Pith. sign in

Paper Citation Record · LEDGER

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos

As of 9 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 0 inbound Pith citation observations for arXiv:2508.21770.

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

pith.paper-citation-record.v1
2508.21770 v2

Coverage vector

measured 59 of 59 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T14:02:05.872722Z

measured 59 of 59 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

59 of 59 outbound references displayed

  • verified exact1
  • verified fuzzy49
  • unresolved8
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c494610a-58b0-4d31-a7b6-0c80420f89ef · outbound

This paper cites Ubnor- mal: New benchmark for supervised open-set video anomaly detection.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Ubnor- mal: New benchmark for supervised open-set video anomaly detection

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:14.607104Z

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=2026-08-05T14:01:59.564950Z digest=sha256:637b150726843e226734f0366f29f8b6a920656af52cd00459bb81a51a3443c5

Observation 4fccf45d-4b79-4a40-95d8-dd36319a87e3 · outbound

This paper cites Towards open set deep networks.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Towards open set deep networks

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:14.498084Z

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=2026-08-05T14:01:59.741279Z digest=sha256:86489b49f878253f60c7cda4e5a4d98c4c1ee0d71ee7de19df012f7e758f1186

Observation cc1f2ea9-6283-4560-9b31-dfbea8634f0f · outbound

This paper cites Is space-time attention all you need for video understanding? InProceedings of the International Conference on Machine Learning (ICML), July 2021.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Is space-time attention all you need for video understanding? InProceedings of the International Conference on Machine Learning (ICML), July 2021

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:14.361736Z

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=2026-08-05T14:01:59.975483Z digest=sha256:e8e1dabc373b9fbf4de42049601cd382118682f45eecdd16975fb009e0a7d604

Observation 500f5cfb-9b58-42ce-a045-cd8a50f365ec · outbound

This paper cites Enlarging instance-specific and class-specific information for open-set action recognition.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Enlarging instance-specific and class-specific information for open-set action recognition

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:14.188134Z

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=2026-08-05T14:02:00.109712Z digest=sha256:a06c450afadab90cdd16799677a137fa59dbf82d0afefd18dfc1b2ac031822b1

Observation 3a761539-6bbd-443a-baae-8ed237cb4a19 · outbound

This paper cites Elaborative rehearsal for zero-shot action recognition.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Elaborative rehearsal for zero-shot action recognition

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-05T14:02:00.192110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:02:00.192110Z digest=sha256:d60dd2776f719abc7a3fe9b32c04a8f998428880ef8749618b9200aa84c3a2dd

Observation ce7c0c73-129b-4b78-8fb7-fb430e31df85 · outbound

This paper cites Wdiscood: Out-of- distribution detection via whitened linear discriminant analysis.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Wdiscood: Out-of- distribution detection via whitened linear discriminant analysis

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:14.024524Z

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=2026-08-05T14:02:00.348788Z digest=sha256:cb0a94841844e4a97a3335a65c3d132d4a8e9bde06a3c4fbf1f98d98028fd005

Observation 1c77dc5e-7b2b-4290-8ced-d051ba3fbbdc · outbound

This paper cites Haa500: Human-centric atomic action dataset with curated videos.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Haa500: Human-centric atomic action dataset with curated videos

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:13.940558Z

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=2026-08-05T14:02:00.439028Z digest=sha256:09837da50e3be239c758f8aaa50f332df0799890d1c9b073160022a7a9386923

Observation 5a4adc85-ee08-4796-916e-c98c8e7905db · outbound

This paper cites Towards unknown-aware learning with virtual outlier synthesis.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Towards unknown-aware learning with virtual outlier synthesis

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:13.644210Z

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=2026-08-05T14:02:00.578152Z digest=sha256:c63f317cfea5ceb6911584b3a79536dd06e7772be6679f37322961d1f804547d

Observation b5dffb49-5c8c-4155-b694-976d266a0012 · outbound

This paper cites Oops! predicting unintentional ac- tion in video.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Oops! predicting unintentional ac- tion in video

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:13.343116Z

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=2026-08-05T14:02:00.696918Z digest=sha256:168089eb9603b826d0f78b72a815c5c3cae86792f158b9560f899bb6cf1a1493

Observation 4b29c84f-1298-4166-b031-c841b3872aa5 · outbound

This paper cites NovelCraft: A Dataset for Novelty Detection and Discovery in Open Worlds.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos NovelCraft: A Dataset for Novelty Detection and Discovery in Open Worlds

Reference 10

Resolution
verified exact
local_arxiv, observed 2026-08-05T14:02:06.442587Z

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=2026-08-05T14:02:00.857266Z digest=sha256:f4c860976aaedbd6e4b0cffd93205a8afdcdb40e70eae4d21a3d710e6633cc39

Observation f335c71d-ca77-4eab-8624-febaea0ce827 · outbound

This paper cites Unsupervised Representation Learning by Predicting Image Rotations.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Unsupervised Representation Learning by Predicting Image Rotations

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-05T14:02:00.976755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:02:00.976755Z digest=sha256:8b74c351f8185ed5f0a4362f4e266cff820d8152391cf3aa2cfc3751e05530c3

Observation a6b816dc-6ac6-4e48-a175-e2b833a6c4dd · outbound

This paper cites Dense open-set recognition with syn- thetic outliers generated by real nvp.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Dense open-set recognition with syn- thetic outliers generated by real nvp

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:13.105602Z

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=2026-08-05T14:02:01.111370Z digest=sha256:47cf5963dfae32c296b15228578f9c8bdd9aa40255742da60aba3e4503b10606

Observation 3221c6d5-d2aa-47d4-b4f8-ecda163b8460 · outbound

This paper cites Learning to discover novel visual categories via deep transfer clustering.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Learning to discover novel visual categories via deep transfer clustering

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:12.930902Z

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=2026-08-05T14:02:01.186296Z digest=sha256:e81f07fd6ff677c12b15cca002cc7e54484b17671d170a0e7344805a91fb7461

Observation 1bdba9f6-4930-4281-bcb3-8e5bfe56a1a1 · outbound

This paper cites Automatically discovering and learning new visual categories with rank- ing statistics.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Automatically discovering and learning new visual categories with rank- ing statistics

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:12.767073Z

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=2026-08-05T14:02:01.306892Z digest=sha256:e85758033b8e2226e196661decc65c43cffb9f352f3992a0981490ef81ad35be

Observation 76da8525-94fa-4fce-9c5a-82b214854fe7 · outbound

This paper cites Autonovel: Automatically discovering and learning novel visual cate- gories.IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(10): 6767–6781, 2021.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Autonovel: Automatically discovering and learning novel visual cate- gories.IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(10): 6767–6781, 2021

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:12.611309Z

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=2026-08-05T14:02:01.420258Z digest=sha256:faffa94448340cd0004994708e7f7f72f39c26523183b8083ca9f92f7c5fd466

Observation f4e04a7b-f4d4-4f3d-a2c1-be977b73d837 · outbound

This paper cites Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet? InProceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 6546–6555, 2018.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet? InProceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 6546–6555, 2018

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:12.465106Z

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=2026-08-05T14:02:01.568984Z digest=sha256:9e5aebeacf2787563cebe16997b0d611f00de34ca9c58cc3c6b629b9b6a06557

Observation 2fc44e2b-0ff3-4f97-a762-be465276dca6 · outbound

This paper cites Video owl-vit: Temporally-consistent open-world localization in video.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Video owl-vit: Temporally-consistent open-world localization in video

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:12.268186Z

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=2026-08-05T14:02:01.711904Z digest=sha256:fc2d15403c9e00c97488eef5056553c161c7c264d6e388bf61a3e69e88402533

Observation dbfb2f24-459b-4e98-935d-61a31caf0d61 · outbound

This paper cites A baseline for detecting misclassified and out- of-distribution examples in neural networks.International Conference on Learning Representations, 2017.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos A baseline for detecting misclassified and out- of-distribution examples in neural networks.International Conference on Learning Representations, 2017

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:12.100141Z

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=2026-08-05T14:02:01.859472Z digest=sha256:1f8131afdc68f0f13345ee521f7c2fe0dbe2d1cf010b116a4623c962f154900a

Observation eefb184b-9bcd-49a5-9baa-0fa8f33eea86 · outbound

This paper cites Deep anomaly detection with outlier exposure.International Conference on Learning Representations, 2019.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Deep anomaly detection with outlier exposure.International Conference on Learning Representations, 2019

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:11.936421Z

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=2026-08-05T14:02:02.004624Z digest=sha256:4f980843826577ca5b263a6adbf092b0ea2721c273727e037f9f0f11046a0abf

Observation 86fe09e9-ec1f-4529-a859-ab67b124e03b · outbound

This paper cites Generalized odin: De- tecting out-of-distribution image without learning from out-of-distribution data.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Generalized odin: De- tecting out-of-distribution image without learning from out-of-distribution data

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:11.790544Z

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=2026-08-05T14:02:02.125505Z digest=sha256:f0ffa39e037e8c433c9d79279339eaed6926d61773424e15c5c42af402c7361d

Observation cad9770e-b561-4603-8198-34cf301899d0 · outbound

This paper cites The Kinetics Human Action Video Dataset.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos The Kinetics Human Action Video Dataset

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-05T14:02:02.276463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:02:02.276463Z digest=sha256:8bcdb9cc1ec8340eb624877673961b2599227f74c5f40898b1966aedc2c7aed2

Observation c5621063-d162-46f4-ba36-664fea4ad350 · outbound

This paper cites Chal- lenges, evaluation and opportunities for open-world learning.Nature Machine Intelli- gence, 6(6):580–588, 2024.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Chal- lenges, evaluation and opportunities for open-world learning.Nature Machine Intelli- gence, 6(6):580–588, 2024

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:11.655563Z

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=2026-08-05T14:02:02.440137Z digest=sha256:6272dccef4633959da9a128c383386c3f3026dd3f9a27d605b5884f3aac869fb

Observation 8e4b0570-c80e-4a39-a6c1-a4438d3c6fd9 · outbound

This paper cites Opengan: Open-set recognition via open data genera- tion.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Opengan: Open-set recognition via open data genera- tion

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:11.515219Z

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=2026-08-05T14:02:02.623178Z digest=sha256:cc3140dc08bc244da2bcae04539e1af880c695a6d25ef5222236196e61c87111

Observation 22802874-4449-4951-8f6e-2790280e88bd · outbound

This paper cites Human action recognition and prediction: A survey.Interna- tional Journal of Computer Vision, 130(5):1366–1401, 2022.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Human action recognition and prediction: A survey.Interna- tional Journal of Computer Vision, 130(5):1366–1401, 2022

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:11.384104Z

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=2026-08-05T14:02:02.758084Z digest=sha256:7be6e3405b035d3188b2595f79c73e1f41bf06150446b1a01e3bb79ed344e81e

Observation fbd90b24-03dd-4766-b5d8-e0a45039c2de · outbound

This paper cites Hmdb: a large video database for human motion recognition.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Hmdb: a large video database for human motion recognition

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:11.220752Z

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=2026-08-05T14:02:02.899424Z digest=sha256:762b9ea28ad3c4336c7da035ca8aa88f37102291027b0c9df0ab8126bd5bb6bc

Observation ad014836-6e04-471f-862e-4581f5b01974 · outbound

This paper cites Resound: Towards action recognition without representation bias.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Resound: Towards action recognition without representation bias

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:11.081851Z

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=2026-08-05T14:02:02.986988Z digest=sha256:d1c063567c9f41c014d696e01b2d93fa5376cc9788fcd1dfec928e5a1fb8c529

Observation a0c76e42-ebf0-4991-a94e-cad8cda903de · outbound

This paper cites Resource-rational analysis: Understanding hu- man cognition as the optimal use of limited computational resources.Behavioral and brain sciences, 43:e1, 2020.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Resource-rational analysis: Understanding hu- man cognition as the optimal use of limited computational resources.Behavioral and brain sciences, 43:e1, 2020

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:10.916377Z

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=2026-08-05T14:02:03.039359Z digest=sha256:44eac586fa5098cdb1e65ad12b4941e9f32e4534b7b4fb7dde46704856e6f13f

Observation 613db08a-00f3-4c9e-b2cd-feed15629500 · outbound

This paper cites Abnormal event detection at 150 fps in matlab.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Abnormal event detection at 150 fps in matlab

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:10.763141Z

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=2026-08-05T14:02:03.094171Z digest=sha256:edfca163a857b99c3e3e65a68200b5d8f4536e4d6439ec9f05391b7a50ff4769

Observation 0d46ae1c-2184-4541-86e7-a7acb2973982 · outbound

This paper cites Anomaly de- tection in crowded scenes.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Anomaly de- tection in crowded scenes

Reference 29

Resolution
metadata mismatch
raw_fallback, observed 2026-08-05T14:02:06.229836Z

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=2026-08-05T14:02:03.136950Z digest=sha256:d0eddfb4a9c9f2d14d9e2e65f438733c66f45697f31f146dda23b5653e0053f7

Observation 1618ee6f-091a-4d8e-bfd4-0d1ecedda25f · outbound

This paper cites HowTo100M: Learning a Text-Video Embedding by Watch- ing Hundred Million Narrated Video Clips.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos HowTo100M: Learning a Text-Video Embedding by Watch- ing Hundred Million Narrated Video Clips

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:10.680199Z

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=2026-08-05T14:02:03.316713Z digest=sha256:cfc94da45be0890113e2ddbd9acb1e695d15332015660ad4dbf8d418f6c523c9

Observation 8af1eb24-6367-4916-be5b-33cfbbe09b3c · outbound

This paper cites Poem: Out-of-distribution detection with pos- terior sampling.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Poem: Out-of-distribution detection with pos- terior sampling

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:10.551577Z

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=2026-08-05T14:02:03.507533Z digest=sha256:e2f45ac79c7b739a2865e82ff1624fc23fe884fabebecb1f1684b2c8af1e6a3e

Observation 4ab5466a-f3e6-4ce8-9f66-58b1a945f861 · outbound

This paper cites Mo- ments in time dataset: one million videos for event understanding.IEEE transactions on pattern analysis and machine intelligence, 42(2):502–508, 2019.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Mo- ments in time dataset: one million videos for event understanding.IEEE transactions on pattern analysis and machine intelligence, 42(2):502–508, 2019

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:10.381973Z

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=2026-08-05T14:02:03.553269Z digest=sha256:435699f9aac3a756a62f0e5ab7dc0452937ca53a8a64d25b12f5da3f29995f97

Observation 8673dd7b-28cf-4cb7-a980-3e24a9fa7645 · outbound

This paper cites Expanding language-image pretrained models for general video recognition.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Expanding language-image pretrained models for general video recognition

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-05T14:02:03.594472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:02:03.594472Z digest=sha256:0735cb033559953664e4aee94e4b954376ff53c479f52a55346d680bdab37f6a

Observation 5965cb6c-c003-492c-b3eb-b552385ce969 · outbound

This paper cites Outlier exposure with confidence control for out-of-distribution detec- tion.Neurocomputing, 441:138–150, 2021.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Outlier exposure with confidence control for out-of-distribution detec- tion.Neurocomputing, 441:138–150, 2021

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:10.250264Z

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=2026-08-05T14:02:03.663952Z digest=sha256:e7535722a523f73ed331551f43cff122b5fbe3830164838dcb92ec78e74fcddb

Observation 43b0e379-fa27-46aa-946b-b97cb0ae7e7f · outbound

This paper cites A survey on vision-based human action recognition.Image and vision computing, 28(6):976–990, 2010.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos A survey on vision-based human action recognition.Image and vision computing, 28(6):976–990, 2010

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:10.120128Z

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=2026-08-05T14:02:03.762859Z digest=sha256:3f08d79217ba89aaae6174d94a877fdfed54190680b4178c7d1b87e71f7908e9

Observation 0c88274e-2914-4fa7-b1ab-7574ef637269 · outbound

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

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Learning transferable visual models from natural language supervision

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:09.995951Z

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=2026-08-05T14:02:03.856227Z digest=sha256:7102c37099e9dea27e0ea86519e157ac9539300ed687bb5450e2eeda0c11f798

Observation 15d0e835-873b-42e7-88cc-876999ec6855 · outbound

This paper cites Fishr: Invariant gradient variances for out-of-distribution generalization.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Fishr: Invariant gradient variances for out-of-distribution generalization

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:09.893998Z

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=2026-08-05T14:02:03.957892Z digest=sha256:fd2da81f354781a457a1a02ae3c52166a819aa9c586ed199b65c36ce1a52f34e

Observation 2a510c09-25be-41ba-ad56-6e5e07bf51cb · outbound

This paper cites If deep learning is the answer, what is the question?Nature Reviews Neuroscience, 22(1):55–67, 2021.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos If deep learning is the answer, what is the question?Nature Reviews Neuroscience, 22(1):55–67, 2021

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-05T14:02:04.067249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:02:04.067249Z digest=sha256:d87075b7652f2006597a44165ebdc17bc69ce6738c9cb47fbbff40bdfa88d0b0

Observation 7f0b9564-2abd-4f87-ab31-6325e71330ce · outbound

This paper cites Meta- recognition: The theory and practice of recognition score analysis.IEEE transactions on pattern analysis and machine intelligence, 33(8):1689–1695, 2011.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Meta- recognition: The theory and practice of recognition score analysis.IEEE transactions on pattern analysis and machine intelligence, 33(8):1689–1695, 2011

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:09.751133Z

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=2026-08-05T14:02:04.147325Z digest=sha256:872dd17cfa43e8db0902f412f2e8c131a514395c86209250c7515cd58cd89e34

Observation 4d9c788d-165c-433b-af06-00aba146c9e3 · outbound

This paper cites UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-05T14:02:04.226399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:02:04.226399Z digest=sha256:6b4997d5818208f8a4fdebc230a7d8a0927b801eae7db34849c8cb9cf483a464

Observation c700c04d-6bc3-40c1-b525-fbf7175aa152 · outbound

This paper cites Real-world anomaly detection in surveillance videos.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Real-world anomaly detection in surveillance videos

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:09.577098Z

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=2026-08-05T14:02:04.324052Z digest=sha256:bd9cc44cf5e5feaaa015139146e6f93c131798eeef4a69a01607ab9765fcf40d

Observation e856d248-1424-47e0-b9f9-f84507e96a64 · outbound

This paper cites Human action recognition from various data modalities: A review.IEEE transactions on pattern analysis and machine intelligence, 45(3):3200–3225, 2022.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Human action recognition from various data modalities: A review.IEEE transactions on pattern analysis and machine intelligence, 45(3):3200–3225, 2022

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:09.378542Z

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=2026-08-05T14:02:04.402105Z digest=sha256:2ba8a7021010551d24ace1df6a47fe370e2dd9cd5d63d504d81d11d9c65c3249

Observation e71b4814-8007-4ffb-a313-a972afcad7fe · outbound

This paper cites Black, Ivan Laptev, and Cordelia Schmid.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Black, Ivan Laptev, and Cordelia Schmid

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:09.193093Z

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=2026-08-05T14:02:04.464878Z digest=sha256:770e8c31a3af4ef0a4fa77c0be5e7344ce2da30fb4a614fd4ec5574ff2cfe3ba

Observation 4afc6e3f-d632-420d-babe-95261d84a10e · outbound

This paper cites Open-set recognition: A good closed-set classifier is all you need? 2021.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Open-set recognition: A good closed-set classifier is all you need? 2021

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:08.991793Z

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=2026-08-05T14:02:04.557425Z digest=sha256:bad972e2289f3a7c2ce2314565d63e47bf1c528e8b9c6d1308058874387a60a3

Observation bedd9d56-d3cb-436c-90a5-96bb781ca5fc · outbound

This paper cites Generalized category discovery.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Generalized category discovery

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:08.881327Z

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=2026-08-05T14:02:04.650860Z digest=sha256:497dd3e5a0275d260d0232216e45da2ce2e87708f29bf4712dafb92f79393faf

Observation fec39636-34ab-453b-9c37-6666dc260ca5 · outbound

This paper cites No representation rules them all in category discovery.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos No representation rules them all in category discovery

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:08.640276Z

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=2026-08-05T14:02:04.718218Z digest=sha256:839e17d7c7ad6362a920494933f0c3ff6fcb9e26e334046150773a410ba80f22

Observation 5bac9760-7640-4d5d-8880-f111f096f965 · outbound

This paper cites Self-supervised video representation learning by pace prediction.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Self-supervised video representation learning by pace prediction

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:08.480574Z

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=2026-08-05T14:02:04.787888Z digest=sha256:541df95a881ff8ed84237f03a3db26a4ea37eaed997fb9081963d5bdaabecb37

Observation ac66d5d3-b773-4a9e-b045-3b934958f55b · outbound

This paper cites Action recognition and detection by com- bining motion and appearance features.THUMOS14 Action Recognition Challenge, 1 (2):2, 2014.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Action recognition and detection by com- bining motion and appearance features.THUMOS14 Action Recognition Challenge, 1 (2):2, 2014

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:08.289468Z

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=2026-08-05T14:02:04.881590Z digest=sha256:010b9b5fe3ed85783d35cd5be4f5b4d18f52936935f31660f344a7e9467b10f1

Observation 3d76a287-af6c-469c-bde0-b99ccc3cfd3f · outbound

This paper cites ActionCLIP: A New Paradigm for Video Action Recognition.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos ActionCLIP: A New Paradigm for Video Action Recognition

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-05T14:02:04.935174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:02:04.935174Z digest=sha256:4a83920acf3e8f27f38bd618554947bb3252feb5dc6cc2005b8132c06e2776f3

Observation 3a16aaa4-b86f-4306-9abd-019f955ab3f0 · outbound

This paper cites Openood: Benchmark- ing generalized out-of-distribution detection.Advances in Neural Information Pro- cessing Systems, 35:32598–32611, 2022.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Openood: Benchmark- ing generalized out-of-distribution detection.Advances in Neural Information Pro- cessing Systems, 35:32598–32611, 2022

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:08.072192Z

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=2026-08-05T14:02:05.014884Z digest=sha256:4408b8b3e42af24aa90b368f3e07e1f54c5bad41ed7dd93b9f0e8b893bddca88

Observation 5e5073cc-84dd-4569-b06c-64f73cb7855a · outbound

This paper cites Generalized out-of- distribution detection: A survey.International Journal of Computer Vision, pages 1–28, 2024.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Generalized out-of- distribution detection: A survey.International Journal of Computer Vision, pages 1–28, 2024

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:07.865968Z

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=2026-08-05T14:02:05.103596Z digest=sha256:f4c067d0993db2830b0e170f4376ded3365c556bafc1a9fa5f809da3d42cb4b2

Observation 9b7c7aa8-c1e7-479a-a0ba-930dae3c597b · outbound

This paper cites Un- derstanding deep learning (still) requires rethinking generalization.Communications of the ACM, 64(3):107–115, 2021.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Un- derstanding deep learning (still) requires rethinking generalization.Communications of the ACM, 64(3):107–115, 2021

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:07.645931Z

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=2026-08-05T14:02:05.216117Z digest=sha256:08aa3012c39077d7ea6df556007f89669a73e0167dd980a3e342d8b2f4c061ec

Observation c095afd6-0bd8-45f0-b4fa-af9e02b90dfe · outbound

This paper cites Mixture outlier exposure: Towards out-of-distribution detection in fine-grained en- vironments.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Mixture outlier exposure: Towards out-of-distribution detection in fine-grained en- vironments

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:07.407597Z

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=2026-08-05T14:02:05.274180Z digest=sha256:48002b7e71695e1c01dd9ba57ef5d3116dadae5de3e5a4a7ed332e403e7ac4c6

Observation 47a6f305-ac19-41bb-9aaf-b037d21b52b0 · outbound

This paper cites Open- mix: Reviving known knowledge for discovering novel visual categories in an open world.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Open- mix: Reviving known knowledge for discovering novel visual categories in an open world

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:07.199110Z

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=2026-08-05T14:02:05.381623Z digest=sha256:ffa011e48dd9ef0c0d7e60ce0e6b0214fa9c4c80706d39c0fa580f77408cf607

Observation c24e56f8-18e8-42a7-9e9e-934521c96303 · outbound

This paper cites Learning placeholders for open-set recognition.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Learning placeholders for open-set recognition

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:07.062700Z

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=2026-08-05T14:02:05.466295Z digest=sha256:5445b041e6e58ed99961d484dea5788e408e389fc46b9edd2d57daecb9716183

Observation aac02e99-d669-4272-bca6-ee4f99b20c7c · outbound

This paper cites Diversified outlier exposure for out-of-distribution detection via in- formative extrapolation.Advances in Neural Information Processing Systems, 36: 22702–22734, 2023.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Diversified outlier exposure for out-of-distribution detection via in- formative extrapolation.Advances in Neural Information Processing Systems, 36: 22702–22734, 2023

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:06.914683Z

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=2026-08-05T14:02:05.542651Z digest=sha256:2198396bf03e0257a842f1b04dcf0e465d337d6f80cc75d8fd2ac4766fa21c42

Observation 3c238e71-90f7-44f6-bf6e-4e3031c6bbd7 · outbound

This paper cites Unleashing mask: Explore the intrinsic out-of-distribution detection capa- bility.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Unleashing mask: Explore the intrinsic out-of-distribution detection capa- bility

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:06.803921Z

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=2026-08-05T14:02:05.634486Z digest=sha256:299297a7fa946c74ae75f89565ab1dafff33bde6f29f266aa9b6ab0fa31ec068

Observation 33fcc031-32cb-4f0a-afcd-e5f7ede42976 · outbound

This paper cites Towards universal representation for unseen action recognition.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Towards universal representation for unseen action recognition

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-05T14:02:05.763997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:02:05.763997Z digest=sha256:250a3b010956e380116126be59f5ae9c1f8f53a47e61a3a45d64d65437a992f3

Observation 2722e854-314d-452b-90d6-c81958eb97ce · outbound

This paper cites Towards open set video anomaly detec- tion.

What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos Towards open set video anomaly detec- tion

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:02:06.642411Z

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=2026-08-05T14:02:05.872722Z digest=sha256:0d860a8bf30a4e2b5a6acea6bd3c05a9fbb1573a72e7af4a435f1688b601caa1

Pith citing papers

No inbound Pith citation observations are available.