Video Understanding by Design: How Datasets Shape Video Models | Paper Citation Record

Observation af737d4e-a076-4b85-807d-542a4c852b3e · outbound

This paper cites Large-scale video classification with convolutional neural networks,.

Video Understanding by Design: How Datasets Shape Video Models Large-scale video classification with convolutional neural networks,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.562439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cf5d4d4-2926-499f-8c04-c9f76b5665c2 · outbound

This paper cites Learning spatiotemporal features with 3d convolutional networks,.

Video Understanding by Design: How Datasets Shape Video Models Learning spatiotemporal features with 3d convolutional networks,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.566161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7b83d8b-aaa4-4957-8ed0-89dbe96e8c9c · outbound

This paper cites Slowfast networks for video recognition,.

Video Understanding by Design: How Datasets Shape Video Models Slowfast networks for video recognition,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.568966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61ed61d3-9c5c-4a18-9fff-f604b1d8a41c · outbound

This paper cites Motion meets attention: Video motion prompts,.

Video Understanding by Design: How Datasets Shape Video Models Motion meets attention: Video motion prompts,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.572025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a9fe7c2-6a88-4b2e-b361-8a1710f8472c · outbound

This paper cites Taylor videos for action recognition,.

Video Understanding by Design: How Datasets Shape Video Models Taylor videos for action recognition,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.574797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 698eff6a-6fdd-4dd2-aa22-1c94c745bf3b · outbound

This paper cites Learnable expansion of graph operators for multi-modal feature fusion,.

Video Understanding by Design: How Datasets Shape Video Models Learnable expansion of graph operators for multi-modal feature fusion,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.578114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc36bfda-5915-4ca3-8b9e-d8733b267178 · outbound

This paper cites Meet jeanie: a similarity measure for 3d skeleton sequences via temporal-viewpoint alignment,.

Video Understanding by Design: How Datasets Shape Video Models Meet jeanie: a similarity measure for 3d skeleton sequences via temporal-viewpoint alignment,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.580999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88974bff-5613-40a0-a9d5-c013942bb74a · outbound

This paper cites Evolving skeletons: Motion dynamics in action recognition,.

Video Understanding by Design: How Datasets Shape Video Models Evolving skeletons: Motion dynamics in action recognition,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.583680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5f942de-b118-4514-ad83-2a2d41453837 · outbound

This paper cites Feature hallucination for self-supervised action recognition,.

Video Understanding by Design: How Datasets Shape Video Models Feature hallucination for self-supervised action recognition,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.586255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa1e96b8-b01f-4e79-801a-75d6ac127e2a · outbound

This paper cites Do language models understand time?.

Video Understanding by Design: How Datasets Shape Video Models Do language models understand time?

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.589156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a144318c-9692-4e1a-b4cc-a8343442d465 · outbound

This paper cites Quo Vadis, Anomaly Detection? LLMs and VLMs in the Spotlight.

Video Understanding by Design: How Datasets Shape Video Models Quo Vadis, Anomaly Detection? LLMs and VLMs in the Spotlight

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.591934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e564258f-e0eb-4074-8427-11388387187a · outbound

This paper cites The journey of action recognition,.

Video Understanding by Design: How Datasets Shape Video Models The journey of action recognition,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.595267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05e508ef-6369-42da-b8dc-847b6e89cf23 · outbound

This paper cites Representation-centric survey of skeletal action recognition and the anubis benchmark,.

Video Understanding by Design: How Datasets Shape Video Models Representation-centric survey of skeletal action recognition and the anubis benchmark,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.598047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 217712fc-9fa7-468a-8a99-833d6bb663f6 · outbound

This paper cites Foundation Models for Video Understanding: A Survey.

Video Understanding by Design: How Datasets Shape Video Models Foundation Models for Video Understanding: A Survey

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.600749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6885caf8-9ccd-4b8a-bb03-9733f743dce4 · outbound

This paper cites Video understanding with large language models: A survey,.

Video Understanding by Design: How Datasets Shape Video Models Video understanding with large language models: A survey,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.603790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a40fdea-d68d-43ba-86ac-02ca168bea99 · outbound

This paper cites The Kinetics Human Action Video Dataset.

