f5f66a-5f3d-4041-bfa0-bc86dc575919 · outbound

This paper cites Deep long-tailed learning: A survey,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Deep long-tailed learning: A survey,

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:02.427318Z

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=2026-08-07T12:07:39.643824Z digest=sha256:e18d8bb803b46aaf1818de9128e7a40062ce39806c1471b9324a0eca57133a54

Observation 71aa160a-29a9-4274-9617-5ff53b3dd9c8 · outbound

This paper cites thesis, Hong Kong Baptist University, 2022.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion thesis, Hong Kong Baptist University, 2022

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:02.226329Z

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=2026-08-07T12:07:39.730537Z digest=sha256:ae3b725d262d6b99994a3f58f4b6c722bcf7bdcff9045c56a4a616685822f156

Observation 3b04d26b-7794-443b-9d7c-c5fd96b74a8b · outbound

This paper cites SMOTE: synthetic minority over-sampling technique,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion SMOTE: synthetic minority over-sampling technique,

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:02.093969Z

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=2026-08-07T12:07:39.800405Z digest=sha256:881b83635dffded1ded0eb3fa5cf9f3994624486e0990506f70ab98a2ad6a63d

Observation 5b43d7bb-aebf-49d2-95bb-b19551428a5d · outbound

This paper cites Learning deep representation for imbalanced classification,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Learning deep representation for imbalanced classification,

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:01.898478Z

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=2026-08-07T12:07:39.892503Z digest=sha256:e4d2d4cdcd1fc70f4bb402b3dd920b1ab9227a575b9b147a42a77781a4c37bcf

Observation 88c64ec9-06f6-4a95-94cd-d9fab48050d2 · outbound

This paper cites M2m: Imbal- anced classification via major-to-minor translation,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion M2m: Imbal- anced classification via major-to-minor translation,

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:01.725530Z

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=2026-08-07T12:07:39.969425Z digest=sha256:024c7bbe0bf091b34ff3037a2a3960b703afc29a53a44f791458ec740e287f80

Observation 5a821a06-a9fd-4f7d-aaac-24c588466d73 · outbound

This paper cites RSG: A simple but effective module for learning imbalanced datasets,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion RSG: A simple but effective module for learning imbalanced datasets,

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:01.522521Z

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=2026-08-07T12:07:40.073684Z digest=sha256:e765ee11bd02ae36ce2a5d0c7c27994a27dd39eb2051b5b3bcc713516b1af997

Observation 7565d919-5630-4001-8281-fdc66ca22cf2 · outbound

This paper cites MetaSAug: Meta semantic augmenta- tion for long-tailed visual recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion MetaSAug: Meta semantic augmenta- tion for long-tailed visual recognition,

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:01.375605Z

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=2026-08-07T12:07:40.188708Z digest=sha256:5ee3674548f5d90c4514d94fb213966e96cdac531041e771fb0da40e397d972a

Observation 50399ca9-7a01-4349-b8f5-420f40b8cd86 · outbound

This paper cites The majority can help the minority: Context- rich minority oversampling for long-tailed classification,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion The majority can help the minority: Context- rich minority oversampling for long-tailed classification,

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:01.206169Z

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=2026-08-07T12:07:40.287273Z digest=sha256:522cd647389405a8597c7b13e507f914bd2661d7b39b7f2475c32e425f959757

Observation 050ffb85-c4a4-4ffe-9582-a0dcd8de3b22 · outbound

This paper cites BBN: Bilateral-branch network with cumulative learning for long-tailed visual recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion BBN: Bilateral-branch network with cumulative learning for long-tailed visual recognition,

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:01.022686Z

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=2026-08-07T12:07:40.403890Z digest=sha256:e4ed7e7daebea505b96fddc2a0fc01ad62b9458bb260baecffbf201e89a11445

Observation 4991eaad-e8e6-4665-a27a-9242673c0552 · outbound

This paper cites Decoupling represen- tation and classifier for long-tailed recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Decoupling represen- tation and classifier for long-tailed recognition,

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:00.846639Z

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=2026-08-07T12:07:40.503192Z digest=sha256:f51c4b8fd1074e4f19d087159a45626d47c2ef66f0ed36bd8f46d4adfffab52e

