Extending Video Masked Autoencoders to 128 frames | Paper Citation Record

Observation 84cf1d58-7cf6-4e59-b24a-18365b0499be · outbound

This paper cites Towards long-form video understanding.

Extending Video Masked Autoencoders to 128 frames Towards long-form video understanding

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T16:22:25.014117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57d954e0-e57e-4b91-834e-9520d8a00794 · outbound

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

Extending Video Masked Autoencoders to 128 frames Egoschema: A diagnostic benchmark for very long-form video language understanding

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T16:22:25.018939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e2090b2-dcc2-4824-91ac-5108d39886e7 · outbound

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

Extending Video Masked Autoencoders to 128 frames Long movie clip classification with state-space video models

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.442059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3abf5ab4-b5ec-4dfe-a7e7-e0e7e9f6434f · outbound

This paper cites Selective structured state-spaces for long-form video understanding.

Extending Video Masked Autoencoders to 128 frames Selective structured state-spaces for long-form video understanding

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.428871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e1d2eb4b-a9ef-4679-8eb6-ccfb70df90db · outbound

This paper cites Memory consolidation enables long-context video understanding.

Extending Video Masked Autoencoders to 128 frames Memory consolidation enables long-context video understanding

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.415408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation fad0160e-a622-46f0-8cbe-1ba5c085f687 · outbound

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

Extending Video Masked Autoencoders to 128 frames Memvit: Memory-augmented multiscale vision transformer for efficient long-term video recognition

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.401384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9136e534-9098-4a59-9d9b-2b43c8578db5 · outbound

This paper cites Token turing machines.

Extending Video Masked Autoencoders to 128 frames Token turing machines

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.386697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1ee8d817-2f90-4da5-b5ff-b16c8255302b · outbound

This paper cites Video recap: Recursive captioning of hour-long videos.

Extending Video Masked Autoencoders to 128 frames Video recap: Recursive captioning of hour-long videos

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.374304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 15282ec6-ac03-48a8-bb04-1f898e7a3bc4 · outbound

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

Extending Video Masked Autoencoders to 128 frames A simple recipe for contrastively pre-training video-first encoders beyond 16 frames

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.360794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 96c04c42-cb02-4ce3-a8e5-aba75807fbeb · outbound

This paper cites A simple llm framework for long-range video question-answering.

Extending Video Masked Autoencoders to 128 frames A simple llm framework for long-range video question-answering

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T16:22:25.054724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b28fee82-238e-451f-a888-05e92652f15a · outbound

This paper cites Long-form video- language pre-training with multimodal temporal contrastive learning.

Extending Video Masked Autoencoders to 128 frames Long-form video- language pre-training with multimodal temporal contrastive learning

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.341094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4dc4e05a-4e81-45f9-ba36-ef5bdde63ccb · outbound

This paper cites Koala: Key frame-conditioned long video-llm.

Extending Video Masked Autoencoders to 128 frames Koala: Key frame-conditioned long video-llm

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.328284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9104b8a1-ea81-4e5d-b003-51f7c116eb30 · outbound

This paper cites Masked autoencoders as spatiotemporal learners.

Extending Video Masked Autoencoders to 128 frames Masked autoencoders as spatiotemporal learners

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.316949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 30a10d9c-6a53-456b-9d89-fc6543a31d37 · outbound

This paper cites Videomae v2: Scaling video masked autoencoders with dual masking.

Extending Video Masked Autoencoders to 128 frames Videomae v2: Scaling video masked autoencoders with dual masking

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.304662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 61aa62bd-3850-4120-ade0-88283e9a3003 · outbound

This paper cites VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training.

Extending Video Masked Autoencoders to 128 frames VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.290950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation cdd82006-37e8-4192-a1fe-5725f23d39cc · outbound

This paper cites How can objects help action recognition? In CVPR, 2023.

Extending Video Masked Autoencoders to 128 frames How can objects help action recognition? In CVPR, 2023

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.278784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2d832d9b-485e-4aca-8091-c506b8885877 · outbound

This paper cites Everest: Efficient masked video autoencoder by removing redundant spatiotemporal tokens.