Video Understanding by Design: How Datasets Shape Video Models The Kinetics Human Action Video Dataset

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.606822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f95e75f5-7ea5-4e24-af56-dbd9cb00ae5a · outbound

This paper cites The” something something.

Video Understanding by Design: How Datasets Shape Video Models The” something something

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.610179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2f0f853-6642-498a-adf2-59609f1058df · outbound

This paper cites Activi- tynet: A large-scale video benchmark for human activity understanding,.

Video Understanding by Design: How Datasets Shape Video Models Activi- tynet: A large-scale video benchmark for human activity understanding,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.612970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ebc26bc-7b7d-4b17-9189-c162a414c5c0 · outbound

This paper cites Hollywood in homes: Crowdsourcing data collection for activity understanding,.

Video Understanding by Design: How Datasets Shape Video Models Hollywood in homes: Crowdsourcing data collection for activity understanding,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.615770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1c36766-1ff9-4d51-a775-fae9c971cb8b · outbound

This paper cites Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos.

Video Understanding by Design: How Datasets Shape Video Models Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.618568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f3b6bb5-81c6-46bb-be11-5340198aa558 · outbound

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

Video Understanding by Design: How Datasets Shape Video Models Ava: A video dataset of spatio-temporally localized atomic visual actions,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.621704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81b15cac-a4d8-427a-a154-3a2047258c66 · outbound

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

Video Understanding by Design: How Datasets Shape Video Models Rescaling egocentric vision: Collection, pipeline and challenges for epic-kitchens- 100,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.624382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58436897-7102-4e39-b35d-b1844c8ad7a7 · outbound

This paper cites Graph based skeleton motion representation and similarity measurement for action recognition,.

Video Understanding by Design: How Datasets Shape Video Models Graph based skeleton motion representation and similarity measurement for action recognition,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.626977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7b717d8-4c90-4cf4-be6c-e95a231864d8 · outbound

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

Video Understanding by Design: How Datasets Shape Video Models Quo vadis, action recognition? a new model and the kinetics dataset,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.629850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 409b2f64-7add-48cc-b93e-907490fc1b3f · outbound

This paper cites Non-local neural networks,.

Video Understanding by Design: How Datasets Shape Video Models Non-local neural networks,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.632560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 805c6334-b76e-4731-8353-3d4e1412f939 · outbound

This paper cites Spatial temporal graph convolutional networks for skeleton-based action recognition,.

Video Understanding by Design: How Datasets Shape Video Models Spatial temporal graph convolutional networks for skeleton-based action recognition,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.635238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34a16798-62c1-4b3b-bb86-7acda8cb0242 · outbound

This paper cites Vivit: A video vision transformer,.

Video Understanding by Design: How Datasets Shape Video Models Vivit: A video vision transformer,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.637882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fac54d79-ad37-4493-a215-5d8ba1158541 · outbound

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

Video Understanding by Design: How Datasets Shape Video Models Is space-time attention all you need for video understanding?

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.640602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1df2569b-70fe-4751-bfb6-68b4ae774b40 · outbound

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

Video Understanding by Design: How Datasets Shape Video Models Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre- training,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.643269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0fc6081-e0ab-4d7b-aab9-69f4f9ca65f5 · outbound

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

Video Understanding by Design: How Datasets Shape Video Models InternVideo: General Video Foundation Models via Generative and Discriminative Learning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.645943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55acbbb5-9c64-4323-b605-b92249014f24 · outbound

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

Video Understanding by Design: How Datasets Shape Video Models Videomae v2: Scaling video masked autoencoders with dual masking,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.648984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18331253-4077-4f84-a368-b481ae0ab25b · outbound

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

Video Understanding by Design: How Datasets Shape Video Models Internvideo2: Scaling foundation models for multimodal video understanding,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.651787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8197175e-9cfb-4a28-8582-471dc2d84705 · outbound

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

Video Understanding by Design: How Datasets Shape Video Models UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.654342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16c3da7b-43bb-4d12-aed1-a73a304493db · outbound

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

Video Understanding by Design: How Datasets Shape Video Models Hmdb: a large video database for human motion recognition,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.657439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35516b6a-f3be-4ac2-a7d1-686491f95699 · outbound

This paper cites A spatio-temporal descriptor based on 3d-gradients,.