Observation fb533ecf-0608-4c08-96e3-7dd193d2428d · outbound

This paper cites Long-tailed recognition by routing diverse distribution- aware experts,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Long-tailed recognition by routing diverse distribution- aware experts,

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:00.673368Z

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=2026-08-07T12:07:40.589088Z digest=sha256:92beb1cc0674ef0d1afa614b21e64aef8b092d848ed4cbf37f13b1a1a1fd40cc

Observation 731d2d29-4999-495b-a2f8-5e2c174b0f9e · outbound

This paper cites The devil is in classifi- cation: A simple framework for long-tail instance segmentation,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion The devil is in classifi- cation: A simple framework for long-tail instance segmentation,

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:00.510700Z

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=2026-08-07T12:07:40.667105Z digest=sha256:cde44ccd6dc7838ea226297ac6777cfa285be8b5ad61ab5914a8ad4952677873

Observation ca54fd38-c3d8-49dd-9d0b-006137c21f28 · outbound

This paper cites Trustworthy long-tailed classification,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Trustworthy long-tailed classification,

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:00.299981Z

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=2026-08-07T12:07:40.751395Z digest=sha256:a4fa6ef17770d04f04da9b54f2717be24b560e67abf2a05921f31c598392e11e

Observation 30c5230b-cebf-446c-81c1-9f016bbe004e · outbound

This paper cites Long-tailed visual recognition via self-heterogeneous integration with knowledge excavation,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Long-tailed visual recognition via self-heterogeneous integration with knowledge excavation,

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:08:00.118017Z

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=2026-08-07T12:07:40.830986Z digest=sha256:636b4fa54854e4e10e52b20635766759bf2ea8bf82d8ebdd4c89001dccc1eff1

Observation e674b5d8-9401-43ec-94a2-01b1f932923f · outbound

This paper cites Focal loss for dense object detection,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Focal loss for dense object detection,

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:59.935776Z

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=2026-08-07T12:07:40.940276Z digest=sha256:60621dfbe41abfc646b4c290d0a0b8c8ec2057d24d1f33bbb9648b7a0a21d480

Observation b4c3a332-cd8e-4b7e-a628-699ed7fd37a3 · outbound

This paper cites Class-balanced loss based on effective number of samples,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Class-balanced loss based on effective number of samples,

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:59.771263Z

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=2026-08-07T12:07:41.037031Z digest=sha256:92aaf470eec78ff32ccb8186feee2739867220ee66b4e713e77cf4c4964613de

Observation a6cbb542-d99d-4036-9991-1d2c584f79be · outbound

This paper cites Balanced meta-softmax for long-tailed visual recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Balanced meta-softmax for long-tailed visual recognition,

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:59.583641Z

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=2026-08-07T12:07:41.125132Z digest=sha256:493ac78d13b65fb62e166990d1c65bf9f7b5d99ea88d522ca193e38fdb3377e7

Observation ff801160-c2a8-43d8-8459-af4d2cda812d · outbound

This paper cites Long-tail learning via logit adjustment,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Long-tail learning via logit adjustment,

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:59.441715Z

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=2026-08-07T12:07:41.198731Z digest=sha256:553ff7e18e1cab9e7a364469288f20743d39e7d93c3b8e836e006af98aa179d1

Observation 4d40e317-cc80-4c65-b42e-ebbab5ef4026 · outbound

This paper cites Disentangling label distribution for long-tailed visual recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Disentangling label distribution for long-tailed visual recognition,

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:59.232829Z

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=2026-08-07T12:07:41.297428Z digest=sha256:19363228ffe7674b18c9f6398892415e1db74714ff55a910d94fb39fa834b247

Observation 27697247-1e84-499b-a312-8e7c05fdadcf · outbound

This paper cites Long-tailed visual recognition via gaussian clouded logit adjustment,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Long-tailed visual recognition via gaussian clouded logit adjustment,

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:59.003746Z

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=2026-08-07T12:07:41.381913Z digest=sha256:20eed3ee1a052f3c098723362e3da70a410743ff28b0d6473e3ec11fd34ccbf1

Observation 6aa16c8e-eeb4-4f34-b42b-d70e743ce377 · outbound

This paper cites A Simple Long-Tailed Recognition Baseline via Vision-Language Model.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion A Simple Long-Tailed Recognition Baseline via Vision-Language Model

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-07T12:07:41.483153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:07:41.483153Z digest=sha256:1ea8055a5f84a8f2ad09f1596c9d3c176bd016b865e5d2b5eeeac0a4d223cb3b

Observation ab13db7f-0b2c-4f33-8a98-988532890e5d · outbound

This paper cites VL-LTR: Learning class-wise visual-linguistic represen- tation for long-tailed visual recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion VL-LTR: Learning class-wise visual-linguistic represen- tation for long-tailed visual recognition,

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:58.747648Z

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=2026-08-07T12:07:41.656193Z digest=sha256:0bfc8ef507bea36b812f80ba59cd7019964585b1dc9dc35c8ea20e8da85b91fd

Observation c5d352db-31f9-4dd3-b687-59756c2ff886 · outbound

This paper cites LPT: long-tailed prompt tuning for image classification,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion LPT: long-tailed prompt tuning for image classification,

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:58.549137Z

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=2026-08-07T12:07:41.759765Z digest=sha256:f4937e6f0baee97cda2edbdc8fc2e400093720f958703713914a2f23588f0ace

Observation f7f62054-65a2-4805-949e-fcef167916bd · outbound

This paper cites ImageNet-21K pretraining for the masses,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion ImageNet-21K pretraining for the masses,

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:58.352310Z

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=2026-08-07T12:07:41.921675Z digest=sha256:9c46386baf473fe6fddda7f5e5a0e7e3d58febf6bcdf471c3727043aa6c9b3c3

Observation 5df9d81a-a7a4-4ca1-b622-f9a0493a7c2d · outbound

This paper cites Learning imbalanced datasets with label-distribution-aware margin loss,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Learning imbalanced datasets with label-distribution-aware margin loss,

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:58.117130Z

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=2026-08-07T12:07:41.991769Z digest=sha256:8ff428707322e2214dafbe76eafd56e0206fc5e1c13289381656a86b66e9f2bc

Observation 2ba777f5-b7ca-443a-9521-61371d5215e6 · outbound

This paper cites Arcface: Additive angular margin loss for deep face recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Arcface: Additive angular margin loss for deep face recognition,

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:57.909975Z

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=2026-08-07T12:07:42.105179Z digest=sha256:c3f38bcd37eee813207910fd01f808543c4148a437863b0fb201360032bf476a

Observation ce588fe6-6d9e-4543-84c6-f7ba6ab16f84 · outbound

This paper cites Cosface: Large margin cosine loss for deep face recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Cosface: Large margin cosine loss for deep face recognition,

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:57.700853Z

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=2026-08-07T12:07:42.198546Z digest=sha256:646bded8dddb6e3c130cf5981f5d2834771269f2132a56254e4ff697baad31b7

Observation b0cf2b83-2489-4634-875a-9a6c76b98ccb · outbound

This paper cites Normface: L2 hypersphere embedding for face verification,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Normface: L2 hypersphere embedding for face verification,

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:57.470863Z

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=2026-08-07T12:07:42.341507Z digest=sha256:88bdd18350db85a86dd33558fa9a015c6a55f93065cda38e5a82fede7b1c2f2b

Observation 8e22b3ac-2673-46ea-960e-cd36fa8c340b · outbound

This paper cites Mtfh: A matrix tri-factorization hashing framework for efficient cross- modal retrieval,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Mtfh: A matrix tri-factorization hashing framework for efficient cross- modal retrieval,

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:57.301535Z

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=2026-08-07T12:07:42.452513Z digest=sha256:2198add4635c20e4e9ffc52663ee8151added4a3190e95a1e065454ee6699850

Observation f7f50869-f496-4a8e-bb43-950500a42c30 · outbound

This paper cites Joint semantic preserving sparse hashing for cross-modal retrieval,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Joint semantic preserving sparse hashing for cross-modal retrieval,

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:57.139878Z

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=2026-08-07T12:07:42.575799Z digest=sha256:539e088ee3bfb66145076a14c167581f87bfe13b7f1a25e6e43b80920226de0d

Observation af753f90-c96a-40cb-880c-a9700fef9b2e · outbound

This paper cites Revisiting unreasonable effectiveness of data in deep learning era,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Revisiting unreasonable effectiveness of data in deep learning era,

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:56.888833Z

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=2026-08-07T12:07:42.670362Z digest=sha256:a421555b5bf88a46cd97c97aeafb68250d9e213561f44d84d52a5c998af6fcc5