Extending Video Masked Autoencoders to 128 frames Everest: Efficient masked video autoencoder by removing redundant spatiotemporal tokens

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.266111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9d1350a1-3813-4f80-bbf4-6a55f4baba20 · outbound

This paper cites Rescaling egocentric vision: Collection, pipeline and challenges for epic-kitchens-100.

Extending Video Masked Autoencoders to 128 frames Rescaling egocentric vision: Collection, pipeline and challenges for epic-kitchens-100

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.253869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6c0d1bea-e94f-46af-ab04-b4c051bd18c1 · outbound

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

Extending Video Masked Autoencoders to 128 frames Resound: Towards action recognition without representation bias

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.241287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 21f1223f-011f-4832-ade6-2ee718f0afb4 · outbound

This paper cites an unresolved cited work.

Extending Video Masked Autoencoders to 128 frames Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-12T16:22:26.229238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 05497a92-60ff-443e-9f04-71f253a54044 · outbound

This paper cites Bevt: Bert pretraining of video transformers.

Extending Video Masked Autoencoders to 128 frames Bevt: Bert pretraining of video transformers

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.218024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e5e7babb-2187-497a-af9d-76469a1373b0 · outbound

This paper cites Girdhar, A.

Extending Video Masked Autoencoders to 128 frames Girdhar, A

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.205639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 713e89ef-4263-417a-b095-74a19c92e633 · outbound

This paper cites Zero-shot text-to-image generation.

Extending Video Masked Autoencoders to 128 frames Zero-shot text-to-image generation

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.193574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation bc7e4fd2-2979-4311-a58b-b08529e687ad · outbound

This paper cites Masked video distillation: Rethinking masked feature modeling for self-supervised video representation learning.

Extending Video Masked Autoencoders to 128 frames Masked video distillation: Rethinking masked feature modeling for self-supervised video representation learning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.182211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e5511110-75f1-465e-bd26-2f2d846c7286 · outbound

This paper cites Magvit: Masked generative video transformer.

Extending Video Masked Autoencoders to 128 frames Magvit: Masked generative video transformer

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.170158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 929db5b8-04b5-4e3d-a6cc-91d48a12431c · outbound

This paper cites Tokenlearner: What can 8 learned tokens do for images and videos? In NeurIPS, 2021.

Extending Video Masked Autoencoders to 128 frames Tokenlearner: What can 8 learned tokens do for images and videos? In NeurIPS, 2021

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.143450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9cd15a53-f043-4a68-9079-f5e6871c87d9 · outbound

This paper cites something something.

Extending Video Masked Autoencoders to 128 frames something something

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.130927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 319a40db-cab6-42ab-86cd-b86c83095958 · outbound

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

Extending Video Masked Autoencoders to 128 frames An image is worth 16x16 words: Transformers for image recognition at scale

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.118986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d87ef826-a40a-4764-958d-63623af7b0cc · outbound

This paper cites Mgmae: Motion guided masking for video masked autoencoding.

Extending Video Masked Autoencoders to 128 frames Mgmae: Motion guided masking for video masked autoencoding

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.105953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b5b0e6f3-fc2d-408f-a232-3ca3c19afbf2 · outbound

This paper cites Motion-guided masking for spatiotemporal representation learning.

Extending Video Masked Autoencoders to 128 frames Motion-guided masking for spatiotemporal representation learning

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.091040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e32096bb-4f64-4512-ac99-52032f45532d · outbound

This paper cites Video codec design: developing image and video compression systems.

Extending Video Masked Autoencoders to 128 frames Video codec design: developing image and video compression systems

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.077412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9a8ae6a4-ee82-4266-bced-f94d9ea68a02 · outbound

This paper cites Raft: Recurrent all-pairs field transforms for optical flow.

Extending Video Masked Autoencoders to 128 frames Raft: Recurrent all-pairs field transforms for optical flow

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.062271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d71d0fc2-7964-48d3-9875-5cb23baf2090 · outbound

This paper cites Videoprism: A foundational visual encoder for video understanding.

Extending Video Masked Autoencoders to 128 frames Videoprism: A foundational visual encoder for video understanding

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.050812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0c81c503-ca16-426b-8f61-e24d49b7afd8 · outbound

This paper cites Internvideo2: Scaling video foundation models for multimodal video understanding.

