mlsanityData to 14 Oct 2026

USV: Towards Understanding the User-generated Short-form Videos

arXiv 2605.20838 ↗First posted 20 May 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Several large-scale video datasets have been published these years and have advanced the area of video understanding. However, the newly emerged user-generated short-form videos have rarely been studied. This paper presents USV, the User-generated Short-form Video dataset for high-level semantic video understanding. The dataset contains around 224K videos collected from UGC platforms by label queries without extra manual verification and trimming. Although video understanding has achieved plausible improvement these years, most works focus on instance-level recognition, which is not sufficient for learning the representation of the high-level semantic information of videos. Therefore, we further establish two tasks: topic recognition and video-text retrieval on USV. We propose two unified and effective baseline methods Multi-Modality Fusion Network (MMF-Net) and Video-Text Contrastive Learning (VTCL), to tackle the topic recognition task and video-text retrieval respectively, and carry out comprehensive benchmarks to facilitate future research. Our project page is https://usvdataset.github.io.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 46 of its 74 references that are in the map. First posted on arXiv 20 May 2026.

Builds on

46 of 74 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  5. 2017The Kinetics Human Action Video Datasetcited by 1,909
  6. 2018SlowFast Networks for Video Recognitioncited by 1,867
  7. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,143
  8. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,103
  9. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,068
  10. 2019HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clipscited by 950
  11. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 902
  12. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 856
34 more
  1. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 795
  2. 2017Dense-Captioning Events in Videoscited by 793
  3. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 686
  4. 2017Localizing Moments in Video with Natural Languagecited by 663
  5. 2017Towards Automatic Learning of Procedures from Web Instructional Videoscited by 619
  6. 2019End-to-End Learning of Visual Representations from Uncurated Instructional Videoscited by 507
  7. 2021Less is More: ClipBERT for Video-and-Language Learning via Sparse Samplingcited by 484
  8. 2017Look, Listen and Learncited by 458
  9. 2017AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actionscited by 449
  10. 2018A Short Note about Kinetics-600cited by 333
  11. 2016YouTube-8M: A Large-Scale Video Classification Benchmarkcited by 324
  12. 2018Cooperative Learning of Audio and Video Models from Self-Supervised Synchronizationcited by 249
  13. 2020FineGym: A Hierarchical Video Dataset for Fine-grained Action Understandingcited by 234
  14. 2020The EPIC-KITCHENS Dataset: Collection, Challenges and Baselinescited by 225
  15. 2017Unsupervised Representation Learning by Sorting Sequencescited by 221
  16. 2018Moments in Time Dataset: one million videos for event understandingcited by 215
  17. 2018A Joint Sequence Fusion Model for Video Question Answering and Retrievalcited by 208
  18. 2014Unifying Visual-Semantic Embeddings with Multimodal Neural Language Modelscited by 198
  19. 2015A Dataset for Movie Descriptioncited by 195
  20. 2016Movie Descriptioncited by 181
  21. 2019Video Representation Learning by Dense Predictive Codingcited by 175
  22. 2020Audiovisual SlowFast Networks for Video Recognitioncited by 146
  23. 2018Learning a Text-Video Embedding from Incomplete and Heterogeneous Datacited by 103
  24. 2017PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understandingcited by 101
  25. 2019Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statisticscited by 92
  26. 2016Hierarchical Deep Temporal Models for Group Activity Recognitioncited by 89
  27. 2016End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answeringcited by 60
  28. 2016Learning Language-Visual Embedding for Movie Understanding with Natural-Languagecited by 41
  29. 2020Learning Spatiotemporal Features via Video and Text Pair Discriminationcited by 38
  30. 2019Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understandingcited by 37
  31. 2016Learning Joint Representations of Videos and Sentences with Web Image Searchcited by 17
  32. 2017Large-scale weakly supervised audio classification using gated convolutional neural networkcited by 17
  33. 2019Large Scale Holistic Video Understandingcited by 12
  34. 2020Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervisioncited by 9

Built on by

Not cited yet.