Observation 474062d1-c1bf-46ba-9f5e-628c96606eea · outbound

This paper cites Does head label help for long-tailed multi-label text classification,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Does head label help for long-tailed multi-label text classification,

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:56.725190Z

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=2026-08-07T12:07:42.751726Z digest=sha256:db4f7bc6be1704204e13ec57d6ba2cac221fb662884a7e189d91786283798db4

Observation 672ce020-0d1b-4e44-a778-ade3f1f9dddd · outbound

This paper cites Permutation-invariant fea- ture restructuring for correlation-aware image set-based recogni- tion,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Permutation-invariant fea- ture restructuring for correlation-aware image set-based recogni- tion,

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:56.538106Z

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=2026-08-07T12:07:42.850950Z digest=sha256:f76c6bd4fb5b40d20686748407ef2ca9d317a255182de61325617ae7b994277d

Observation a548fbe5-3088-4f0f-b1c1-de3783bfe28d · outbound

This paper cites Feature fusion from head to tail for long-tailed visual recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Feature fusion from head to tail for long-tailed visual recognition,

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:56.300313Z

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=2026-08-07T12:07:43.000758Z digest=sha256:90d04aba8e4111ac4b0e46288e9ae5c73a3c82483c53171e0a666dd7d30da5d7

Observation 4c1b6cdc-b334-43b6-8a7f-a6d42f32d9ab · outbound

This paper cites Autoaugment: Learning augmentation strategies from data,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Autoaugment: Learning augmentation strategies from data,

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:56.073197Z

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=2026-08-07T12:07:43.097621Z digest=sha256:0e9666621a455f8906768c71c2b6c7f5af1d9861b3b3bb1529ce78d822e58750

Observation 77f7a0a4-1252-41c2-8d72-f45e4c16a81b · outbound

This paper cites Fast autoaugment,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Fast autoaugment,

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:55.921883Z

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=2026-08-07T12:07:43.183603Z digest=sha256:102219c54b6ba9cb32636c4657c4b390c7897d8ce40b856b19a5406f609ed4d1

Observation ca55480c-4f33-41b6-9c7f-22b5b38d3ef4 · outbound

This paper cites Pop- ulation based augmentation: Efficient learning of augmentation policy schedules,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Pop- ulation based augmentation: Efficient learning of augmentation policy schedules,

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:55.725895Z

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=2026-08-07T12:07:43.281547Z digest=sha256:70d74cd15d367759375553a7edc8567b64de06429db7e24ff84f9ff08cae6b75

Observation 8906a713-d90e-4625-932c-38ce05c3727c · outbound

This paper cites Randaugment: Practical automated data augmentation with a reduced search space,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Randaugment: Practical automated data augmentation with a reduced search space,

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:55.587668Z

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=2026-08-07T12:07:43.352048Z digest=sha256:d3056a6a30dd5e0b667613277658dad978d43d1072f66075e38e0ae6b950bc38

Observation 9b4ec4b3-6a49-4cfb-8201-235b16d288fa · outbound

This paper cites Parametric contrastive learning,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Parametric contrastive learning,

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:55.403587Z

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=2026-08-07T12:07:43.453686Z digest=sha256:3b8cb7c54bfad823e2f493cf40d343eb324d5340ce2f13dd5f4d8fecae1fa1ca

Observation 995327fb-03e3-4c3e-a382-34f66c466411 · outbound

This paper cites Nested collaborative learning for long-tailed visual recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Nested collaborative learning for long-tailed visual recognition,

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:55.213636Z

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=2026-08-07T12:07:43.554049Z digest=sha256:be674114e931c5d99f98e70fce90d5dd854e04069a56bfb951fae1f9753b0195

Observation adef0f3e-7f48-4623-a95f-65071cd58e1e · outbound

This paper cites Improving calibration for long-tailed recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Improving calibration for long-tailed recognition,

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:55.006894Z

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=2026-08-07T12:07:43.621974Z digest=sha256:ea834e0470c0746ec72c2d88ae879c3eaf4ba5a602eacd092bded3c220c18433

Observation 7ef2af3f-f3f6-40f6-985f-b678f5e38267 · outbound

This paper cites Distribution alignment: A unified framework for long-tail visual recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Distribution alignment: A unified framework for long-tail visual recognition,

