mlsanityData to 7 Oct 2026

EgoSelf: From Memory to Personalized Egocentric Assistant

arXiv 2604.19564 ↗First posted 21 Apr 2026cs.CV cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Egocentric assistants often rely on first-person view data to capture user behavior and context for personalized services. Since different users exhibit distinct habits, preferences, and routines, such personalization is essential for truly effective assistance. However, effectively integrating long-term user data for personalization remains a key challenge. To address this, we introduce EgoSelf, a system that includes a graph-based interaction memory constructed from past observations and a dedicated learning task for personalization. The memory captures temporal and semantic relationships among interaction events and entities, from which user-specific profiles are derived. The personalized learning task is formulated as a prediction problem where the model predicts possible future interactions from individual user's historical behavior recorded in the graph. Extensive experiments demonstrate the effectiveness of EgoSelf as a personalized egocentric assistant. Code is available at https://abie-e.github.io/EgoSelf/.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 50 of its 63 references that are in the map. First posted on arXiv 21 Apr 2026.

Builds on

50 of 63 references.

References · 50

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  4. 2024GPT-4o System Cardcited by 4,467
  5. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  6. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  7. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  8. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  9. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  10. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  11. 2024Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysiscited by 1,375
  12. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
38 more
  1. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 800
  2. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 789
  3. 2019VideoBERT: A Joint Model for Video and Language Representation Learningcited by 702
  4. 2023VILA: On Pre-training for Visual Language Modelscited by 686
  5. 2023EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understandingcited by 666
  6. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
  7. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  8. 2023LLaMA-VID: An Image is Worth 2 Tokens in Large Language Modelscited by 539
  9. 2023MovieChat: From Dense Token to Sparse Memory for Long Video Understandingcited by 536
  10. 2020Rescaling Egocentric Visioncited by 529
  11. 2024Long Context Transfer from Language to Visioncited by 502
  12. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
  13. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memorycited by 372
  14. 2024LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understandingcited by 341
  15. 2024LongVILA: Scaling Long-Context Visual Language Models for Long Videoscited by 303
  16. 2022Egocentric Video-Language Pretrainingcited by 231
  17. 2024MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understandingcited by 223
  18. 2022Learning Video Representations from Large Language Modelscited by 204
  19. 2021Anticipative Video Transformercited by 197
  20. 2024Streaming Long Video Understanding with Large Language Modelscited by 164
  21. 2024LongVLM: Efficient Long Video Understanding via Large Language Modelscited by 146
  22. 2023EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbonecited by 130
  23. 2024SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Modelscited by 123
  24. 2025HD-EPIC: A Highly-Detailed Egocentric Video Datasetcited by 101
  25. 2021Ego-Exo: Transferring Visual Representations from Third-person to First-person Videoscited by 98
  26. 2025Gemini Embedding: Generalizable Embeddings from Geminicited by 93
  27. 2025EgoLife: Towards Egocentric Life Assistantcited by 86
  28. 2023EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Modelscited by 59
  29. 2023Action Scene Graphs for Long-Form Understanding of Egocentric Videoscited by 51
  30. 2023Memory-and-Anticipation Transformer for Online Action Understandingcited by 39
  31. 2022IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Textcited by 36
  32. 2022Interaction Region Visual Transformer for Egocentric Action Anticipationcited by 36
  33. 2024AMEGO: Active Memory from long EGOcentric videoscited by 35
  34. 2023Ego-Only: Egocentric Action Detection without Exocentric Transferringcited by 30
  35. 2023Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognitioncited by 20
  36. 2025Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?cited by 19
  37. 2025Fostering Video Reasoning via Next-Event Predictioncited by 15
  38. 2024A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectivescited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026EgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memorycited by 0
  2. 2026AI Smart Glasses for Wearable Intelligence: From Egocentric Sensing to Agentic Personalizationcited by 0