Video Understanding by Design: How Datasets Shape Video Models A spatio-temporal descriptor based on 3d-gradients,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.660022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a8a63d9-f1f4-456a-a99c-f4a1312c2794 · outbound

This paper cites Action recognition with improved trajectories,.

Video Understanding by Design: How Datasets Shape Video Models Action recognition with improved trajectories,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.662771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63fc5404-8e68-459b-8621-267e1d8f186e · outbound

This paper cites Scaling egocentric vision: The epic-kitchens dataset,.

Video Understanding by Design: How Datasets Shape Video Models Scaling egocentric vision: The epic-kitchens dataset,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.665375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad772c31-d47f-48bf-91cc-bcf662bebb83 · outbound

This paper cites Two-stream convolutional networks for action recognition in videos,.

Video Understanding by Design: How Datasets Shape Video Models Two-stream convolutional networks for action recognition in videos,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.667946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2dae815-9191-46da-885b-c4957829917f · outbound

This paper cites Omnivl: One foundation model for image-language and video-language tasks,.

Video Understanding by Design: How Datasets Shape Video Models Omnivl: One foundation model for image-language and video-language tasks,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.670604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcf3a715-2126-4325-8124-ed369c523a1d · outbound

This paper cites Visionllm v2: An end-to-end generalist multimodal large language model for hundreds of vision-language tasks,.

Video Understanding by Design: How Datasets Shape Video Models Visionllm v2: An end-to-end generalist multimodal large language model for hundreds of vision-language tasks,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.673640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 435b8b26-c420-4acd-a4e5-dba506fbf4f0 · outbound

This paper cites Timechat: A time-sensitive multimodal large language model for long video understanding,.

Video Understanding by Design: How Datasets Shape Video Models Timechat: A time-sensitive multimodal large language model for long video understanding,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.676601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b5490e0-2e3a-4634-999e-122cbdad0bbe · outbound

This paper cites VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding.

Video Understanding by Design: How Datasets Shape Video Models VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.679514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5207923e-f815-4db3-9b59-2e52ba6f6ad1 · outbound

This paper cites Unified-io 2: Scaling autoregressive multimodal models with vision language audio and action,.

Video Understanding by Design: How Datasets Shape Video Models Unified-io 2: Scaling autoregressive multimodal models with vision language audio and action,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.682433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dcda8f1-40f6-49e0-868c-1270c6a1440d · outbound

This paper cites Masked feature prediction for self-supervised visual pre-training,.

Video Understanding by Design: How Datasets Shape Video Models Masked feature prediction for self-supervised visual pre-training,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.685162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77021111-4909-4dfc-8655-dbb89abc8b61 · outbound

This paper cites Transductive zero-shot action recog- nition by word-vector embedding,.

Video Understanding by Design: How Datasets Shape Video Models Transductive zero-shot action recog- nition by word-vector embedding,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.687849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6219dd9c-0f4b-4d6b-bf6c-d006c4927ebd · outbound

This paper cites Out-of-distribution detection for generalized zero-shot action recognition,.

Video Understanding by Design: How Datasets Shape Video Models Out-of-distribution detection for generalized zero-shot action recognition,

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.690645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7526746-074c-4203-a8ec-2f782c923469 · outbound

This paper cites Few-shot action recognition with permutation-invariant attention,.

Video Understanding by Design: How Datasets Shape Video Models Few-shot action recognition with permutation-invariant attention,

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.693367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d81fe392-c880-4688-9e6e-3676c10a83e5 · outbound

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

Video Understanding by Design: How Datasets Shape Video Models ActionCLIP: A New Paradigm for Video Action Recognition

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.696663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0853462e-8aa3-42fd-bbba-fb31e8679276 · outbound

This paper cites Temporal-relational crosstransformers for few-shot action recognition,.

Video Understanding by Design: How Datasets Shape Video Models Temporal-relational crosstransformers for few-shot action recognition,

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.699682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77d5d7f8-c3a1-4acc-9e7a-a51fe6cd4de3 · outbound

This paper cites Temporal-viewpoint transportation plan for skeletal few-shot action recognition,.

Video Understanding by Design: How Datasets Shape Video Models Temporal-viewpoint transportation plan for skeletal few-shot action recognition,

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.702438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1dfd0bd-09fc-4b29-bac9-645a425db9ef · outbound

This paper cites Uncertainty-dtw for time series and sequences,.