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:54.841293Z

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=2026-08-07T12:07:43.699052Z digest=sha256:38de0cefe4d9682d14da2b92d12cc83ddf5168052ca27524bf58274665129cbf

Observation 3c74928e-ec44-466f-868a-09ea1470c6b6 · outbound

This paper cites Ace: Ally complementary experts for solving long-tailed recognition in one- shot,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Ace: Ally complementary experts for solving long-tailed recognition in one- shot,

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:54.655589Z

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=2026-08-07T12:07:43.786703Z digest=sha256:bcec98bbad249aaa523e1445502d118144e9ae14c31ac0d70f985b065f91c2a6

Observation d03e0f5b-e001-4e03-a4ab-b4284f3bfe5d · outbound

This paper cites Reslt: Residual learning for long-tailed recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Reslt: Residual learning for long-tailed recognition,

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:54.468053Z

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=2026-08-07T12:07:43.869485Z digest=sha256:97e61045d25889f1dd8d450e0ab2316be60a0012dcc3384630f3d7dfa3a4297b

Observation 7f1dd69e-1c0b-49a2-81f4-d485e5bad901 · outbound

This paper cites Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification,

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:54.208217Z

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=2026-08-07T12:07:43.961758Z digest=sha256:f6c9acb33df458eb9b587461e478a8512177c892aab2794cb20cc0926d39c6af

Observation b171e61d-07e8-4474-9b11-2699fd049f09 · outbound

This paper cites Overcoming classifier imbalance for long- tail object detection with balanced group softmax,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Overcoming classifier imbalance for long- tail object detection with balanced group softmax,

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:53.928072Z

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=2026-08-07T12:07:44.083120Z digest=sha256:83f4d367933736c0a097db4468a6df483eac9dddf6ebfa5be8d1ee98c6263ae8

Observation 4af8c0d3-1b94-488e-9659-dd446e68fd0d · outbound

This paper cites Key point sen- sitive loss for long-tailed visual recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Key point sen- sitive loss for long-tailed visual recognition,

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:53.645427Z

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=2026-08-07T12:07:44.153760Z digest=sha256:fe0f09470992978f8100bf00c76c61aa1a0f84ab4642adb1eb9bba00bce7c836

Observation 4771ca5c-e434-463c-b381-1ef788359c60 · outbound

This paper cites Seesaw loss for long-tailed instance segmentation,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Seesaw loss for long-tailed instance segmentation,

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:53.437775Z

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=2026-08-07T12:07:44.244835Z digest=sha256:1572407a44153bdce279abaedf127624e3556b56f31ff18421267aa7927bd0b5

Observation c60a1c25-4bd4-40a2-9247-9b29421ce7eb · outbound

This paper cites An image is worth 16x16 words: Transformers for image recog- nition at scale,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion An image is worth 16x16 words: Transformers for image recog- nition at scale,

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:53.164764Z

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=2026-08-07T12:07:44.326930Z digest=sha256:c98e3689b0b95233b82c97c4cbeca6de38767e2c1881059b524a4ed7ade541f3

Observation d2863f2a-c35a-4d89-a29d-14e62aff85cc · outbound

This paper cites Attention is all you need,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Attention is all you need,

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:52.821045Z

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=2026-08-07T12:07:44.397755Z digest=sha256:71b649a06420d45ed8d6dbfc586965bbd012cbd1b278851ba739aaa7a1c1599b

Observation 6131b92f-eb92-4bca-8d24-e219fb1de95f · outbound

This paper cites Learning imbalanced data with vision transformers,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Learning imbalanced data with vision transformers,

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:52.415920Z

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=2026-08-07T12:07:44.448511Z digest=sha256:dc0668c9731d44cfcac547e1afd5825dcf0415bf4815ae95d3e6f5cc1d9d3ad0

Observation 554f16a4-2953-4421-ae49-36f1aed5573b · outbound

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

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Learning transferable visual models from natural language supervision,

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-07T12:07:44.504999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:07:44.504999Z digest=sha256:7193e6ce1428a7daa89c917cc1d4b82171a5b345339a6c65c377f700fea31e0a

Observation a5c3c3fc-6210-4981-8842-42c3a4795f26 · outbound

This paper cites Visual prompt tuning,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Visual prompt tuning,