Extending Video Masked Autoencoders to 128 frames Internvideo2: Scaling video foundation models for multimodal video understanding

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.037738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 55a81fcf-1c28-4640-b3d8-ce4c2b551f17 · outbound

This paper cites Vivit: A video vision transformer.

Extending Video Masked Autoencoders to 128 frames Vivit: A video vision transformer

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.024691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 07e3e8ce-9ff2-4a61-9d79-e761d97b7bfb · outbound

This paper cites Finite scalar quantization: VQ-V AE made simple.

Extending Video Masked Autoencoders to 128 frames Finite scalar quantization: VQ-V AE made simple

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:26.011181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 02398460-7a6d-40c7-bf63-b314a15cce3f · outbound

This paper cites A Short Note about Kinetics-600.

Extending Video Masked Autoencoders to 128 frames A Short Note about Kinetics-600

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T16:22:25.164843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95ecca2f-f416-4873-9e90-80143ff10102 · outbound

This paper cites A Short Note on the Kinetics-700 Human Action Dataset.

Extending Video Masked Autoencoders to 128 frames A Short Note on the Kinetics-700 Human Action Dataset

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T16:22:25.168857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a196cfee-b1a4-49b0-b4a2-0d09a82b791d · outbound

This paper cites Multiview transformers for video recognition.

Extending Video Masked Autoencoders to 128 frames Multiview transformers for video recognition

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.997209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 33cfc5de-95ae-40d3-8b38-2227648e89d7 · outbound

This paper cites Temporally-Adaptive Models for Efficient Video Understanding.

Extending Video Masked Autoencoders to 128 frames Temporally-Adaptive Models for Efficient Video Understanding

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T16:22:25.176362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f028e33-ae02-4d0b-8d47-ea889ce8eda2 · outbound

This paper cites Training a Large Video Model on a Single Machine in a Day.

Extending Video Masked Autoencoders to 128 frames Training a Large Video Model on a Single Machine in a Day

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-12T16:22:25.180917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72d5d421-0073-40e7-8db3-f1349385d633 · outbound

This paper cites Imagenet-21k pretraining for the masses.

Extending Video Masked Autoencoders to 128 frames Imagenet-21k pretraining for the masses

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.983302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 45a79a2a-274c-496e-b7cf-87f33caffe1d · outbound

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

Extending Video Masked Autoencoders to 128 frames Ego4d: Around the world in 3,000 hours of egocentric video

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.972248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation bdb7e0cb-169d-4786-bfcf-e6475c709066 · outbound

This paper cites Verbs in action: Improving verb understanding in video-language models.

Extending Video Masked Autoencoders to 128 frames Verbs in action: Improving verb understanding in video-language models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.961247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ec83fec6-7af5-4875-aefd-eb8f725487be · outbound

This paper cites Slowfast networks for video recognition.

Extending Video Masked Autoencoders to 128 frames Slowfast networks for video recognition

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.949510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 24b0f31e-184e-43ca-9067-4636c6be323f · outbound

This paper cites Interactive prototype learning for egocentric action recognition.

Extending Video Masked Autoencoders to 128 frames Interactive prototype learning for egocentric action recognition

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.939197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0be7e6c2-5f50-4e9f-aa24-cd85927732bb · outbound

This paper cites Movinets: Mobile video networks for efficient video recognition.

Extending Video Masked Autoencoders to 128 frames Movinets: Mobile video networks for efficient video recognition

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.928022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a08bd723-c388-4787-9478-9e4cdde59e2d · outbound

This paper cites Omnivore: A single model for many visual modalities.

Extending Video Masked Autoencoders to 128 frames Omnivore: A single model for many visual modalities

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.916079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 08528d82-d877-41a5-ba58-e4c47280dda9 · outbound

This paper cites Learning video representations from large language models.

Extending Video Masked Autoencoders to 128 frames Learning video representations from large language models

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.903493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 994e1ecd-afde-4267-9eff-b2a21a9e9a74 · outbound

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

Extending Video Masked Autoencoders to 128 frames Is space-time attention all you need for video understanding? In ICML, 2021

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.891843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 62167356-5e55-4fb7-8620-e87d6e8f161f · outbound

This paper cites Video swin transformer.

