Memory-Augmented Video Understanding

Overview

Memory-augmented video understanding studies how models can retain useful evidence from long videos or live streams when their context and compute are limited. Approaches include bounded frame caches and semantic compression, hierarchical event- or entity-based memories, and retrieval systems that can revisit relevant clips; some methods also update recurrent states or model weights over time. These techniques support tasks such as streaming question answering, long-video and egocentric reasoning, and tracking objects or events across time, which are tested in both real-time and offline benchmarks. A central challenge is balancing compact, efficient memory with reliable retrieval of fine details, especially when later questions depend on evidence that seemed unimportant when first observed.

Latest papers

96 papers15 papers in the last four weeks, down 32% on the four weeks before. 0.1% of all new papers.

Mar 2, 2026

From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents

While multimodal large language models have demonstrated impressive short-term reasoning, they struggle with long-horizon video understanding due to limited context windows and static memory mechanisms that fail to mirror human cognitive efficiency. Existing paradigms typically fall into two extremes: vision-centric methods that incur high latency and redundancy through dense visual accumulation, or text-centric approaches that suffer from detail loss and hallucination via aggressive captioning. To bridge this gap, we propose MM-Mem, a pyramidal multimodal memory architecture grounded in Fuzzy-Trace Theory. MM-Mem structures memory hierarchically into a Sensory Buffer, Episodic Stream, and Symbolic Schema, enabling the progressive distillation of fine-grained perceptual traces (verbatim) into high-level semantic schemas (gist). Furthermore, to govern the dynamic construction of memory, we derive a Semantic Information Bottleneck objective and introduce SIB-GRPO to optimize the trade-off between memory compression and task-relevant information retention. In inference, we design an entropy-driven top-down memory retrieval strategy. Extensive experiments across 4 benchmarks confirm that MM-Mem achieves state-of-the-art performance on both offline and streaming tasks, demonstrating robust generalization and validating the effectiveness of cognition-inspired memory organization. Code and associated configurations are publicly available at https://github.com/EliSpectre/MM-Mem.
Feb 27, 2026

EgoGraph: Temporal Knowledge Graph for Egocentric Video Understanding

Ultra-long egocentric videos spanning multiple days present significant challenges for video understanding. Existing approaches still rely on fragmented local processing and limited temporal modeling, restricting their ability to reason over such extended sequences. To address these limitations, we introduce EgoGraph, a training-free and dynamic knowledge-graph construction framework that explicitly encodes long-term, cross-entity dependencies in egocentric video streams. EgoGraph employs a novel egocentric schema that unifies the extraction and abstraction of core entities, such as people, objects, locations, and events, and structurally reasons about their attributes and interactions, yielding a significantly richer and more coherent semantic representation than traditional clip-based video models. Crucially, we develop a temporal relational modeling strategy that captures temporal dependencies across entities and accumulates stable long-term memory over multiple days, enabling complex temporal reasoning. Extensive experiments on the EgoLifeQA and EgoR1-bench benchmarks demonstrate that EgoGraph achieves state-of-the-art performance on long-term video question answering, validating its effectiveness as a new paradigm for ultra-long egocentric video understanding.
Feb 25, 2026

WeaveTime: Stream from Earlier Frames into Emergent Memory in VideoLLMs

Recent advances in Multimodal Large Language Models have greatly improved visual understanding and reasoning, yet their quadratic attention and offline training protocols make them ill-suited for streaming settings where frames arrive sequentially and future observations are inaccessible. We diagnose a core limitation of current Video-LLMs, namely Time-Agnosticism, in which videos are treated as an unordered bag of evidence rather than a causally ordered sequence, yielding two failures in streams: temporal order ambiguity, in which the model cannot follow or reason over the correct chronological order, and past-current focus blindness where it fails to distinguish present observations from accumulated history. We present WeaveTime, a simple, efficient, and model agnostic framework that first teaches order and then uses order. We introduce a lightweight Temporal Reconstruction objective-our Streaming Order Perception enhancement-that instills order aware representations with minimal finetuning and no specialized streaming data. At inference, a Past-Current Dynamic Focus Cache performs uncertainty triggered, coarse-to-fine retrieval, expanding history only when needed. Plugged into exsiting Video-LLM without architectural changes, WeaveTime delivers consistent gains on representative streaming benchmarks, improving accuracy while reducing latency. These results establish WeaveTime as a practical path toward time aware stream Video-LLMs under strict online, time causal constraints. Code and weights will be made publicly available. Project Page: https://zhangyl4.github.io/publications/weavetime/
Feb 2, 2026

FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding

Transitioning Multimodal Large Language Models (MLLMs) from offline to online streaming video understanding is essential for continuous perception. However, existing methods lack flexible adaptivity, leading to irreversible detail loss and context fragmentation. To resolve this, we propose FreshMem, a Frequency-Space Hybrid Memory network inspired by the brain's logarithmic perception and memory consolidation. FreshMem reconciles short-term fidelity with long-term coherence through two synergistic modules: Multi-scale Frequency Memory (MFM), which projects overflowing frames into representative frequency coefficients, complemented by residual details to reconstruct a global historical "gist"; and Space Thumbnail Memory (STM), which discretizes the continuous stream into episodic clusters by employing an adaptive compression strategy to distill them into high-density space thumbnails. Extensive experiments show that FreshMem significantly boosts the Qwen2-VL baseline, yielding gains of 5.20%, 4.52%, and 2.34% on StreamingBench, OV-Bench, and OVO-Bench, respectively. As a training-free solution, FreshMem outperforms several fully fine-tuned methods, offering a highly efficient paradigm for long-horizon streaming video understanding.
Jan 21, 2026

SpatialMem: Metric-Aligned Long-Horizon Video Memory for Language Grounding and QA

SpatialMem is a memory-based system which integrates 3D geometry, semantics, and language with one another in one combined, queryable representation. Starting with casually recorded egocentric RGB video, SpatialMem recreates metrically scaled interior scenes, recognizes structural 3D anchors (walls, doors, windows) as the first-layer scaffold, and associates open-vocabulary object nodes with evidence patches, visual embeddings, and two-layer descriptions to 3D coordinates, enabling spatial-relation reasoning, language-directed retrieval, and QA without special sensors. We test at scale on public benchmarks. On VSI-Bench (288288 videos, 5,1305{,}130 questions) SpatialMem scores 37.537.5 overall with RGB alone, and its margin is precisely where a metric memory should earn it (room size 41.441.4 vs.\ 24.424.4 with a same-size frame model). On the episodic-memory task of OpenEQA (953953 questions) the memory serialised to text is lower than the blind control, but as evidence-frame retrieval it recovers frame-level accuracy, matching uniform sampling at an equal eight-frame budget and pulling ahead as the budget tightens, with every answer grounded in linked 3D evidence. On 1212 ScanNet scenes evaluated using instance-level official annotations, the anchor-first hierarchy assigns the retrieved object to the proper structural parent where open-vocabulary 3D scene graphs essentially cannot (0.240.24 compared to 0.010.01 with matched input), a capability difference instead of an overall win. The queryable index has a cost of 1414,KB per scene without the linked evidence frames, and we make available the suites, memories and code.
Oct 12, 2025

Action-Dynamics Modeling and Cross-Temporal Interaction for Online Action Understanding

Online action understanding, encompassing action detection and anticipation, is central to numerous practical applications. However, untrimmed videos contain substantial redundant and noisy historical information, and the complementary interactions among historical, current, and future-oriented representations remain underexplored. To address these challenges, we propose the State-Specific Model (SSM), a unified framework for online action detection and anticipation. Its Representative State-Based Memory Compression module selects representative anchor frames from the observed memory and aggregates anchor-conditioned context into a compact set of representative memory states, thereby reducing memory redundancy. The subsequent Action Pattern Learning module learns multi-dimensional relations among these states and performs graph reasoning over the resulting directed representative-state graph to model action dynamics and derive a future-oriented cue. The Cross-Temporal Interaction module then enables this cue to interact with historical and current cues, refining the representations used for simultaneous online action detection and anticipation. Extensive experiments on EPIC-Kitchens-100, THUMOS'14, TVSeries, and the introduced Parkinson's Disease Mouse Behaviour dataset demonstrate competitive performance and generalizability across diverse online action understanding settings. These results underscore the value of graph-based action-dynamics modelling and cross-temporal interaction for online action understanding.