About this paper
MemInStream is a benchmark that evaluates memory capabilities in streaming video understanding using evidence-controlled validation to separate memory limitations from visual understanding failures.
Streaming video understanding aims to continuously process incoming visual observations, making the retention and retrieval of relevant information increasingly important as the video history grows. Although existing benchmarks include memory-related questions, question-answering accuracy alone does not reliably measure memory capabilities. Incorrect predictions may arise from failures in visual understanding rather than forgetting, whereas correct predictions may rely on linguistic priors or recent observations without requiring historical memory. To address these ambiguities, we introduce MemInStream, a benchmark dedicated to evaluating memory capabilities in streaming video…
streaming video understandingmemory capabilitiesevidence-controlled validation protocoltemporally localized evidence intervalsevidence solvabilitymemory necessitymemory-independent shortcutsEpisodic RetrievalState Tracking and UpdatingMulti-Evidence Integration
- Upvotes
- 6
- Authors
- 13
- Published
- Nov 11, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
MemInStream: Memorizing or Merely Recognizing? Rethinking Streaming Video Memory Evaluation was first seen on Hugging Face · Daily papers on Nov 17, 2026. Since then it has appeared in 7 checks on 1 different day. Its best position was #16 of 30, reached on Nov 17, 23:28 UTC. It dropped off the list after Nov 17, 23:28 UTC.