Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG

• URL: http://arxiv.org/abs/2608.28699v1
• Date: Thu, 27 Aug 2026 14:25:32 GMT
• Title: Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG
• Abstract summary: Retrieval-augmented generation (RAG) offers a promising middle ground by selectively retrieving relevant video segments for grounded generation.<n>We investigate RAG for movie understanding, which demands story-level reasoning over characters, events, and narrative arcs spanning hours of content.<n>We introduce NarraScene, a narrative-centric scene segmentation dataset annotated with a three-level cognitive taxonomy spanning physical, character, and narrative change.
• Score: 26.7662002828488
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Understanding long-form video remains a fundamental challenge for multimodal large language models (MLLMs). Sparse frame sampling fails to capture fine-grained visual details, while dense sampling quickly exceeds context length limits. Retrieval-augmented generation (RAG) offers a promising middle ground by selectively retrieving relevant video segments for grounded generation, yet its effectiveness critically depends on the quality of the video segments used as retrieval units. In this paper, we investigate RAG for movie understanding, which demands story-level reasoning over characters, events, and narrative arcs spanning hours of content. Scene segmentation, a long-studied problem that partitions movies into semantically coherent units, is a natural candidate for defining such retrieval units. We reexamine whether existing methods actually serve this role through comprehensive evaluation on downstream movie understanding tasks, and find that they consistently fail to outperform naive uniform temporal chunking. Our audit of the most standard scene segmentation benchmarks reveals why: current annotations prioritize visually salient transitions over narrative event structure. Motivated by this mismatch, we introduce NarraScene, a narrative-centric scene segmentation dataset annotated with a three-level cognitive taxonomy spanning physical, character, and narrative change, where every valid boundary requires a narrative-level shift. When used as retrieval units, these narrative-grounded segments outperform uniform chunking on downstream movie understanding tasks, suggesting that the central challenge for scene segmentation in movie RAG is not detecting boundaries, but identifying the narrative event units that matter for movie understanding.

Related papers

• Explainable Forensics of Manipulated Segments in Untrimmed Long Videos [50.190474724159465]
  We formulate the task of Temporal AI-Generated Segment localization and Explanation.<n>We introduce TASLE, a large-scale benchmark comprising 12,472 untrimmed videos with diverse manipulation patterns and rich annotation signals.<n>We propose MSLoc, a coarse-to-fine forensic baseline that combines a boundary-sensitive proposal generation module for efficient long-video scanning with an MLLM-based refinement module for precise boundary localization and interpretable reasoning.
  arXiv  Detail & Related papers  (2026-06-01T15:48:38Z)
• ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation [69.45329019089041]
  Multi-Shot Video Extrapolation (MSVE) is a task that extends an observed frame or clip into a sequence of cinematically structured shots.<n>MSVE reveals that long-video failure is not merely a limitation of context length, but a failure of context allocation.<n>We propose Recursive Context Allocation (ReCA), an inference-time framework that allocates context hierarchically across planning and generation.
  arXiv  Detail & Related papers  (2026-05-26T04:16:56Z)
• Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark [13.365117498062565]
  This work defines a scene as a coherent segment of a video in which both visual and semantic contexts remain consistent.<n>We introduce a new benchmark, SceneBench, designed to provide scene-level challenges.<n>Scene-RAG improves VLM performance by +2.50%, confirming that current models still struggle with long-context retention.
  arXiv  Detail & Related papers  (2026-03-28T12:44:19Z)
• VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding [40.699624658181456]
  VideoDetective is a framework that integrates query-to-segment relevance and inter-segment affinity for effective clue hunting in long-video question answering.<n>Our method consistently achieves substantial gains across a wide range of mainstream MLLMs on representative benchmarks, with accuracy improvements of up to 7.5% on VideoMME-long.
  arXiv  Detail & Related papers  (2026-03-23T17:59:51Z)
• Temporal Prompting Matters: Rethinking Referring Video Object Segmentation [64.82333675385802]
  Referring Video Object (RVOS) aims to segment the object referred to by the query sentence in the video.<n>Most existing methods require end-to-end training with dense mask annotations.<n>We propose a Temporal Prompt Generation and Selection (Tenet) framework to address the referring and video factors.
  arXiv  Detail & Related papers  (2025-10-08T17:59:57Z)
• SceneRAG: Scene-level Retrieval-Augmented Generation for Video Understanding [6.980340270823506]
  We present SceneRAG, a framework to segment videos into narrative-consistent scenes.<n>For each scene, the framework fuses information from both visual and textual modalities to extract entity relations.<n>Experiments on the LongerVideos benchmark, featuring over 134 hours of diverse content, confirm that SceneRAG substantially outperforms prior baselines.
  arXiv  Detail & Related papers  (2025-06-09T10:00:54Z)
• CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for Videos [59.391265901911005]
  We propose CoT-RVS, a novel framework employing the zero-shot Chain-of-Thought (CoT) capability of MLLM to address complex challenges by temporal-semantic reasoning.<n>CoT-RVS analyzes the visible objects within a given frame that possibly match the language query (semantic), and chooses a corresponding for each object that can be observed effortlessly among all frames (temporal)<n>Our framework's training-free feature further allows its extension to process online video streams, where the CoT is used at test time to update the object of interest when a better target starts to emerge
  arXiv  Detail & Related papers  (2025-05-24T07:01:31Z)
• ViLLa: Video Reasoning Segmentation with Large Language Model [48.75470418596875]
  We present ViLLa: Video reasoning segmentation with Large Language Model.<n>Our ViLLa manages to tackle these challenges through multiple core innovations.<n>To enable efficient processing of long videos, ViLLa incorporates (3) a key segment sampler that adaptively partitions long videos into shorter but semantically dense segments for less redundancy.
  arXiv  Detail & Related papers  (2024-07-18T17:59:17Z)
• Multi-Modal Domain Adaptation Across Video Scenes for Temporal Video Grounding [59.599378814835205]
  Temporal Video Grounding (TVG) aims to localize the temporal boundary of a specific segment in an untrimmed video based on a given language query. We introduce a novel AMDA method to adaptively adjust the model's scene-related knowledge by incorporating insights from the target data.
  arXiv  Detail & Related papers  (2023-12-21T07:49:27Z)
• Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation [79.50868197788773]
  We develop a more accurate weakly-supervised solution by introducing Cross-Sentence Relations Mining. We explore two cross-sentence relational constraints: (1) trimmed ordering and (2) semantic consistency among sentences in a paragraph description of video activities. Experiments on two publicly available activity localisation datasets show the advantages of our approach over the state-of-the-art weakly supervised methods.
  arXiv  Detail & Related papers  (2021-07-23T20:04:01Z)
• A Hierarchical Multi-Modal Encoder for Moment Localization in Video Corpus [31.387948069111893]
  We show how to identify a short segment in a long video that semantically matches a text query. To tackle this problem, we propose the HierArchical Multi-Modal EncodeR (HAMMER) that encodes a video at both the coarse-grained clip level and the fine-trimmed frame level. We conduct extensive experiments to evaluate our model on moment localization in video corpus on ActivityNet Captions and TVR datasets.
  arXiv  Detail & Related papers  (2020-11-18T02:42:36Z)
• A Local-to-Global Approach to Multi-modal Movie Scene Segmentation [95.34033481442353]
  We build a large-scale video dataset MovieScenes, which contains 21K annotated scene segments from 150 movies. We propose a local-to-global scene segmentation framework, which integrates multi-modal information across three levels, i.e. clip, segment, and movie. Our experiments show that the proposed network is able to segment a movie into scenes with high accuracy, consistently outperforming previous methods.
  arXiv  Detail & Related papers  (2020-04-06T13:58:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.