Video Understanding by Design: How Datasets Shape Video Models Uncertainty-dtw for time series and sequences,

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.705135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 525169ae-a5e4-403a-b3a6-d6cd8e947381 · outbound

This paper cites Reinforced Video Captioning with Entailment Rewards.

Video Understanding by Design: How Datasets Shape Video Models Reinforced Video Captioning with Entailment Rewards

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.707954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff198091-dbd3-4222-a246-9883e9874bfa · outbound

This paper cites Embodied question answering,.

Video Understanding by Design: How Datasets Shape Video Models Embodied question answering,

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.710825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 107ce85e-d625-49ce-a115-a097141dbf44 · outbound

This paper cites Merlot: Multimodal neural script knowledge models,.

Video Understanding by Design: How Datasets Shape Video Models Merlot: Multimodal neural script knowledge models,

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.713506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf8a4492-20c5-4de6-9030-5872e0641fe7 · outbound

This paper cites Flamingo: a visual language model for few-shot learning,.

Video Understanding by Design: How Datasets Shape Video Models Flamingo: a visual language model for few-shot learning,

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.716087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2bbb6d3-55b3-4173-b271-9799c40e42b6 · outbound

This paper cites Human action recognition from various data modalities: A review,.

Video Understanding by Design: How Datasets Shape Video Models Human action recognition from various data modalities: A review,

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.719093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acd93843-1245-4273-9ddf-fc8d3bb2bc92 · outbound

This paper cites Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives.

Video Understanding by Design: How Datasets Shape Video Models Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.721882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c106935-f0ae-487d-9b55-44be443ebbff · outbound

This paper cites Video question answering: A survey of the state-of-the-art,.

Video Understanding by Design: How Datasets Shape Video Models Video question answering: A survey of the state-of-the-art,

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.724813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31bcdc0b-7e56-40b2-81a7-758c6c21f8e3 · outbound

This paper cites A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming.

Video Understanding by Design: How Datasets Shape Video Models A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.730222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2c92449-c826-482c-a6e2-524519aeb595 · outbound

This paper cites Human activity analysis: A review,.

Video Understanding by Design: How Datasets Shape Video Models Human activity analysis: A review,

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.733204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd60c122-08a2-4ac8-a417-484c94867174 · outbound

This paper cites Going deeper into action recognition: A survey,.

Video Understanding by Design: How Datasets Shape Video Models Going deeper into action recognition: A survey,

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.735946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7484f816-5a30-4e7a-9785-c74dc3bc7b56 · outbound

This paper cites A survey on video-based human action recognition: recent updates, datasets, challenges, and applications,.

Video Understanding by Design: How Datasets Shape Video Models A survey on video-based human action recognition: recent updates, datasets, challenges, and applications,

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.738840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9ed3d35-625b-44b0-a307-ecee01b7523f · outbound

This paper cites Vision Transformers for Action Recognition: A Survey.

Video Understanding by Design: How Datasets Shape Video Models Vision Transformers for Action Recognition: A Survey

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.742070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 554aeb2d-04fa-4b0d-a5d9-afeedeadee1a · outbound

This paper cites Video transformers: A survey,.

Video Understanding by Design: How Datasets Shape Video Models Video transformers: A survey,

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.745553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08c4997d-03ab-4165-8fc9-7f2f7dec14ee · outbound

This paper cites End-to-end learning of visual representations from uncurated instruc- tional videos,.

Video Understanding by Design: How Datasets Shape Video Models End-to-end learning of visual representations from uncurated instruc- tional videos,

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.749025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 874c92ce-cc18-49f2-8bf4-abb8e70106f2 · outbound

This paper cites Multimodal learning with transform- ers: A survey,.

Video Understanding by Design: How Datasets Shape Video Models Multimodal learning with transform- ers: A survey,

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.751971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52a66120-939a-45d9-9441-3f6016525276 · outbound

This paper cites A survey on human activity recognition from videos,.

Video Understanding by Design: How Datasets Shape Video Models A survey on human activity recognition from videos,

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.755142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c39646f6-9189-41a6-8854-4eecc7651061 · outbound

This paper cites A comparative review of recent kinect-based action recognition algorithms,.

