Long-horizon egocentric video is a rich substrate for wearable AI assistants, but object-centric questions such as where an item was moved, when it last changed state, or why it was relocated remain difficult because caption- and transcript-based memories rarely preserve persistent object identity or structured spatial change. Existing long-video QA methods mainly emphasize temporal grounding and clip retrieval, while prior 3D scene-graph methods typically assume stronger geometry than free-motion wearable RGB video provides, including point clouds, RGB-D input, posed views, sparse reconstruction, or reconstructed scenes.
arXiv:2608. 11017v1 Announce Type: cross Abstract: Long-horizon egocentric video is a rich substrate for wearable AI assistants, but object-centric questions such as where an item was moved, when it last changed state, or why it was relocated remain difficult because caption- and transcript-based memories rarely preserve persistent object identity or structured spatial change.
arXiv:2510. 01483v3 Announce Type: replace-cross Abstract: Vision-language models (VLMs) demonstrate strong image-level scene understanding, but reasoning over long egocentric video remains costly: because VLMs maintain no persistent memory or explicit spatial representation, all sampled frames must be re-processed for every new query.
EgoMemReason is a new benchmark for week‑long egocentric video understanding that focuses on memory‑driven reasoning rather than simple perception tasks. It tests three memory types—entity, event, and behavior—across 500 questions, each requiring evidence from an average of 5.1 video segments and 25.9 hours of backtracking. Evaluation of 17 models shows that even the best achieves only 39.6% accuracy, highlighting the difficulty of long‑horizon memory in multimodal systems.
Real-world spatial intelligence requires agents to understand scenes from continuous video streams, where objects move, persist, disappear, and reappear over time. While recent spatial foundation models have enabled generalizable feed-forward 3D reconstruction, most streaming methods remain geometry-centric and lack temporally consistent object-level understanding.
Event-Causal RAG (EC‑RAG) is a lightweight retrieval‑augmented framework designed for reasoning over ultra‑long and streaming videos. It segments video streams into semantically complete events using a dual visual‑audio sentinel mechanism, representing each event as a State‑Event‑State (SES) structure that captures pre‑event, event, and post‑event states. During question answering, bidirectional graph retrieval accesses relevant predecessor and successor events from a dual vector‑graph memory, and answers are generated using both this structured memory and the corresponding video evidence. The authors also introduce ECV‑1H, an hour‑scale long‑video QA benchmark with over 150 hours of untrimmed video and 1,251 human‑annotated QA pairs, where EC‑RAG achieves significant accuracy gains across multiple video foundation models while maintaining efficient streaming memory usage on a single RTX 5090 GPU.
BuddyVQA is a new benchmark for companion‑style question answering on egocentric streaming video, comprising 21.6K questions tied to 6K highlight moments across 1,012 long first‑person videos. It emphasizes two often overlooked aspects of daily first‑person QA: ego‑deictic expressions and interactively chained questions, requiring models to resolve visual pronouns and infer user intent within a long‑form streaming context. The authors propose MyBuddy, a multimodal chain‑of‑thought QA assistant that uses a question filter and multi‑level memory to efficiently retrieve visual and QA information, achieving significant performance gains on BuddyVQA and generalizing to other streaming and common video QA benchmarks.
The paper "Can 4D Foundation Models Remember?" introduces PersistBench, a dataset and metric suite that uses 360° videos to evaluate visual memory in 4D foundation models. It focuses on three aspects—object permanence, motion continuity, and appearance preservation—to assess how well models remember objects after they leave the field of view. Experiments show that current models only maintain short‑term consistency, revealing a significant gap between perception and robust memory.
arXiv:2608. 07408v1 Announce Type: cross Abstract: We study visual persistence in interactive video world models.
The paper introduces Linguistic Trajectory Encoding (LTE), a hybrid representation that compresses dynamic object motion histories using natural language descriptions, sparse spatial anchors, and visual anchors. LTE adapts compression to motion complexity by anchoring periods without reliable observations to the last seen location while preserving accuracy with geometric waypoints and linguistic descriptions. Evaluated on the newly constructed Spatial Memory Benchmark (SMB) from EgoLife multi‑day recordings, LTE achieves 45.3 % success in semantic trajectory retrieval and 48.7 % in long‑horizon object retrieval, outperforming prior structured‑memory and VLM baselines, and compresses trajectories 8.7×–26.1× with sub‑second query latency on 24‑hour video.
arXiv:2603.04349v2 Announce Type: replace Abstract: Understanding long videos is crucial for embodied intelligent agents, as their performance depends on effectively accumulating and using long-horiz...
arXiv:2608.18734v2 Announce Type: replace Abstract: 4D understanding and reasoning is a fundamental capability for embodied AI agents operating in dynamic physical environments. However, existing vis...
MemoryCard is a video-memory-based augmentation framework designed to improve long-video question answering for Vision‑Language Models. It segments lengthy videos into semantically coherent units—each representing a distinct topic or event—by performing a self‑reading process over the video and aligned utterances. For each unit, the framework generates an event‑level video gist and selects representative visual moments, which are compiled into unified Memory Cards that are used for retrieval and answering questions, yielding up to a 21.8% relative accuracy improvement under comparable visual‑token budgets.