Video Frame Selection

Understanding long videos is crucial for embodied intelligent agents, as their performance depends on effectively accumulating and using long-horizon perceptual memories. Multimodal large language models (MLLMs) are increasingly used for long-video understanding, but their performance degrades and inference time increases as more frames are provided. Therefore, selecting informative keyframes is essential for efficient question answering over long videos. In this work, we develop FocusGraph, a framework for keyframe selection in egocentric long-video question answering. It includes a lightweight Scene-Graph LLM Selector that identifies query-relevant clips from compact graph-based captions, avoiding the need to process raw frame sequences at question time. From these clips, we extract keyframes using Patch-wise Sparse-Flow Retention (PSFR), an offline program-evolved method with no learned parameters at inference time, before passing them to an MLLM for answer generation. FocusGraph achieves state-of-the-art performance on FindingDory and HourVideo while reducing question-time inference cost compared with existing approaches.

Always-on egocentric cameras are increasingly used as demonstrations for embodied robotics, imitation learning, and assistive AR, but the resulting video streams are dominated by redundant and low-quality frames. Under the storage and battery constraints of wearable devices, choosing which frames to keep is as important as how to learn from them. We observe that modern eye-tracking headsets provide a continuous, training-free side channel that decomposes into two complementary axes: gaze fixation captures visual stability (quality), while pupil response captures arousal-linked moments (novelty). We operationalize this insight as a Dual-Criterion Frame Curator that first gates frames by gaze quality and then ranks the survivors by pupil-derived novelty. On the Visual Experience Dataset (VEDB), curated frames at 10% budget match the classification performance of the full stream, and naive signal fusion consistently destroys both contributions. The benefit is task-dependent: pupil ranking improves activity recognition, while gaze-only selection already dominates for scene recognition, confirming that the two signals serve genuinely different roles. Our method requires no model inference and operates at capture time, offering a path toward efficient, always-on egocentric data curation.

Massive frame redundancy and limited context window make efficient frame selection crucial for long-video understanding with large vision-language models (LVLMs). Prevailing approaches, however, adopt a flat sampling paradigm which treats the video as an unstructured collection of frames. In this paper, we introduce Event-Anchored Frame Selection (EFS), a hierarchical, event-aware pipeline. Leveraging self-supervised DINO embeddings, EFS first partitions the video stream into visually homogeneous temporal segments, which serve as proxies for semantic events. Within each event, it then selects the most query-relevant frame as an anchor. These anchors act as structural priors that guide a global refinement stage using an adaptive Maximal Marginal Relevance (MMR) scheme. This pipeline ensures the final keyframe set jointly optimizes for event coverage, query relevance, and visual diversity. As a training-free, plug-and-play module, EFS can be seamlessly integrated into off-the-shelf LVLMs, yielding substantial gains on challenging video understanding benchmarks. Specifically, when applied to LLaVA-Video-7B, EFS improves accuracy by 4.7%, 4.9%, and 8.8% on VideoMME, LongVideoBench, and MLVU, respectively.

Video summarization transforms long videos into concise representations that are easier to document and analyze, especially in high-stakes domains such as surgical training. However, long-form videos often require dense frame processing or supervised training pipelines, which can be computationally expensive and may still miss important procedural content. We present PRISM: Procedural Representation via Integrated Semantic and Multimodal Analysis, a zero-shot and training-free framework for frame-efficient procedural video summarization. PRISM selects fewer than 5% of video frames while retaining over 84% semantic content and improving over baselines by up to 7.5%. Rather than exhaustively processing frames, PRISM uses lightweight visual filtering and dynamically generated procedural labels as semantic anchors to select meaningful frame-label groups. This selective inference design preserves key actions, transitions, and contextual details while reducing the number of visual inputs passed to downstream vision-language captioning stages. We evaluate PRISM on YouCook2 and ActivityNet Captions, with additional studies on keyframe selection benchmarks and surgical video datasets. Across procedural and domain-specific video tasks, PRISM achieves strong semantic alignment and accuracy, suggesting that efficient multimodal video understanding can be achieved by grounding generation in dynamically generated semantic anchors.

User-generated videos (UGVs) uploaded from mobile phones to social media sites like YouTube and TikTok are short and non-repetitive. We summarize a transitory UGV into several keyframes in linear-time via fast graph sampling based on Gershgorin disc alignment (GDA). Specifically, we first model a sequence of $N$ frames in a UGV as an $M$-hop path graph $\cG^o$ for $M \ll N$, where the similarity between two frames within $M$ time instants is encoded as a positive edge based on feature similarity. Towards efficient sampling, we then ``unfold'' $\cG^o$ to a $1$-hop path graph $\cG$, specified by a generalized graph Laplacian matrix $\cL$, via one of two graph unfolding procedures with provable performance bounds. We show that maximizing the smallest eigenvalue $λ_{\min}(\B)$ of a coefficient matrix $\B = \diag{\h} + μ\cL$, where $\h$ is the binary keyframe selection vector, is equivalent to minimizing a worst-case signal reconstruction error. We maximize instead the Gershgorin circle theorem (GCT) lower bound $λ^-_{\min}(\B)$ by choosing $\h$ via a new fast graph sampling algorithm that iteratively aligns left-ends of Gershgorin discs for all graph nodes (frames). Experiments on multiple short video datasets show that our algorithm achieves comparable or better keyframe selection performance compared to state-of-the-art methods, at a substantially reduced complexity.