Principles of Visual Tokens for Efficient Video Understanding | Paper Citation Record

Observation 5a99891b-2e49-4489-8005-51c9dc53d51a · outbound

This paper cites Vivit: A video vi- sion transformer.

Principles of Visual Tokens for Efficient Video Understanding Vivit: A video vi- sion transformer

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:11.107604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c9348b78-6a67-4449-bb64-609cc30b4912 · outbound

This paper cites Is Space-Time Attention All You Need for Video Understanding?.

Principles of Visual Tokens for Efficient Video Understanding Is Space-Time Attention All You Need for Video Understanding?

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.546390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49cabee7-aefe-4090-8476-4ad7f9bdc92f · outbound

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

Principles of Visual Tokens for Efficient Video Understanding Is space-time attention all you need for video understanding? In ICML, page 4, 2021

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.554368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81fd44e9-98bc-428e-9fa7-c3e18c494187 · outbound

This paper cites Token merging: Your ViT but faster.

Principles of Visual Tokens for Efficient Video Understanding Token merging: Your ViT but faster

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:11.075015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 42b7f1f4-3f60-4fac-a742-73a4fe5dc6ef · outbound

This paper cites Revisiting the” video” in video-language understanding.

Principles of Visual Tokens for Efficient Video Understanding Revisiting the” video” in video-language understanding

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:11.052252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9651a4fb-f220-45f0-8ef8-75e05b8d0472 · outbound

This paper cites Space-time mixing attention for video transformer.

Principles of Visual Tokens for Efficient Video Understanding Space-time mixing attention for video transformer

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:11.031143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation fabe6ce3-449a-4b92-b86a-857a4caa921e · outbound

This paper cites Activitynet: A large-scale video benchmark for human activity understanding.

Principles of Visual Tokens for Efficient Video Understanding Activitynet: A large-scale video benchmark for human activity understanding

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.595147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9612554-9565-471e-920a-d940a518b9df · outbound

This paper cites Quo vadis, action recognition? a new model and the kinetics dataset.

Principles of Visual Tokens for Efficient Video Understanding Quo vadis, action recognition? a new model and the kinetics dataset

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:11.001220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a852fa36-f5f0-458f-bc78-b053c27ab8f5 · outbound

This paper cites An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models, 2024.

Principles of Visual Tokens for Efficient Video Understanding An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models, 2024

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.981335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 25b26d8c-8dc3-44cb-bad3-b381833ec000 · outbound

This paper cites an unresolved cited work.

Principles of Visual Tokens for Efficient Video Understanding Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-12T16:38:10.960743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 47cf182b-374d-48fe-93a6-9457ea518760 · outbound

This paper cites Prune spatio-temporal tokens by semantic-aware temporal accumulation.

Principles of Visual Tokens for Efficient Video Understanding Prune spatio-temporal tokens by semantic-aware temporal accumulation

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.941052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ff94fd5d-3e5c-40e1-83de-4cce007a8738 · outbound

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

Principles of Visual Tokens for Efficient Video Understanding An image is worth 16x16 words: Trans- formers for image recognition at scale

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.635930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b345fdf-3da9-4331-a4cc-dd588465739c · outbound

This paper cites Multiscale vision transformers.

Principles of Visual Tokens for Efficient Video Understanding Multiscale vision transformers

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.910305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 48f3a647-1921-41d7-8c5e-859bf389090c · outbound

This paper cites X3d: Expanding architectures for efficient video recognition.

Principles of Visual Tokens for Efficient Video Understanding X3d: Expanding architectures for efficient video recognition

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.890972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0bd73605-a781-43b2-ac83-0abdbf5e436a · outbound

This paper cites Slowfast networks for video recognition.

Principles of Visual Tokens for Efficient Video Understanding Slowfast networks for video recognition

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.658326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7ea3224-d89b-494d-a436-a9a769696a5a · outbound

This paper cites Efficient video transformers via spatial-temporal token merging for action recognition.

Principles of Visual Tokens for Efficient Video Understanding Efficient video transformers via spatial-temporal token merging for action recognition

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.851935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ec917cda-c365-402b-a165-4e86a39f60ab · outbound

This paper cites Smart frame selection for action recognition.

Principles of Visual Tokens for Efficient Video Understanding Smart frame selection for action recognition

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.670309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3eeda23-3d4a-4dea-9fd3-c64001b2df71 · outbound

This paper cites Watt For What: Rethinking Deep Learning's Energy-Performance Relationship.

Principles of Visual Tokens for Efficient Video Understanding Watt For What: Rethinking Deep Learning's Energy-Performance Relationship

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.676924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb986a7b-b58f-402c-a25d-1fc5628338a2 · outbound

This paper cites Optimizing factorized encoder models: Time and memory reduction for scalable and efficient action recognition.

Principles of Visual Tokens for Efficient Video Understanding Optimizing factorized encoder models: Time and memory reduction for scalable and efficient action recognition

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.812740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2edfc8e9-b2ce-4bce-a2eb-53498af96b52 · outbound

This paper cites something something.

Principles of Visual Tokens for Efficient Video Understanding something something

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.787929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c0a9017a-ad20-4001-8630-4e55eef1602e · outbound

This paper cites Ava: A video dataset of spatio-temporally localized atomic visual actions.

Principles of Visual Tokens for Efficient Video Understanding Ava: A video dataset of spatio-temporally localized atomic visual actions

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.697107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adfa02c1-ed9d-4c8d-90f7-a8970e545584 · outbound

This paper cites an unresolved cited work.

Principles of Visual Tokens for Efficient Video Understanding Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-12T16:38:10.753008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation cfa34fc8-2a72-4cc2-8ae8-ac1bf3f41028 · outbound

This paper cites LookupViT: Compressing visual information to a limited number of tokens.

Principles of Visual Tokens for Efficient Video Understanding LookupViT: Compressing visual information to a limited number of tokens

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-08-12T16:38:10.119977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ecbcfb01-bc9f-473c-92a5-b1b7cdfe0ec4 · outbound

This paper cites Revisiting token pruning for object detection and instance segmentation.

Principles of Visual Tokens for Efficient Video Understanding Revisiting token pruning for object detection and instance segmentation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.714750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 602013d9-90ab-49bc-873f-38010dd65c0a · outbound

This paper cites Swin transformer: 9 Hierarchical vision transformer using shifted windows.

Principles of Visual Tokens for Efficient Video Understanding Swin transformer: 9 Hierarchical vision transformer using shifted windows

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.718586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1340edae-8416-4d56-8865-ae5b6f5ede89 · outbound

This paper cites Video swin transformer.

Principles of Visual Tokens for Efficient Video Understanding Video swin transformer

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.695342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 59cbb268-d70c-42cd-975b-dc68b59c9c99 · outbound

This paper cites Video transformer network.

Principles of Visual Tokens for Efficient Video Understanding Video transformer network

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.671573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6bb2d98a-286b-487b-8c46-1544f41c56a2 · outbound

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

Principles of Visual Tokens for Efficient Video Understanding Expanding language-image pretrained models for gen- eral video recognition

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.737194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0797f54-8feb-45a7-8fdf-0511431ca87b · outbound

This paper cites St-adapter: Parameter-efficient image-to-video transfer learning.

Principles of Visual Tokens for Efficient Video Understanding St-adapter: Parameter-efficient image-to-video transfer learning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.744700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a513123d-c351-407e-95d4-8c80f29e1fa2 · outbound

This paper cites K-centered patch sampling for efficient video recognition.

Principles of Visual Tokens for Efficient Video Understanding K-centered patch sampling for efficient video recognition

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.624875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 34fbc06d-8cd9-44a6-8a19-3d578edff604 · outbound

This paper cites Asano, Is- han Misra Florian Metze, Christoph Feichtenhofer, Andrea Vedaldi, and Jo ˜ao F.

Principles of Visual Tokens for Efficient Video Understanding Asano, Is- han Misra Florian Metze, Christoph Feichtenhofer, Andrea Vedaldi, and Jo ˜ao F

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.602725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d5be688a-fbbc-48ed-862b-48795aed311f · outbound

This paper cites So, Maud Texier, and Jeff Dean.

Principles of Visual Tokens for Efficient Video Understanding So, Maud Texier, and Jeff Dean

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.578776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 89f85019-3d55-4d11-a005-a117a8eef86b · outbound

This paper cites How does the primate brain combine generative and discriminative computations in vision?.

Principles of Visual Tokens for Efficient Video Understanding How does the primate brain combine generative and discriminative computations in vision?

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-12T16:38:10.086545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation afecf784-5a76-4a59-b954-f984930b3757 · outbound

This paper cites Dynamicvit: Efficient vision transformers with dynamic token sparsification.

Principles of Visual Tokens for Efficient Video Understanding Dynamicvit: Efficient vision transformers with dynamic token sparsification

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.773955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6e191aa-4563-456b-9d38-200a2507f493 · outbound

This paper cites TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?.

Principles of Visual Tokens for Efficient Video Understanding TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.781891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c64056be-71b2-4f73-a879-28f300e8441f · outbound

This paper cites Selvaraju, Abhishek Das, Ramakrishna Vedantam, Michael Cogswell, Devi Parikh, and Dhruv Ba- tra.

Principles of Visual Tokens for Efficient Video Understanding Selvaraju, Abhishek Das, Ramakrishna Vedantam, Michael Cogswell, Devi Parikh, and Dhruv Ba- tra

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.531612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 253eb58c-3783-48b2-8a40-03be771481f6 · outbound

This paper cites Only time can tell: Discovering temporal data for temporal modeling.

Principles of Visual Tokens for Efficient Video Understanding Only time can tell: Discovering temporal data for temporal modeling

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.507034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d826674c-9cc0-4f29-8b22-2b105315db20 · outbound

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

Principles of Visual Tokens for Efficient Video Understanding UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.801167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74e6b19c-f94e-4ecb-9e89-7e5ed0031801 · outbound

This paper cites VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training.

Principles of Visual Tokens for Efficient Video Understanding VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.806583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db30876b-61c8-4e75-900b-c2afe0611f5f · outbound

This paper cites Training data-efficient image transformers & distillation through at- tention.

Principles of Visual Tokens for Efficient Video Understanding Training data-efficient image transformers & distillation through at- tention

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.812884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42879cc2-add6-46c6-ae1a-77b6447084ba · outbound

This paper cites Attention is all you need.

Principles of Visual Tokens for Efficient Video Understanding Attention is all you need

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.463112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 723c88fb-5569-4fa7-b021-9037e90ce588 · outbound

This paper cites Efficient video transformers with spatial- temporal token selection.

Principles of Visual Tokens for Efficient Video Understanding Efficient video transformers with spatial- temporal token selection

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.430041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation dffe762e-8325-4ff8-993b-c2834b93bc77 · outbound

This paper cites Actionclip: Adapting language-image pretrained models for video action recognition.

Principles of Visual Tokens for Efficient Video Understanding Actionclip: Adapting language-image pretrained models for video action recognition

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.405228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 17e7c3c5-5d9f-40c0-8763-a95ada95aafc · outbound

This paper cites Vila: Efficient video-language alignment for video question answering.

Principles of Visual Tokens for Efficient Video Understanding Vila: Efficient video-language alignment for video question answering

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.378103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 84b220ef-6547-4687-ac53-421d9391f825 · outbound

This paper cites Video-focalnets: Spatio-temporal focal modu- lation for video action recognition.

Principles of Visual Tokens for Efficient Video Understanding Video-focalnets: Spatio-temporal focal modu- lation for video action recognition

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.351817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 665eb6e4-ab17-43a3-b74d-afbf74dd7766 · outbound

This paper cites Manmatha, Alex Smola, and Philipp Kr¨ahenb¨uhl.

Principles of Visual Tokens for Efficient Video Understanding Manmatha, Alex Smola, and Philipp Kr¨ahenb¨uhl

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.325086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 7b6373a5-13ef-4083-b0ba-fab7f0b5b684 · outbound

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

Principles of Visual Tokens for Efficient Video Understanding Memvit: Memory-augmented multiscale vision transformer for efficient long-term video recognition

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.306355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 79bb0272-bd07-4e33-93ce-2f1be485168c · outbound

This paper cites Can i trust your answer? visually grounded video question answering.

Principles of Visual Tokens for Efficient Video Understanding Can i trust your answer? visually grounded video question answering

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-12T16:38:09.859186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5201b10-1d8b-4aa0-a730-2072546fec75 · outbound

This paper cites Aim: Adapting image models for effi- cient video action recognition.

Principles of Visual Tokens for Efficient Video Understanding Aim: Adapting image models for effi- cient video action recognition

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.271496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 7768a25e-84b1-41fe-a56b-15c65398e260 · outbound

This paper cites A-vit: Adap- tive tokens for efficient vision transformer.

Principles of Visual Tokens for Efficient Video Understanding A-vit: Adap- tive tokens for efficient vision transformer

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.253123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a7ba7476-5d2f-4e15-8c85-82037d865916 · outbound

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

Principles of Visual Tokens for Efficient Video Understanding Self-chained image-language model for video localization and question answering

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.235125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6f62fb58-6e13-44f0-b29d-15c2176a3f41 · outbound

This paper cites Pyramid feature attention net- work for saliency detection.

Principles of Visual Tokens for Efficient Video Understanding Pyramid feature attention net- work for saliency detection

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.217473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c2c53224-c922-44fb-bbfc-34ab9845defc · outbound

This paper cites How can objects help action recognition? 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 2353–2362, 2023.

Principles of Visual Tokens for Efficient Video Understanding How can objects help action recognition? 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 2353–2362, 2023

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:38:10.197334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 95ba41bf-3a83-443d-8bac-6c62795b021e · outbound

This paper cites ECO: Efficient Convolutional Network for Online Video Understanding.

Principles of Visual Tokens for Efficient Video Understanding ECO: Efficient Convolutional Network for Online Video Understanding

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-08-12T16:38:09.954883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers