mlsanityData to 7 Oct 2026

3MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social Media Short Videos

arXiv 2203.14456 ↗First posted 28 Mar 2022cs.CV cs.AI cs.MMcited by 8

Not on the map. Why?

Abstract (arXiv)

We present 3MASSIV, a multilingual, multimodal and multi-aspect, expertly-annotated dataset of diverse short videos extracted from short-video social media platform - Moj. 3MASSIV comprises of 50k short videos (20 seconds average duration) and 100K unlabeled videos in 11 different languages and captures popular short video trends like pranks, fails, romance, comedy expressed via unique audio-visual formats like self-shot videos, reaction videos, lip-synching, self-sung songs, etc. 3MASSIV presents an opportunity for multimodal and multilingual semantic understanding on these unique videos by annotating them for concepts, affective states, media types, and audio language. We present a thorough analysis of 3MASSIV and highlight the variety and unique aspects of our dataset compared to other contemporary popular datasets with strong baselines. We also show how the social media content in 3MASSIV is dynamic and temporal in nature, which can be used for semantic understanding tasks and cross-lingual analysis.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 42 of its 83 references that are in the map. First posted on arXiv 28 Mar 2022.

Builds on

42 of 83 references.

References · 42

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  3. 2017The Kinetics Human Action Video Datasetcited by 1,894
  4. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  5. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,092
  6. 2016CNN Architectures for Large-Scale Audio Classificationcited by 701
  7. 2017Localizing Moments in Video with Natural Languagecited by 660
  8. 2019Multimodal Transformer for Unaligned Multimodal Language Sequencescited by 637
  9. 2019ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answeringcited by 559
  10. 2017Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?cited by 551
  11. 2016Hollywood in Homes: Crowdsourcing Data Collection for Activity Understandingcited by 535
  12. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
30 more
  1. 2020GoEmotions: A Dataset of Fine-Grained Emotionscited by 479
  2. 2018TVQA: Localized, Compositional Video Question Answeringcited by 463
  3. 2019VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Researchcited by 412
  4. 2016YouTube-8M: A Large-Scale Video Classification Benchmarkcited by 324
  5. 2019A Short Note on the Kinetics-700 Human Action Datasetcited by 308
  6. 2015MovieQA: Understanding Stories in Movies through Question-Answeringcited by 304
  7. 2020The EPIC-KITCHENS Dataset: Collection, Challenges and Baselinescited by 221
  8. 2018Moments in Time Dataset: one million videos for event understandingcited by 215
  9. 2020TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrievalcited by 215
  10. 2019Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Goodcited by 207
  11. 2020TAO: A Large-Scale Benchmark for Tracking Any Objectcited by 146
  12. 2018How2: A Large-scale Dataset for Multimodal Language Understandingcited by 137
  13. 2020Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentencescited by 116
  14. 2017YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Videocited by 109
  15. 2020The AVA-Kinetics Localized Human Actions Video Datasetcited by 82
  16. 2019Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Videocited by 60
  17. 2016Leveraging Video Descriptions to Learn Video Question Answeringcited by 55
  18. 2020DiffNet++: A Neural Influence and Interest Diffusion Network for Social Recommendationcited by 46
  19. 2019Integrating Text and Image: Determining Multimodal Document Intent in Instagram Postscited by 37
  20. 2019STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaitscited by 36
  21. 2018Vision as an Interlingua: Learning Multilingual Semantic Embeddings of Untranscribed Speechcited by 26
  22. 2020Intentonomy: a Dataset and Study towards Human Intent Understandingcited by 22
  23. 2021CLSRIL-23: Cross Lingual Speech Representations for Indic Languagescited by 22
  24. 2018Visually grounded cross-lingual keyword spotting in speechcited by 19
  25. 2018Equal But Not The Same: Understanding the Implicit Relationship Between Persuasive Images and Textcited by 15
  26. 2019Large Scale Holistic Video Understandingcited by 12
  27. 2021Cascaded Multilingual Audio-Visual Learning from Videoscited by 8
  28. 2014Lifespan and propagation of information in On-line Social Networks a Case Studycited by 4
  29. 2020EEV: A Large-Scale Dataset for Studying Evoked Expressions from Videocited by 4
  30. 2016The Open World of Micro-Videoscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 1; 2025: 3.

8 papers.

  1. 2023Joyful: Joint Modality Fusion and Graph Contrastive Learning for Multimodal Emotion Recognitioncited by 14
  2. 2023MM-AU:Towards Multimodal Understanding of Advertisement Videoscited by 7
  3. 2023Video Recognition in Portrait Modecited by 6
  4. 2024Delving Deep into Engagement Prediction of Short Videoscited by 4
  5. 2022C2KD: Cross-Lingual Cross-Modal Knowledge Distillation for Multilingual Text-Video Retrievalcited by 3
  6. 2025Audio-visual Event Localization on Portrait Mode Short Videoscited by 3
  7. 2025Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understandingcited by 3
  8. 2025FinCap: Topic-Aligned Captions for Short-Form Financial YouTube Videoscited by 2