{"url":"/dataset/something-something-v2","name":"Something-Something V2","full_name":null,"description_markdown":"The 20BN-SOMETHING-SOMETHING V2 dataset is a large collection of labeled video clips that show humans performing pre-defined basic actions with everyday objects. The dataset was created by a large number of crowd workers. It allows machine learning models to develop fine-grained understanding of basic actions that occur in the physical world. It contains 220,847 videos, with 168,913 in the training set, 24,777 in the validation set and 27,157 in the test set. There are 174 labels.\r\n\r\n[Source](https://developer.qualcomm.com/software/ai-datasets/something-something)\r\n\r\n[Image Source](https://developer.qualcomm.com/software/ai-datasets/something-something)","description_withheld":null,"homepage":"https://developer.qualcomm.com/software/ai-datasets/something-something","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-something-something-video-database-for","title":"The \"something something\" video database for learning and evaluating visual common sense","first_author":"Raghav Goyal","url":null},"license":{"name":"Custom","url":"https://20bn.com/licensing/datasets/academic"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Action Recognition","url":"/task/action-recognition-in-videos","datasets_with_task":"/datasets/task/action-recognition-in-videos"},{"name":"Action Classification","url":"/task/action-classification","datasets_with_task":"/datasets/task/action-classification"},{"name":"Action Recognition In Videos","url":"/task/action-recognition-in-videos-2","datasets_with_task":"/datasets/task/action-recognition-in-videos-2"},{"name":"Video Prediction","url":"/task/video-prediction","datasets_with_task":"/datasets/task/video-prediction"},{"name":"Video Classification","url":"/task/video-classification","datasets_with_task":"/datasets/task/video-classification"},{"name":"Text-to-Video Generation","url":"/task/text-to-video-generation","datasets_with_task":"/datasets/task/text-to-video-generation"},{"name":"Early Action Prediction","url":"/task/early-action-prediction","datasets_with_task":"/datasets/task/early-action-prediction"},{"name":"General Action Video Anomaly Detection","url":"/task/general-action-video-anomaly-detection","datasets_with_task":"/datasets/task/general-action-video-anomaly-detection"}],"languages":[],"variants":["Something-Something V2"],"data_loaders":[{"repo":"https://github.com/open-mmlab/mmaction2","url":"https://github.com/open-mmlab/mmaction2/blob/master/tools/data/sthv2/README.md","frameworks":["pytorch"]}],"num_papers_in_archive":290,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset_variant":"Something-Something V2","rows":123,"metrics":["Top-1 Accuracy","Top-5 Accuracy","Parameters","GFLOPs"],"first_row_in_archive_order":{"model":"MVD (Kinetics400 pretrain, ViT-H, 16 frame)","paper":"/paper/masked-video-distillation-rethinking-masked","metrics":{"GFLOPs":"1192x6","Parameters":"633","Top-1 Accuracy":"77.3","Top-5 Accuracy":"95.7"},"code_links":[{"title":"ruiwang2021/mvd","url":"https://github.com/ruiwang2021/mvd"},{"title":"2023-MindSpore-4/Code-5","url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/MVD"},{"title":"Mind23-2/MindCode-3","url":"https://github.com/Mind23-2/MindCode-3/tree/main/MVD"},{"title":"Mind23-2/MindCode-101","url":"https://github.com/Mind23-2/MindCode-101/tree/main/MVD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-recognition-in-videos-on-something-3","task":"Action Recognition In Videos","dataset_variant":"Something-Something V2","rows":4,"metrics":["Top-1 Accuracy","Top-5 Accuracy"],"first_row_in_archive_order":{"model":"STM (16 frames, ImageNet pretraining)","paper":"/paper/stm-spatiotemporal-and-motion-encoding-for","metrics":{"Top-1 Accuracy":"64.2","Top-5 Accuracy":"89.8"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/general-action-video-anomaly-detection-on","task":"General Action Video Anomaly Detection","dataset_variant":"Something-Something V2","rows":3,"metrics":["Avg. ROC-AUC","Architecture"],"first_row_in_archive_order":{"model":"Pooled Image Level kNN","paper":"/paper/approaches-toward-physical-and-general-video","metrics":{"Architecture":"ViT","Avg. ROC-AUC":"0.58"},"code_links":[{"title":"laurarkart/Physical-Anomalous-Trajectory-or-Motion-PHANTOM-Dataset","url":"https://github.com/laurarkart/Physical-Anomalous-Trajectory-or-Motion-PHANTOM-Dataset"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-classification-on-something-something-2","task":"Action Classification","dataset_variant":"Something-Something V2","rows":1,"metrics":["Acc@1","Acc@5"],"first_row_in_archive_order":{"model":"AdaMAE","paper":"/paper/adamae-adaptive-masking-for-efficient","metrics":{"Acc@1":"70.04","Acc@5":"92.7"},"code_links":[{"title":"wgcban/adamae","url":"https://github.com/wgcban/adamae"},{"title":"Nithin-GK/UniteandConquer","url":"https://github.com/Nithin-GK/UniteandConquer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-to-video-generation-on-something","task":"Text-to-Video Generation","dataset_variant":"Something-Something V2","rows":1,"metrics":["FVD"],"first_row_in_archive_order":{"model":"MAGVIT","paper":"/paper/magvit-masked-generative-video-transformer","metrics":{"FVD":"79.1"},"code_links":[{"title":"google-research/magvit","url":"https://github.com/google-research/magvit"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-classification-on-something-something-1","task":"Video Classification","dataset_variant":"Something-Something V2","rows":1,"metrics":["Top-5 Accuracy"],"first_row_in_archive_order":{"model":"MSNet-R50En (ours)","paper":"/paper/motionsqueeze-neural-motion-feature-learning","metrics":{"Top-5 Accuracy":"91"},"code_links":[{"title":"arunos728/MotionSqueeze","url":"https://github.com/arunos728/MotionSqueeze"},{"title":"arunos728/arunos728.github.io","url":"https://github.com/arunos728/arunos728.github.io"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-prediction-on-something-something-v2","task":"Video Prediction","dataset_variant":"Something-Something V2","rows":1,"metrics":["FVD"],"first_row_in_archive_order":{"model":"MAGVIT","paper":"/paper/magvit-masked-generative-video-transformer","metrics":{"FVD":"28.5"},"code_links":[{"title":"google-research/magvit","url":"https://github.com/google-research/magvit"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/dejavid-encoder-agnostic-learned-temporal","title":"DejaVid: Encoder-Agnostic Learned Temporal Matching for Video Classification","date":"2025-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tds-clip-temporal-difference-side-network-for","title":"TDS-CLIP: Temporal Difference Side Network for Image-to-Video Transfer Learning","date":"2024-08-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-correlation-structures-for-vision","title":"Learning Correlation Structures for Vision Transformers","date":"2024-04-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/cast-cross-attention-in-space-and-time-for-1","title":"CAST: Cross-Attention in Space and Time for Video Action Recognition","date":"2023-11-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":9,"samples_unverified":8,"pointer_only_for_licence":17,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/side4video-spatial-temporal-side-network-for","title":"Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning","date":"2023-11-27","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/asymmetric-masked-distillation-for-pre","title":"Asymmetric Masked Distillation for Pre-Training Small Foundation Models","date":"2023-11-06","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/zeroi2v-zero-cost-adaptation-of-pre-trained","title":"ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video","date":"2023-10-02","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/temporally-adaptive-models-for-efficient","title":"Temporally-Adaptive Models for Efficient Video Understanding","date":"2023-08-10","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/what-can-simple-arithmetic-operations-do-for","title":"What Can Simple Arithmetic Operations Do for Temporal Modeling?","date":"2023-07-18","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":3,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hiera-a-hierarchical-vision-transformer","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","date":"2023-06-01","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/prompt-learning-for-action-recognition","title":"SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognition","date":"2023-05-21","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/implicit-temporal-modeling-with-learnable","title":"Implicit Temporal Modeling with Learnable Alignment for Video Recognition","date":"2023-04-20","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/videomae-v2-scaling-video-masked-autoencoders","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","date":"2023-03-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":2,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/the-effectiveness-of-mae-pre-pretraining-for","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","date":"2023-03-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/visual-representation-learning-from-unlabeled","title":"ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders","date":"2023-03-21","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/maximizing-spatio-temporal-entropy-of-deep-3d","title":"Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition","date":"2023-03-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-scale-motion-aware-module-for-video","title":"Multi-scale Motion-Aware Module for Video Action Recognition","date":"2023-02-19","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/magvit-masked-generative-video-transformer","title":"MAGVIT: Masked Generative Video Transformer","date":"2022-12-10","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":1,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/masked-video-distillation-rethinking-masked","title":"Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning","date":"2022-12-08","rows_on_this_dataset":4,"code_links":4,"syntology":null},{"paper":"/paper/rethinking-video-vits-sparse-video-tubes-for","title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","date":"2022-12-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/internvideo-general-video-foundation-models","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","date":"2022-12-06","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/global-temporal-difference-network-for-action","title":"Global Temporal Difference Network for Action Recognition","date":"2022-11-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/adamae-adaptive-masking-for-efficient","title":"AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders","date":"2022-11-16","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":25,"samples_ran":9,"samples_unverified":16,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/uniformerv2-spatiotemporal-learning-by-arming","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","date":"2022-09-22","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/omnivl-one-foundation-model-for-image","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","date":"2022-09-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/spatial-temporal-pyramid-graph-reasoning-for","title":"Spatial-Temporal Pyramid Graph Reasoning for Action Recognition","date":"2022-08-09","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/spatiotemporal-self-attention-modeling-with","title":"Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition","date":"2022-07-27","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mar-masked-autoencoders-for-efficient-action","title":"MAR: Masked Autoencoders for Efficient Action Recognition","date":"2022-07-24","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/action-recognition-with-motion","title":"Action Recognition With Motion Diversification and Dynamic Selection","date":"2022-07-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/parameter-efficient-image-to-video-transfer","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","date":"2022-06-27","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":4,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/stand-alone-inter-frame-attention-in-video-1","title":"Stand-Alone Inter-Frame Attention in Video Models","date":"2022-06-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mlp-3d-a-mlp-like-3d-architecture-with-1","title":"MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing","date":"2022-06-13","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/videomae-masked-autoencoders-are-data-1","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","date":"2022-03-23","rows_on_this_dataset":3,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":9,"samples_unverified":4,"pointer_only_for_licence":12,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/direcformer-a-directed-attention-in","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","date":"2022-03-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":4,"samples_unverified":4,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/group-contextualization-for-video-recognition","title":"Group Contextualization for Video Recognition","date":"2022-03-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":5,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/slow-fast-visual-tempo-learning-for-video","title":"Motion-driven Visual Tempo Learning for Video-based Action Recognition","date":"2022-02-24","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/omnivore-a-single-model-for-many-visual","title":"Omnivore: A Single Model for Many Visual Modalities","date":"2022-01-20","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/action-keypoint-network-for-efficient-video","title":"Action Keypoint Network for Efficient Video Recognition","date":"2022-01-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multiview-transformers-for-video-recognition","title":"Multiview Transformers for Video Recognition","date":"2022-01-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/masked-feature-prediction-for-self-supervised","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","date":"2021-12-16","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/co-training-transformer-with-videos-and","title":"Co-training Transformer with Videos and Images Improves Action Recognition","date":"2021-12-14","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/approaches-toward-physical-and-general-video","title":"Approaches Toward Physical and General Video Anomaly Detection","date":"2021-12-14","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/self-supervised-video-transformer","title":"Self-supervised Video Transformer","date":"2021-12-02","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improved-multiscale-vision-transformers-for","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","date":"2021-12-02","rows_on_this_dataset":4,"code_links":9,"syntology":null},{"paper":"/paper/bevt-bert-pretraining-of-video-transformers","title":"BEVT: BERT Pretraining of Video Transformers","date":"2021-12-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/morphmlp-a-self-attention-free-mlp-like","title":"MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning","date":"2021-11-24","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/relational-self-attention-what-s-missing-in","title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","date":"2021-11-02","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/object-region-video-transformers-1","title":"Object-Region Video Transformers","date":"2021-10-13","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":1,"samples_unverified":6,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tada-temporally-adaptive-convolutions-for-1","title":"TAda! Temporally-Adaptive Convolutions for Video Understanding","date":"2021-10-12","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/uniformer-unified-transformer-for-efficient","title":"UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning","date":"2021-09-29","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/video-swin-transformer","title":"Video Swin Transformer","date":"2021-06-24","rows_on_this_dataset":1,"code_links":15,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":32,"samples_ran":7,"samples_unverified":25,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/vimpac-video-pre-training-via-masked-token","title":"VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning","date":"2021-06-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/space-time-mixing-attention-for-video","title":"Space-time Mixing Attention for Video Transformer","date":"2021-06-10","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/keeping-your-eye-on-the-ball-trajectory","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","date":"2021-06-09","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ct-net-channel-tensorization-network-for-1","title":"CT-Net: Channel Tensorization Network for Video Classification","date":"2021-06-03","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":10,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/vidtr-video-transformer-without-convolutions","title":"VidTr: Video Transformer Without Convolutions","date":"2021-04-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multiscale-vision-transformers","title":"Multiscale Vision Transformers","date":"2021-04-22","rows_on_this_dataset":3,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":26,"samples_ran":13,"samples_unverified":13,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/2103-15691","title":"ViViT: A Video Vision Transformer","date":"2021-03-29","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":21,"samples_ran":14,"samples_unverified":7,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/movinets-mobile-video-networks-for-efficient","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","date":"2021-03-21","rows_on_this_dataset":4,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":8,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-self-similarity-in-space-and-time-as-1","title":"Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition","date":"2021-02-14","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/is-space-time-attention-all-you-need-for","title":"Is Space-Time Attention All You Need for Video Understanding?","date":"2021-02-09","rows_on_this_dataset":3,"code_links":16,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":43,"samples_ran":35,"samples_unverified":8,"pointer_only_for_licence":14,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tdn-temporal-difference-networks-for","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","date":"2020-12-18","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mvfnet-multi-view-fusion-network-for","title":"MVFNet: Multi-View Fusion Network for Efficient Video Recognition","date":"2020-12-13","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/diverse-temporal-aggregation-and-depthwise","title":"Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification","date":"2020-12-01","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/mutual-modality-learning-for-video-action","title":"Mutual Modality Learning for Video Action Classification","date":"2020-11-04","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/pan-towards-fast-action-recognition-via","title":"PAN: Towards Fast Action Recognition via Learning Persistence of Appearance","date":"2020-08-08","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/motionsqueeze-neural-motion-feature-learning","title":"MotionSqueeze: Neural Motion Feature Learning for Video Understanding","date":"2020-07-20","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":3,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/temporal-pyramid-network-for-action","title":"Temporal Pyramid Network for Action Recognition","date":"2020-04-07","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/knowing-what-where-and-when-to-look-efficient","title":"Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention","date":"2020-04-02","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-memory-guided-normality-for-anomaly","title":"Learning Memory-guided Normality for Anomaly Detection","date":"2020-03-30","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/more-is-less-learning-efficient-video-1","title":"More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation","date":"2019-12-02","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-multigrid-method-for-efficiently-training","title":"A Multigrid Method for Efficiently Training Video Models","date":"2019-12-02","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":2,"samples_unverified":8,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/comparative-analysis-of-cnn-based","title":"Comparative Analysis of CNN-based Spatiotemporal Reasoning in Videos","date":"2019-09-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/temporal-reasoning-graph-for-activity","title":"Temporal Reasoning Graph for Activity Recognition","date":"2019-08-27","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/cooperative-cross-stream-network-for","title":"Cooperative Cross-Stream Network for Discriminative Action Representation","date":"2019-08-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/stm-spatiotemporal-and-motion-encoding-for","title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","date":"2019-08-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/few-shot-video-classification-via-temporal","title":"Few-Shot Video Classification via Temporal Alignment","date":"2019-06-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-video-representations-from","title":"Learning Video Representations from Correspondence Proposals","date":"2019-05-20","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/paying-more-attention-to-motion-attention","title":"Attention Distillation for Learning Video Representations","date":"2019-04-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/slowfast-networks-for-video-recognition","title":"SlowFast Networks for Video Recognition","date":"2018-12-10","rows_on_this_dataset":1,"code_links":15,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":0,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/temporal-shift-module-for-efficient-video","title":"TSM: Temporal Shift Module for Efficient Video Understanding","date":"2018-11-20","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":6,"samples_unverified":10,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/denseimage-network-video-spatial-temporal","title":"DenseImage Network: Video Spatial-Temporal Evolution Encoding and Understanding","date":"2018-05-19","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/temporal-relational-reasoning-in-videos","title":"Temporal Relational Reasoning in Videos","date":"2017-11-22","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/the-something-something-video-database-for","title":"The \"something something\" video database for learning and evaluating visual common sense","date":"2017-06-13","rows_on_this_dataset":1,"code_links":5,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":40,"samples_harvested":352,"samples_ran":170,"samples_unverified":182,"pointer_only_for_licence":87,"papers_with_no_sample_that_ran":6,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}