mlsanityData to 7 Oct 2026

Domain Adaptation in Multi-View Embedding for Cross-Modal Video Retrieval

arXiv 2110.12812 ↗First posted 25 Oct 2021cs.CV cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Given a gallery of uncaptioned video sequences, this paper considers the task of retrieving videos based on their relevance to an unseen text query. To compensate for the lack of annotations, we rely instead on a related video gallery composed of video-caption pairs, termed the source gallery, albeit with a domain gap between its videos and those in the target gallery. We thus introduce the problem of Unsupervised Domain Adaptation for Cross-modal Video Retrieval, along with a new benchmark on fine-grained actions. We propose a novel iterative domain alignment method by means of pseudo-labelling target videos and cross-domain (i.e. source-target) ranking. Our approach adapts the embedding space to the target gallery, consistently outperforming source-only as well as marginal and conditional alignment methods.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 42 of its 63 references that are in the map. First posted on arXiv 25 Oct 2021.

Builds on

42 of 63 references.

References · 42

  1. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  3. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  4. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  5. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  6. 2019HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clipscited by 946
  7. 2019End-to-End Learning of Visual Representations from Uncurated Instructional Videoscited by 506
  8. 2021Less is More: ClipBERT for Video-and-Language Learning via Sparse Samplingcited by 484
  9. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  10. 2020Multi-modal Transformer for Video Retrievalcited by 395
  11. 2015Return of Frustratingly Easy Domain Adaptationcited by 389
  12. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
30 more
  1. 2019Label Propagation for Deep Semi-supervised Learningcited by 287
  2. 2019EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognitioncited by 226
  3. 2019Use What You Have: Video Retrieval Using Representations From Collaborative Expertscited by 214
  4. 2020Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identificationcited by 214
  5. 2018DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptationcited by 212
  6. 2018Progressive Feature Alignment for Unsupervised Domain Adaptationcited by 183
  7. 2020Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoningcited by 180
  8. 2017Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identificationcited by 168
  9. 2017Asymmetric Tri-training for Unsupervised Domain Adaptationcited by 152
  10. 2019Transferrable Prototypical Networks for Unsupervised Domain Adaptationcited by 141
  11. 2015Learning Deep Structure-Preserving Image-Text Embeddingscited by 139
  12. 2020Multi-Modal Domain Adaptation for Fine-Grained Action Recognitioncited by 115
  13. 2018Learning a Text-Video Embedding from Incomplete and Heterogeneous Datacited by 103
  14. 2021T2VLAD: Global-Local Sequence Alignment for Text-Video Retrievalcited by 103
  15. 2019Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddingscited by 101
  16. 2019Temporal Attentive Alignment for Large-Scale Video Domain Adaptationcited by 100
  17. 2021Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformerscited by 93
  18. 2019Cluster Alignment with a Teacher for Unsupervised Domain Adaptationcited by 88
  19. 2015Zero-Shot Learning via Semantic Similarity Embeddingcited by 74
  20. 2020Action Segmentation with Joint Self-Supervised Temporal Domain Adaptationcited by 74
  21. 2017Unsupervised Person Re-identification: Clustering and Fine-tuningcited by 73
  22. 2019Unsupervised Domain Adaptation using Feature-Whitening and Consensus Losscited by 67
  23. 2019Self-training with progressive augmentation for unsupervised cross-domain person re-identificationcited by 54
  24. 2021On Semantic Similarity in Video Retrievalcited by 45
  25. 2018Domain Adaptation through Synthesis for Unsupervised Person Re-identificationcited by 44
  26. 2021Action Segmentation with Mixed Temporal Domain Adaptationcited by 21
  27. 2019Action2Vec: A Crossmodal Embedding Approach to Action Learningcited by 19
  28. 2019Ladder Loss for Coherent Visual-Semantic Embeddingcited by 15
  29. 2021Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignmentcited by 9
  30. 2020Unsupervised Domain Adaptation for Spatio-Temporal Action Localizationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 0; 2023: 2; 2024: 2; 2025: 0; 2026: 1.

6 papers.

  1. 2021Cross Modal Retrieval with Querybank Normalisationcited by 71
  2. 2023Are Synthetic Data Useful for Egocentric Hand-Object Interaction Detection?cited by 10
  3. 2024Test-time Adaptation for Cross-modal Retrieval with Query Shiftcited by 10
  4. 2024PAC-Bayesian Domain Adaptation Bounds for Multi-view learningcited by 1
  5. 2023Multi-Modal Domain Adaptation Across Video Scenes for Temporal Video Groundingcited by 0
  6. 2026Leveraging Synthetic Data for Enhancing Egocentric Hand-Object Interaction Detectioncited by 0