Video Understanding by Design: How Datasets Shape Video Models A comparative review of recent kinect-based action recognition algorithms,

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.758367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8054463e-bc0c-48d7-9725-c6400020047f · outbound

This paper cites Skeleton- based action recognition with shift graph convolutional network,.

Video Understanding by Design: How Datasets Shape Video Models Skeleton- based action recognition with shift graph convolutional network,

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.761547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25a293b3-e079-4a0d-a344-0898308c7d7e · outbound

This paper cites Graph convo- lutional neural network for human action recognition: A comprehensive survey,.

Video Understanding by Design: How Datasets Shape Video Models Graph convo- lutional neural network for human action recognition: A comprehensive survey,

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.764684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fc55875-7abb-4e8e-82f8-0766c7cbc3cc · outbound

This paper cites A survey on deep learning for skeleton-based human animation,.

Video Understanding by Design: How Datasets Shape Video Models A survey on deep learning for skeleton-based human animation,

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.767528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2b88aff-6e0c-40e3-9551-cae65747091a · outbound

This paper cites A survey on 3d skeleton-based action recognition using learning method,.

Video Understanding by Design: How Datasets Shape Video Models A survey on 3d skeleton-based action recognition using learning method,

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.770265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6139f1af-29f4-43bf-ba9b-efdd8eff4bad · outbound

This paper cites Self-supervised visual feature learning with deep neural networks: A survey,.

Video Understanding by Design: How Datasets Shape Video Models Self-supervised visual feature learning with deep neural networks: A survey,

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.772962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fb5a8a2-c48f-44e3-a6a8-51fa303abafd · outbound

This paper cites Self- supervised learning: Generative or contrastive,.

Video Understanding by Design: How Datasets Shape Video Models Self- supervised learning: Generative or contrastive,

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.775806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0adc5e7-5e0c-4b80-a685-b9b809160857 · outbound

This paper cites Self-supervised representation learning: Introduction, advances, and challenges,.

Video Understanding by Design: How Datasets Shape Video Models Self-supervised representation learning: Introduction, advances, and challenges,

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.778740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d67e78c3-3907-435c-ad8d-98a6ffdf97ae · outbound

This paper cites Deep generative models: Survey,.

Video Understanding by Design: How Datasets Shape Video Models Deep generative models: Survey,

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.781602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08df6e10-aa14-4c6d-a590-a69f6797d422 · outbound

This paper cites A survey of multimodal deep generative models,.

Video Understanding by Design: How Datasets Shape Video Models A survey of multimodal deep generative models,

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.784280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51bc42a8-cf82-4859-8e68-c361b0f90c19 · outbound

This paper cites Sora as an agi world model? a complete survey on text-to-video generation,.

Video Understanding by Design: How Datasets Shape Video Models Sora as an agi world model? a complete survey on text-to-video generation,

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.787325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ff27288-f786-48c8-8049-70c983c38830 · outbound

This paper cites A survey on video diffusion models,.

Video Understanding by Design: How Datasets Shape Video Models A survey on video diffusion models,

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.790189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 348cf097-dd21-4269-8785-def3e3d856c4 · outbound

This paper cites Benchmarking a multimodal and multiview and interactive dataset for human action recognition,.

Video Understanding by Design: How Datasets Shape Video Models Benchmarking a multimodal and multiview and interactive dataset for human action recognition,

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.792842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f2df4d5-0dd3-43a9-8481-1f67f0a90918 · outbound

This paper cites Video benchmarks of human action datasets: a review,.

Video Understanding by Design: How Datasets Shape Video Models Video benchmarks of human action datasets: a review,

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.796479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76cd93f5-0b11-400a-bf4f-7bdce5c6c16a · outbound

This paper cites A review of convolutional-neural-network- based action recognition,.

Video Understanding by Design: How Datasets Shape Video Models A review of convolutional-neural-network- based action recognition,

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.799528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2eb788e-7db7-40e4-9911-5d1d70a88faa · outbound

This paper cites Benchmarking micro-action recognition: Dataset, methods, and applications,.

Video Understanding by Design: How Datasets Shape Video Models Benchmarking micro-action recognition: Dataset, methods, and applications,

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.802273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8df63e0-75e7-40e0-859c-8218a3bcf36f · outbound

This paper cites An outlook into the future of egocentric vision,.

Video Understanding by Design: How Datasets Shape Video Models An outlook into the future of egocentric vision,

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.805214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8f6e50b-f237-40bc-b825-469bc8b99776 · outbound

This paper cites A survey of content-aware video analysis for sports,.

Video Understanding by Design: How Datasets Shape Video Models A survey of content-aware video analysis for sports,

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.807877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b21731e8-c9c5-4fa2-9186-d7403273ec4b · outbound

This paper cites Video transcoding: an overview of various techniques and research issues,.

Video Understanding by Design: How Datasets Shape Video Models Video transcoding: an overview of various techniques and research issues,

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.810764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3c6fe3b-a3b8-43fc-a3db-87bc48f4fde5 · outbound

This paper cites Video description: A survey of methods, datasets, and evaluation metrics,.

Video Understanding by Design: How Datasets Shape Video Models Video description: A survey of methods, datasets, and evaluation metrics,

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.813690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df6379d3-78a0-4078-b712-6fb025e639e8 · outbound

This paper cites Generative multi- view human action recognition,.

Video Understanding by Design: How Datasets Shape Video Models Generative multi- view human action recognition,

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.816412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4eeb544d-2cbb-4849-968a-e1c744b4f1d1 · outbound

This paper cites Human action recognition and prediction: A survey,.

Video Understanding by Design: How Datasets Shape Video Models Human action recognition and prediction: A survey,

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.819066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cb1cf0d-6d3f-45a2-bfae-96ee2912e6d2 · outbound

This paper cites Video generative adversarial networks: a review,.

Video Understanding by Design: How Datasets Shape Video Models Video generative adversarial networks: a review,

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.821755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7227d4e1-5845-42db-bd91-084c134eb6f5 · outbound

This paper cites Search-map-search: a frame selection paradigm for action recognition,.

Video Understanding by Design: How Datasets Shape Video Models Search-map-search: a frame selection paradigm for action recognition,

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.824426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 466a9ec3-f511-4ccc-9a82-7bea40bf394a · outbound

This paper cites Self-supervised learning for videos: A survey,.

Video Understanding by Design: How Datasets Shape Video Models Self-supervised learning for videos: A survey,

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.827055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83d239b4-12f3-4dd2-ad6b-717589ed63cb · outbound

This paper cites On space-time interest points,.

Video Understanding by Design: How Datasets Shape Video Models On space-time interest points,

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.829719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a54a205-b635-4054-a346-79755aa9367a · outbound

This paper cites Histograms of oriented gradients for human detection,.

Video Understanding by Design: How Datasets Shape Video Models Histograms of oriented gradients for human detection,

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.832545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16a61d7f-0eb9-4fd2-8d50-675aa9e0a063 · outbound

This paper cites Dense trajectories and motion boundary descriptors for action recognition,.

Video Understanding by Design: How Datasets Shape Video Models Dense trajectories and motion boundary descriptors for action recognition,

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.835545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 232b5f38-071b-48e5-bd29-c93db579818b · outbound

This paper cites Transformers in vision: A survey,.

Video Understanding by Design: How Datasets Shape Video Models Transformers in vision: A survey,

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.838250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 238925de-89ca-4b9a-8802-0201e4604e44 · outbound

This paper cites Deep Reinforcement Learning: An Overview.

Video Understanding by Design: How Datasets Shape Video Models Deep Reinforcement Learning: An Overview

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.840934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce44ac83-9d05-471c-887f-f45921c23157 · outbound

This paper cites Deep reinforcement learning: A brief survey,.

Video Understanding by Design: How Datasets Shape Video Models Deep reinforcement learning: A brief survey,

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.843803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd59018d-85cd-4943-bd36-770cc3f106ce · outbound

This paper cites Continual lifelong learning with neural networks: A review,.

Video Understanding by Design: How Datasets Shape Video Models Continual lifelong learning with neural networks: A review,

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.846721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f13ee776-fed0-471b-9cd0-df84cc97350a · outbound

This paper cites Federated machine learning: Concept and applications,.

Video Understanding by Design: How Datasets Shape Video Models Federated machine learning: Concept and applications,

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:41.849450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers