mlsanityData to 7 Oct 2026

LSTA: Long Short-Term Attention for Egocentric Action Recognition

arXiv 1811.10698 ↗First posted 26 Nov 2018cs.CVcited by 57

Not on the map. Why?

Abstract (arXiv)

Egocentric activity recognition is one of the most challenging tasks in video analysis. It requires a fine-grained discrimination of small objects and their manipulation. While some methods base on strong supervision and attention mechanisms, they are either annotation consuming or do not take spatio-temporal patterns into account. In this paper we propose LSTA as a mechanism to focus on features from spatial relevant parts while attention is being tracked smoothly across the video sequence. We demonstrate the effectiveness of LSTA on egocentric activity recognition with an end-to-end trainable two-stream architecture, achieving state of the art performance on four standard benchmarks.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 12; 2023: 6; 2024: 10; 2025: 6; 2026: 6.

57 papers.

Sort:

By area:

  1. 2022Learning Video Representations from Large Language Modelscited by 204
  2. 2021Ego-Exo: Transferring Visual Representations from Third-person to First-person Videoscited by 98
  3. 2024EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real Worldcited by 93
  4. 2023An Outlook into the Future of Egocentric Visioncited by 84
  5. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
  6. 2021E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognitioncited by 50
  7. 2024Retrieval-Augmented Egocentric Video Captioningcited by 42
  8. 2021With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognitioncited by 41
  9. 2021Learning to Anticipate Egocentric Actions by Imaginationcited by 40
  10. 2021Trear: Transformer-based RGB-D Egocentric Action Recognitioncited by 39
  11. 2021Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognitioncited by 35
  12. 2021Self-Regulated Learning for Egocentric Video Activity Anticipationcited by 32
38 more
  1. 2022Egocentric Prediction of Action Target in 3Dcited by 31
  2. 2023LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuningcited by 28
  3. 2024EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Viewscited by 26
  4. 2021Revisiting 3D Object Detection From an Egocentric Perspectivecited by 18
  5. 2024Masked Video and Body-worn IMU Autoencoder for Egocentric Action Recognitioncited by 18
  6. 2025Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Inputcited by 17
  7. 2025EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmarkcited by 16
  8. 2021Relevance Detection in Cataract Surgery Videos by Spatio-Temporal Action Localizationcited by 15
  9. 2022Gate-Shift-Fuse for Video Action Recognitioncited by 15
  10. 2022A Survey of Video-based Action Quality Assessmentcited by 14
  11. 2023Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspectivecited by 14
  12. 2021Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Taskscited by 13
  13. 2024Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?cited by 11
  14. 2024POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-View Worldcited by 10
  15. 2021Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignmentcited by 9
  16. 2022SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognitioncited by 8
  17. 2024GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognitioncited by 8
  18. 2021Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionariescited by 6
  19. 2021Higher Order Recurrent Space-Time Transformer for Video Action Predictioncited by 6
  20. 2023Discovering Novel Actions from Open World Egocentric Videos with Object-Grounded Visual Commonsense Reasoningcited by 6
  21. 2024Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentationcited by 6
  22. 2021Spatiotemporal Deformable Scene Graphs for Complex Activity Detectioncited by 5
  23. 2025ANNEXE: Unified Analyzing, Answering, and Pixel Grounding for Egocentric Interactioncited by 5
  24. 2021Indoor Future Person Localization from an Egocentric Wearable Cameracited by 4
  25. 2021Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clipscited by 4
  26. 2025Ego-centric Predictive Model Conditioned on Hand Trajectoriescited by 4
  27. 2025ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognitioncited by 3
  28. 2022THORN: Temporal Human-Object Relation Network for Action Recognitioncited by 2
  29. 2023EgoViT: Pyramid Video Transformer for Egocentric Action Recognitioncited by 2
  30. 2023Free-Form Composition Networks for Egocentric Action Recognitioncited by 2
  31. 2022Human Gaze Guided Attention for Surgical Activity Recognitioncited by 1
  32. 2022Efficient Human Vision Inspired Action Recognition using Adaptive Spatiotemporal Samplingcited by 1
  33. 2022Bringing Online Egocentric Action Recognition into the wildcited by 1
  34. 2022ReLER@ZJU Submission to the Ego4D Moment Queries Challenge 2022cited by 1
  35. 2022Inductive Attention for Video Action Anticipationcited by 1
  36. 2024FILS: Self-Supervised Video Feature Prediction In Semantic Language Spacecited by 1
  37. 2026TRec: Learning Hand-Object Interactions through 2D Point Track Motioncited by 1
  38. 2026EgoReasoner: Learning Egocentric 4D Reasoning via Task-Adaptive Structured Thinkingcited by 1

50 most cited of 57 All 57 (JSON)