Extending Video Masked Autoencoders to 128 frames Video swin transformer

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.879718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation be25e975-2432-4536-8ce7-8d7427f0d842 · outbound

This paper cites Can an image classifier suffice for action recognition? In ICLR, 2022.

Extending Video Masked Autoencoders to 128 frames Can an image classifier suffice for action recognition? In ICLR, 2022

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.868902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5efa996f-7043-42bb-bb20-13945d3dc966 · outbound

This paper cites Object-region video transformers.

Extending Video Masked Autoencoders to 128 frames Object-region video transformers

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.857839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 738d1098-9f5d-4766-8627-53e4d24a5d64 · outbound

This paper cites Aim: Adapting image models for efficient video action recognition.

Extending Video Masked Autoencoders to 128 frames Aim: Adapting image models for efficient video action recognition

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.845804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 26189b8b-33f3-4750-9990-c658006ca20a · outbound

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

Extending Video Masked Autoencoders to 128 frames Video-focalnets: Spatio-temporal focal modulation for video action recognition

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.834222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6d0e83f9-ab6a-4b0e-910c-dc8b000828e3 · outbound

This paper cites Language model beats diffusion–tokenizer is key to visual generation.

Extending Video Masked Autoencoders to 128 frames Language model beats diffusion–tokenizer is key to visual generation

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.819649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 35bf2940-3183-4085-8371-02c89b5ee713 · outbound

This paper cites Finegym: A hierarchical video dataset for fine-grained action understanding.

Extending Video Masked Autoencoders to 128 frames Finegym: A hierarchical video dataset for fine-grained action understanding

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.804450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c0e06bc4-9991-4702-8521-b65e8aa77aa3 · outbound

This paper cites Learning temporal cues for fine-grained action recognition.

Extending Video Masked Autoencoders to 128 frames Learning temporal cues for fine-grained action recognition

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.790238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b2aa5f83-862d-4df6-b1f7-ebe7564d0c09 · outbound

This paper cites Tsm: Temporal shift module for efficient video understanding.

Extending Video Masked Autoencoders to 128 frames Tsm: Temporal shift module for efficient video understanding

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.775928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 33ddac3d-e7d2-4c61-85b0-c7df2c2651a0 · outbound

This paper cites Temporal query networks for fine-grained video understanding.

Extending Video Masked Autoencoders to 128 frames Temporal query networks for fine-grained video understanding

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.762566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d5c37d89-8b6f-4e04-b893-76292cb9fbaf · outbound

This paper cites Combined cnn transformer encoder for enhanced fine-grained human action recognition.

Extending Video Masked Autoencoders to 128 frames Combined cnn transformer encoder for enhanced fine-grained human action recognition

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.751023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c1217cf0-e260-4354-a23a-649cf1548550 · outbound

This paper cites Going deeper with image transformers.

Extending Video Masked Autoencoders to 128 frames Going deeper with image transformers

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.738041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e4c247d4-831e-46c6-a25f-64cfd87e3220 · outbound

This paper cites Scenic: A jax library for computer vision research and beyond.

Extending Video Masked Autoencoders to 128 frames Scenic: A jax library for computer vision research and beyond

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.722729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0a74a736-5133-4c9c-a196-f891b24fb370 · outbound

This paper cites We found this slightly improved accuracy ( +0.5 points on EPIC-Kitchens-100 Verbs and +1.2 points on Diving48).

Extending Video Masked Autoencoders to 128 frames We found this slightly improved accuracy ( +0.5 points on EPIC-Kitchens-100 Verbs and +1.2 points on Diving48)

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.700975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e8883ef5-e7c8-4e61-a54c-8143413ce151 · outbound

This paper cites an unresolved cited work.

Extending Video Masked Autoencoders to 128 frames Unresolved cited work

Reference 66

Resolution: unresolved; raw_fallback, observed 2026-08-12T16:22:25.681314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7121ac07-0f58-47f2-ad01-88e579276083 · outbound

This paper cites 17 Table 9: Model size vs frames.

Extending Video Masked Autoencoders to 128 frames 17 Table 9: Model size vs frames

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.667471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 13270ed7-aa41-42bd-a1da-25f5ef192c76 · outbound

This paper cites Guidelines: • The answer NA means that the abstract and introduction do not include the claims made in the paper.

Extending Video Masked Autoencoders to 128 frames Guidelines: • The answer NA means that the abstract and introduction do not include the claims made in the paper

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.653781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation fd7f5d79-0999-4578-ba91-897e965c755c · outbound

This paper cites Limitations.

Extending Video Masked Autoencoders to 128 frames Limitations

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.636688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 10456fc6-93cc-44fe-982e-3888d20813f1 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not include theoretical results.

Extending Video Masked Autoencoders to 128 frames Guidelines: • The answer NA means that the paper does not include theoretical results

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.619738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 955057ce-da5a-4eab-b8a1-3bb1e743a1f6 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not include experiments.

Extending Video Masked Autoencoders to 128 frames Guidelines: • The answer NA means that the paper does not include experiments

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.605281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 05b446cf-6eb3-4330-affd-25d7dd01dfe0 · outbound

This paper cites Guidelines: • The answer NA means that paper does not include experiments requiring code.

Extending Video Masked Autoencoders to 128 frames Guidelines: • The answer NA means that paper does not include experiments requiring code

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.588626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 903717b9-95c5-4a0b-ab71-e54f72805d1b · outbound

This paper cites Guidelines: • The answer NA means that the paper does not include experiments.

Extending Video Masked Autoencoders to 128 frames Guidelines: • The answer NA means that the paper does not include experiments

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.572605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7504251a-762c-41d2-ad08-4e797b83ce0a · outbound

This paper cites Guidelines: • The answer NA means that the paper does not include experiments.

Extending Video Masked Autoencoders to 128 frames Guidelines: • The answer NA means that the paper does not include experiments

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.559349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e409290e-ad8e-4ba9-95c5-8ff826b82976 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not include experiments.

Extending Video Masked Autoencoders to 128 frames Guidelines: • The answer NA means that the paper does not include experiments

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.543694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 151092d4-fe23-4c42-8e99-94dce5af1702 · outbound

This paper cites Guidelines: • The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics.

Extending Video Masked Autoencoders to 128 frames Guidelines: • The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.528011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 27550e91-dc95-4ad8-834c-1d3ca347c615 · outbound

This paper cites • If the authors answer NA or No, they should explain why their work has no societal impact or why the paper does not address societal impact.

Extending Video Masked Autoencoders to 128 frames • If the authors answer NA or No, they should explain why their work has no societal impact or why the paper does not address societal impact

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.510829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1832e7fb-510a-4c78-80da-e7490525eabf · outbound

This paper cites Guidelines: • The answer NA means that the paper poses no such risks.

Extending Video Masked Autoencoders to 128 frames Guidelines: • The answer NA means that the paper poses no such risks

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.497541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e87e9080-6d21-4d13-8e92-c9dc39889c6e · outbound

This paper cites Guidelines: • The answer NA means that the paper does not use existing assets.

Extending Video Masked Autoencoders to 128 frames Guidelines: • The answer NA means that the paper does not use existing assets

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.484090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0f1ef82c-5084-4726-b5f5-3e7278d9683a · outbound

This paper cites Guidelines: • The answer NA means that the paper does not release new assets.

Extending Video Masked Autoencoders to 128 frames Guidelines: • The answer NA means that the paper does not release new assets

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-12T16:22:25.347041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32ea79b1-a7bb-4d37-9d42-eee4bc252c05 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.

Extending Video Masked Autoencoders to 128 frames Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.464389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1f04bade-1819-48ac-ab45-49e80ce8e8d8 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.

Extending Video Masked Autoencoders to 128 frames Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:22:25.450458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 17e2c672-1e70-46a4-a07b-68f28e108efe · outbound

This paper cites an unresolved cited work.

Extending Video Masked Autoencoders to 128 frames Unresolved cited work

Reference 2023

Resolution: parse uncertain; raw_fallback, observed 2026-08-12T16:22:26.154889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers