mlsanityData to 14 Oct 2026

What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations

arXiv 2306.08713 ↗First posted 14 Jun 2023cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

We propose and address a new generalisation problem: can a model trained for action recognition successfully classify actions when they are performed within a previously unseen scenario and in a previously unseen location? To answer this question, we introduce the Action Recognition Generalisation Over scenarios and locations dataset (ARGO1M), which contains 1.1M video clips from the large-scale Ego4D dataset, across 10 scenarios and 13 locations. We demonstrate recognition models struggle to generalise over 10 proposed test splits, each of an unseen scenario in an unseen location. We thus propose CIR, a method to represent each video as a Cross-Instance Reconstruction of videos from other domains. Reconstructions are paired with text narrations to guide the learning of a domain generalisable representation. We provide extensive analysis and ablations on ARGO1M that show CIR outperforms prior domain generalisation works on all test splits. Code and data: https://chiaraplizz.github.io/what-can-a-cook/.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 50 of its 67 references that are in the map. First posted on arXiv 14 Jun 2023.

Builds on

50 of 67 references.

References · 50

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  8. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  9. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  10. 2018SlowFast Networks for Video Recognitioncited by 1,867
  11. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  12. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
38 more
  1. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  2. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  3. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  4. 2020In Search of Lost Domain Generalizationcited by 1,054
  5. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  6. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 981
  7. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 795
  8. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  9. 2018Recognition in Terra Incognitacited by 658
  10. 2020Rescaling Egocentric Visioncited by 540
  11. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  12. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 450
  13. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 429
  14. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 407
  15. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 382
  16. 2017Temporal Relational Reasoning in Videoscited by 324
  17. 2019Adversarial Domain Adaptation with Domain Mixupcited by 250
  18. 2019Episodic Training for Domain Generalizationcited by 245
  19. 2022Egocentric Video-Language Pretrainingcited by 232
  20. 2018Moments in Time Dataset: one million videos for event understandingcited by 215
  21. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  22. 2020Support-set bottlenecks for video-text representation learningcited by 170
  23. 2019Feature-Critic Networks for Heterogeneous Domain Generalizationcited by 130
  24. 2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
  25. 2020Multi-Modal Domain Adaptation for Fine-Grained Action Recognitioncited by 115
  26. 2020Heterogeneous Domain Generalization via Domain Mixupcited by 103
  27. 2021Temporal-Relational CrossTransformers for Few-Shot Action Recognitioncited by 84
  28. 2022Prompt Vision Transformer for Domain Generalizationcited by 52
  29. 2021Learning Cross-modal Contrastive Features for Video Domain Adaptationcited by 47
  30. 2020Self-Supervised Learning Across Domainscited by 44
  31. 2022Compound Domain Generalization via Meta-Knowledge Encodingcited by 40
  32. 2021Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognitioncited by 35
  33. 2022Grounding Visual Representations with Texts for Domain Generalizationcited by 30
  34. 2023Use Your Head: Improving Long-Tail Video Recognitioncited by 22
  35. 2022Domain-Unified Prompt Representations for Source-Free Domain Generalizationcited by 21
  36. 2022Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalizationcited by 20
  37. 2019VideoDG: Generalizing Temporal Relations in Videos to Novel Domainscited by 14
  38. 2019Temporal Attentive Alignment for Video Domain Adaptationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 11; 2025: 7; 2026: 4.

25 papers.

Sort:

By area:

  1. 2023An Outlook into the Future of Egocentric Visioncited by 84
  2. 2024EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generationcited by 41
  3. 2025Challenges and Trends in Egocentric Vision: A Surveycited by 20
  4. 2025The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimationcited by 16
  5. 2024XOV-Action: Towards Generalizable Open-Vocabulary Action Recognitioncited by 15
  6. 2024Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognitioncited by 14
  7. 2024AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipationcited by 14
  8. 2023A Survey on Deep Learning Techniques for Action Anticipationcited by 11
  9. 2024Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?cited by 11
  10. 2023Are Synthetic Data Useful for Egocentric Hand-Object Interaction Detection?cited by 10
  11. 2024A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectivescited by 9
  12. 2024What does CLIP know about peeling a banana?cited by 9
13 more
  1. 2024Human-Centric Transformer for Domain Adaptive Action Recognitioncited by 8
  2. 2024Egocentric zone-aware action recognition across environmentscited by 6
  3. 2025Hier-EgoPack: Hierarchical Egocentric Video Understanding with Diverse Task Perspectivescited by 5
  4. 2025EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretrainingcited by 5
  5. 2024Tell, Don't Show!: Language Guidance Eases Transfer Across Domains in Images and Videoscited by 4
  6. 2024Integrating Audio Narrations to Strengthen Domain Generalization in Multimodal First-Person Action Recognitioncited by 2
  7. 2025Domain Generalization using Action Sequences for Egocentric Action Recognitioncited by 1
  8. 2026Integrating Affordances and Attention models for Short-Term Object Interaction Anticipationcited by 1
  9. 2025VUDG: A Dataset for Video Understanding Domain Generalizationcited by 0
  10. 2025EgoEMS: A High-Fidelity Multimodal Egocentric Dataset for Cognitive Assistance in Emergency Medical Servicescited by 0
  11. 2026Ego4OOD: Rethinking Egocentric Video Domain Generalization via Covariate Shift Scoringcited by 0
  12. 2026SAVA-X: Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and Bidirectional Cross View Fusioncited by 0
  13. 2026Leveraging Synthetic Data for Enhancing Egocentric Hand-Object Interaction Detectioncited by 0