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:51.982864Z

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=2026-08-07T12:07:44.566027Z digest=sha256:b06edc5bc28a5b2d7969e07fbb8da3edc25657da3787899ecf38c6caa53d3855

Observation 6e0bdb26-53c4-4009-905f-f4596b23d9ba · outbound

This paper cites Adaptformer: Adapting vision transformers for scalable visual recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Adaptformer: Adapting vision transformers for scalable visual recognition,

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:51.645768Z

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=2026-08-07T12:07:44.633952Z digest=sha256:8b60de703c8cbd47d28ae1b031f246e99ec3344cfc13bbb37ecfe473157d5f5a

Observation d77de30e-7d26-4b03-b6b8-8e2fecb2fe60 · outbound

This paper cites Lora: Low- rank adaptation of large language models,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Lora: Low- rank adaptation of large language models,

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:51.317108Z

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=2026-08-07T12:07:44.711185Z digest=sha256:2aea945e8d76f8a8b4f97dfda5b9c34fb2c4b6c8fc6c7a4b1d37f0de3ceee44a

Observation 258795eb-05ca-4443-bc28-ed728be42d9a · outbound

This paper cites Retrieval augmented classification for long-tail visual recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Retrieval augmented classification for long-tail visual recognition,

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:51.031197Z

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=2026-08-07T12:07:44.796971Z digest=sha256:a6c3b367146546b242f1b3a8ae6211076531e527f1807c368954316eac1e54de

Observation 0937fb6b-bdbe-4547-9e71-5ec20b7d5619 · outbound

This paper cites Vl-ltr: Learning class-wise visual-linguistic represen- tation for long-tailed visual recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Vl-ltr: Learning class-wise visual-linguistic represen- tation for long-tailed visual recognition,

Reference 61

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:50.718207Z

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=2026-08-07T12:07:44.845852Z digest=sha256:6cfb89073b49bd350a4984ac5ee115e784be17cd19c4e77b425499cf5c4c3e04

Observation 8889acae-bfb8-4e3b-8d84-e37ecb167861 · outbound

This paper cites Deep over-sampling frame- work for classifying imbalanced data,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Deep over-sampling frame- work for classifying imbalanced data,

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:50.439140Z

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=2026-08-07T12:07:44.904118Z digest=sha256:2e8ed1cc4f31804af8987a722167dcf2fa0525f416be3c52b100700ecd9386f2

Observation c953591d-d07c-4bac-8114-d94326ef5367 · outbound

This paper cites A survey on long- tailed visual recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion A survey on long- tailed visual recognition,

Reference 63

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:50.148958Z

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=2026-08-07T12:07:44.957225Z digest=sha256:5d605ebace70fa2eed7db41a722f964cecb30f084f4cc649fd8fbeb07a463a1f

Observation 0dd8c12a-417f-44f7-ba3e-e13b83596486 · outbound

This paper cites Deep sets,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Deep sets,

Reference 64

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:49.813940Z

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=2026-08-07T12:07:45.023002Z digest=sha256:6d9921ddecf4d5b86002057ac952b617a3554babb485687a18a52249e9c21a6c

Observation a72d71b2-cf9c-4652-b018-fdc4a6ef4c6e · outbound

This paper cites Deep set prediction networks,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Deep set prediction networks,

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:49.501356Z

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=2026-08-07T12:07:45.087761Z digest=sha256:267489b5dab820649401b4ebcc068d4aed4658f86dad701042b8d16ae42c398a

Observation 706cf300-167a-4649-8589-9d5d1036832c · outbound

This paper cites Deep residual learning for image recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Deep residual learning for image recognition,

Reference 66

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:49.195254Z

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=2026-08-07T12:07:45.147664Z digest=sha256:e9f5a3639bd202aac506779214d675faa7d79202ab38564bcb95da6a5989b753

Observation 898161e4-6369-4a33-b8b1-f369f4464327 · outbound

This paper cites The inaturalist species classification and detection dataset,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion The inaturalist species classification and detection dataset,

Reference 67

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:48.896012Z

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=2026-08-07T12:07:45.218259Z digest=sha256:b18dfdf5ff9ae7eaee4b4c9c81c52880e493eadf763b02de60339f7f32c2eb94

Observation 714309f1-0f87-48b4-8aa6-d76595d6173e · outbound

This paper cites Open long-tailed recognition in a dynamic world,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Open long-tailed recognition in a dynamic world,

Reference 68

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:48.581479Z

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=2026-08-07T12:07:45.288163Z digest=sha256:647177bc84d3303ef4476affa071fb45403b2ab2818bd53d82153c26b2f3bf1c

Observation bad364af-8d17-4a21-a8de-d708e6eb3bb8 · outbound

This paper cites Learning multiple layers of features from tiny images,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Learning multiple layers of features from tiny images,

Reference 69

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:48.340522Z

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=2026-08-07T12:07:45.363137Z digest=sha256:6d8b8c03370b44e9fb19abe9430c67bebdaa6cc98d09ddfb741345874b3a0df5

Observation ea22e9b7-a8b9-4d8c-a1ea-7383bc43d690 · outbound

This paper cites Feature space augmentation for long-tailed data,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Feature space augmentation for long-tailed data,

Reference 70

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:48.121877Z

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=2026-08-07T12:07:45.432972Z digest=sha256:34e0632cb96c6fa2a4bc23f9a8e5e11db1d06e8e1b6a206421f6b1b6d1ea1d5a

Observation 3dd961f8-b5d5-4dea-9539-920d4855a035 · outbound

This paper cites Imagenet large scale visual recognition challenge,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Imagenet large scale visual recognition challenge,

Reference 71

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:47.856125Z

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=2026-08-07T12:07:45.528940Z digest=sha256:1e6f479383092f0cfad18c5a6656ab8e6d7921da7b1a00afef1fa5b258d6937e

Observation 75fc2a3d-d93f-474c-b162-aaa1475d6610 · outbound

This paper cites Places: A 10 million image database for scene recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Places: A 10 million image database for scene recognition,

Reference 72

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:47.590005Z

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=2026-08-07T12:07:45.624575Z digest=sha256:e04ef66110d7e73995211915dd5166ca2b1f83aa15523a70082f60772a1f26ab

Observation 083c9a19-3766-4526-8aac-8c2ed118cc1d · outbound

This paper cites Memory-based jitter: JOURNAL OF LATEX CLASS FILES 13 Improving visual recognition on long-tailed data with diversity in memory,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Memory-based jitter: JOURNAL OF LATEX CLASS FILES 13 Improving visual recognition on long-tailed data with diversity in memory,

Reference 73

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:47.307620Z

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=2026-08-07T12:07:45.716802Z digest=sha256:1045cac37cff4a366e43438458f2069f875e44b17756434ab2deba5b37324aef

Observation 928b154a-6d9a-4d87-b826-cf422d93c33e · outbound

This paper cites An optimal transport view of class-imbalanced visual recognition,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion An optimal transport view of class-imbalanced visual recognition,

Reference 74

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:47.015247Z

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=2026-08-07T12:07:45.786410Z digest=sha256:17e41ab8ecbcaf57064d7cd5e2e793291e1e40895f1f38c33cb7a3aebe10dd56

Observation 26c5d0c2-a198-49da-9b1c-fa14d25156a3 · outbound

This paper cites mixup: Beyond empirical risk minimization,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion mixup: Beyond empirical risk minimization,

Reference 75

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:46.738930Z

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=2026-08-07T12:07:45.876984Z digest=sha256:1cc7e754885081e4ebe2932d6768967f631229cea5e559ab53227a8996acfdfb

Observation 02c77aec-5127-49e2-9aa5-bae1bc9c5b11 · outbound

This paper cites Exploring vision-language models for imbalanced learning,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Exploring vision-language models for imbalanced learning,

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:46.495454Z

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=2026-08-07T12:07:45.944269Z digest=sha256:58766257b352e2932d2b1be3d6b7f13595e570697e8dd14e480f3d9708d70eb2

Observation dc70dc5a-c1a5-414f-9e54-32abc25550ab · outbound

This paper cites Bag of tricks for long-tailed visual recognition with deep convo- lutional neural networks,.

PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion Bag of tricks for long-tailed visual recognition with deep convo- lutional neural networks,

Reference 77

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:07:46.327206Z

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=2026-08-07T12:07:46.025831Z digest=sha256:6430762f5d370b40ee1abec35c3a39f21bb623e67204afeecbcf186082f1032c

Pith citing papers

No inbound Pith citation observations are available.