Paper Citation Record · LEDGER

AdaVid: Adaptive Video-Language Pretraining

As of 18 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2504.12513.

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

pith.paper-citation-record.v1
2504.12513 v1

Coverage vector

measured 51 of 51 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T12:35:56.191733Z

measured 51 of 51 standing notices

One-hop event checks from named stored sources.

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

measured 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

51 of 51 outbound references displayed

verified exact1
verified fuzzy24
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fe9c2dec-853d-4ac7-80c4-21ac84cb7edc · outbound

This paper cites Hiervl: Learning hierarchical video-language embeddings.

AdaVid: Adaptive Video-Language Pretraining Hiervl: Learning hierarchical video-language embeddings

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.966485Z

Source-reported events for the cited work

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

Observation 0aef341b-cf31-4931-b3e5-5a06b043f0b8 · outbound

This paper cites Frozen in time: A joint video and image encoder for end-to- end retrieval.

AdaVid: Adaptive Video-Language Pretraining Frozen in time: A joint video and image encoder for end-to- end retrieval

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.951522Z

Source-reported events for the cited work

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

Observation 44a795ac-f4d3-428b-b48a-d2a600b54f28 · outbound

This paper cites Memory Consolidation Enables Long-Context Video Understanding.

AdaVid: Adaptive Video-Language Pretraining Memory Consolidation Enables Long-Context Video Understanding

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:55.963796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52cf30be-8cf9-44a7-9954-b313918114dc · outbound

This paper cites Longformer: The Long-Document Transformer.

AdaVid: Adaptive Video-Language Pretraining Longformer: The Long-Document Transformer

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:55.969231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9c3490f-ca98-4857-86ef-acff910beb61 · outbound

This paper cites Is space-time attention all you need for video understanding? In ICML, page 4, 2021.

AdaVid: Adaptive Video-Language Pretraining Is space-time attention all you need for video understanding? In ICML, page 4, 2021

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.936390Z

Source-reported events for the cited work

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

Observation 6e27c4bb-9e01-49fc-90e2-efccd3fd852d · outbound

This paper cites Flexivit: One model for all patch sizes.

AdaVid: Adaptive Video-Language Pretraining Flexivit: One model for all patch sizes

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.921806Z

Source-reported events for the cited work

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

Observation f473e052-b15d-4cb3-b7c0-61d167d87e89 · outbound

This paper cites Once-for-All: Train One Network and Specialize it for Efficient Deployment.

AdaVid: Adaptive Video-Language Pretraining Once-for-All: Train One Network and Specialize it for Efficient Deployment

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:55.984188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 824ac077-966e-42ea-be87-e6d81d372349 · outbound

This paper cites Emerg- ing properties in self-supervised vision transformers.

AdaVid: Adaptive Video-Language Pretraining Emerg- ing properties in self-supervised vision transformers

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.907252Z

Source-reported events for the cited work

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

Observation 096fdd9b-bd77-4d49-a29c-37af99143617 · outbound

This paper cites Vision transformer slimming: Multi-dimension searching in continuous optimiza- tion space.

AdaVid: Adaptive Video-Language Pretraining Vision transformer slimming: Multi-dimension searching in continuous optimiza- tion space

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.892774Z

Source-reported events for the cited work

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

Observation 0722223b-cbd0-402f-97d8-b8f9f094dccf · outbound

This paper cites Towards the Limit of Network Quantization.

AdaVid: Adaptive Video-Language Pretraining Towards the Limit of Network Quantization

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:55.998203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05a3fe94-49c0-4002-826b-fe1afda5c235 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

AdaVid: Adaptive Video-Language Pretraining BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.003372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 440cb46e-30f8-4f78-8fa4-889d3d75a44a · outbound

This paper cites Matformer: Nested transformer for elastic inference.

AdaVid: Adaptive Video-Language Pretraining Matformer: Nested transformer for elastic inference

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.877891Z

Source-reported events for the cited work

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

Observation 77641918-6f5d-471a-85c3-986fcb0da2e0 · outbound

This paper cites Slowfast networks for video recognition.

AdaVid: Adaptive Video-Language Pretraining Slowfast networks for video recognition

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.861335Z

Source-reported events for the cited work

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

Observation 05e8a850-a9b9-4757-bc7a-853394a9cc16 · outbound

This paper cites Ego4d: Around the world in 3,000 hours of egocentric video.

AdaVid: Adaptive Video-Language Pretraining Ego4d: Around the world in 3,000 hours of egocentric video

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.846268Z

Source-reported events for the cited work

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

Observation e3809cd4-506c-4386-91d2-8d6271a610d4 · outbound

This paper cites Ego4d: Around the world in 3,000 hours of egocentric video.

AdaVid: Adaptive Video-Language Pretraining Ego4d: Around the world in 3,000 hours of egocentric video

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.832277Z

Source-reported events for the cited work

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

Observation da3a14b4-915a-41bd-924d-3e905235e210 · outbound

This paper cites Dynamic convnets on tiny devices via nested sparsity.

AdaVid: Adaptive Video-Language Pretraining Dynamic convnets on tiny devices via nested sparsity

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.818036Z

Source-reported events for the cited work

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

Observation bcaa72c8-997d-445c-8839-ea0a049f07a6 · outbound

This paper cites Transkimmer: Transformer Learns to Layer-wise Skim.

AdaVid: Adaptive Video-Language Pretraining Transkimmer: Transformer Learns to Layer-wise Skim

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.031204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fccdba26-2254-439b-892c-2250a6d5162c · outbound

This paper cites Distilling the Knowledge in a Neural Network.

AdaVid: Adaptive Video-Language Pretraining Distilling the Knowledge in a Neural Network

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.035899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4640f7b3-90cc-446e-8e9c-ce294c95de7e · outbound

This paper cites Training Compute-Optimal Large Language Models.

AdaVid: Adaptive Video-Language Pretraining Training Compute-Optimal Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.040813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10756d83-cb59-4617-841a-a84c00ef0b31 · outbound

This paper cites Dynabert: Dynamic bert with adaptive width and depth.

AdaVid: Adaptive Video-Language Pretraining Dynabert: Dynamic bert with adaptive width and depth

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.804032Z

Source-reported events for the cited work

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

Observation 7a036d8c-987c-43d3-a4b4-52b26a4e5795 · outbound

This paper cites Long movie clip classification with state-space video models.

AdaVid: Adaptive Video-Language Pretraining Long movie clip classification with state-space video models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.049562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fbb887f-d92d-485c-ab64-82a673efe4b0 · outbound

This paper cites Video ReCap: Recursive Captioning of Hour-Long Videos.

AdaVid: Adaptive Video-Language Pretraining Video ReCap: Recursive Captioning of Hour-Long Videos

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.054262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d14186c5-df10-40b1-a9b3-05541d0585c1 · outbound

This paper cites Perceiver IO: A General Architecture for Structured Inputs & Outputs.

AdaVid: Adaptive Video-Language Pretraining Perceiver IO: A General Architecture for Structured Inputs & Outputs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.058930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0615abc7-7681-4708-a7c2-e681c661cba4 · outbound

This paper cites Matryoshka representation learning.

AdaVid: Adaptive Video-Language Pretraining Matryoshka representation learning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.780186Z

Source-reported events for the cited work

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

Observation c354b6f8-641f-409a-b30b-0c17bbe8b3ee · outbound

This paper cites Block Pruning For Faster Transformers.

AdaVid: Adaptive Video-Language Pretraining Block Pruning For Faster Transformers

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.068793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc3b5e32-5c90-4b00-be4f-a08a413218d0 · outbound

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

AdaVid: Adaptive Video-Language Pretraining Resound: Towards action recognition without representation bias

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.765223Z

Source-reported events for the cited work

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

Observation ae65ca19-72ad-4e95-bdf9-61c8ab151262 · outbound

This paper cites Egocentric Video-Language Pretraining.

AdaVid: Adaptive Video-Language Pretraining Egocentric Video-Language Pretraining

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.078363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce75f7db-64a8-4ce0-9e2e-526e496bf87d · outbound

This paper cites Egocentric video-language pretraining.

AdaVid: Adaptive Video-Language Pretraining Egocentric video-language pretraining

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.749579Z

Source-reported events for the cited work

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

Observation c51ad084-7082-426e-b1d4-73f91270ff0b · outbound

This paper cites Rethinking the Value of Network Pruning.

AdaVid: Adaptive Video-Language Pretraining Rethinking the Value of Network Pruning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.087445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0d0ef6f-8449-4594-a162-77d548a1b18a · outbound

This paper cites Decoupled Weight Decay Regularization.

AdaVid: Adaptive Video-Language Pretraining Decoupled Weight Decay Regularization

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.092058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2053245-e3a9-4b9c-93a3-30288afa8d6e · outbound

This paper cites UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation.

AdaVid: Adaptive Video-Language Pretraining UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.096502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87c13dce-107c-453e-8ca7-06937970a679 · outbound

This paper cites Egoschema: A diagnostic benchmark for very long- form video language understanding.

AdaVid: Adaptive Video-Language Pretraining Egoschema: A diagnostic benchmark for very long- form video language understanding

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.735087Z

Source-reported events for the cited work

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

Observation d2b4998c-b90c-492c-baa6-b8160e4604e6 · outbound

This paper cites Howto100m: Learning a text-video embedding by watching hundred mil- lion narrated video clips.

AdaVid: Adaptive Video-Language Pretraining Howto100m: Learning a text-video embedding by watching hundred mil- lion narrated video clips

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.720661Z

Source-reported events for the cited work

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

Observation 8a0b218f-5f8f-4904-8cf0-e37b93acfa7b · outbound

This paper cites End-to-end learn- ing of visual representations from uncurated instructional videos.

AdaVid: Adaptive Video-Language Pretraining End-to-end learn- ing of visual representations from uncurated instructional videos

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.706236Z

Source-reported events for the cited work

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

Observation cc4a0554-9109-4996-9e89-d03841bb85ca · outbound

This paper cites A sim- ple recipe for contrastively pre-training video-first encoders beyond 16 frames.

AdaVid: Adaptive Video-Language Pretraining A sim- ple recipe for contrastively pre-training video-first encoders beyond 16 frames

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.691703Z

Source-reported events for the cited work

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

Observation 721ea63a-ec2c-4c0c-93db-3822f6387b3a · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

AdaVid: Adaptive Video-Language Pretraining Learning transferable visual models from natural language supervi- sion

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.119502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc351f54-06a2-4124-a937-65c6e3239472 · outbound

This paper cites SHARCS: Efficient Transformers through Routing with Dynamic Width Sub-networks.

AdaVid: Adaptive Video-Language Pretraining SHARCS: Efficient Transformers through Routing with Dynamic Width Sub-networks

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-08-16T12:35:56.322949Z

Source-reported events for the cited work

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

Observation a1a911d8-a3d9-4c5e-938e-8a01a045b54e · outbound

This paper cites DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter.

AdaVid: Adaptive Video-Language Pretraining DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.128650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e87bcd01-65a0-40f3-874b-df2ac13f6d83 · outbound

This paper cites Q- bert: Hessian based ultra low precision quantization of bert.

AdaVid: Adaptive Video-Language Pretraining Q- bert: Hessian based ultra low precision quantization of bert

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.668159Z

Source-reported events for the cited work

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

Observation 63612549-91f1-42c6-84b6-e2ea945978e7 · outbound

This paper cites Training data-efficient image transformers & distillation through atten- tion.

AdaVid: Adaptive Video-Language Pretraining Training data-efficient image transformers & distillation through atten- tion

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.653140Z

Source-reported events for the cited work

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

Observation 2f04f4e1-1728-4516-9703-d2657e51f998 · outbound

This paper cites Attention is all you need.

AdaVid: Adaptive Video-Language Pretraining Attention is all you need

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.142606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3a657a0-3aed-46bf-99ea-320548a525cc · outbound

This paper cites Deformable video trans- former.

AdaVid: Adaptive Video-Language Pretraining Deformable video trans- former

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.628578Z

Source-reported events for the cited work

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

Observation 24561286-af50-4f6d-a761-985ccb83a42c · outbound

This paper cites VideoAgent: Long-form Video Understanding with Large Language Model as Agent.

AdaVid: Adaptive Video-Language Pretraining VideoAgent: Long-form Video Understanding with Large Language Model as Agent

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.151992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c970475-6e73-41c5-a6db-0b8dcfacdd20 · outbound

This paper cites InternVideo: General Video Foundation Models via Generative and Discriminative Learning.

AdaVid: Adaptive Video-Language Pretraining InternVideo: General Video Foundation Models via Generative and Discriminative Learning

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.157243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8060ef7f-6824-4eda-b5e7-a5e9ba352308 · outbound

This paper cites Memvit: Memory-augmented multiscale vision transformer for efficient long-term video recognition.

AdaVid: Adaptive Video-Language Pretraining Memvit: Memory-augmented multiscale vision transformer for efficient long-term video recognition

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.162838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 052cd404-e35f-47d8-b9a3-ced47168b153 · outbound

This paper cites VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding.

AdaVid: Adaptive Video-Language Pretraining VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.167427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6b921f7-1817-4f60-b8c9-178b349f5c63 · outbound

This paper cites Slimmable Neural Networks.

AdaVid: Adaptive Video-Language Pretraining Slimmable Neural Networks

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.172291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c19320ce-cf02-4109-856d-7fe29833806a · outbound

This paper cites Self-chained image-language model for video localization and question answering.

AdaVid: Adaptive Video-Language Pretraining Self-chained image-language model for video localization and question answering

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.177310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5739293f-3212-42ca-a1a7-c8fe5a48e90b · outbound

This paper cites Poa: Pre-training once for models of all sizes.

AdaVid: Adaptive Video-Language Pretraining Poa: Pre-training once for models of all sizes

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.595138Z

Source-reported events for the cited work

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

Observation d9093c44-da05-4731-ab8f-e1582d8778d9 · outbound

This paper cites Mgsampler: An explainable sampling strategy for video ac- tion recognition.

AdaVid: Adaptive Video-Language Pretraining Mgsampler: An explainable sampling strategy for video ac- tion recognition

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-16T12:35:56.186656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 907ccd42-b7ab-41b0-88fb-8defaf1949d5 · outbound

This paper cites FLOPs computation A.1.

AdaVid: Adaptive Video-Language Pretraining FLOPs computation A.1

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:35:56.571000Z

Source-reported events for the cited work

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

Pith citing papers

No inbound Pith citation observations are available.