Narrative Aligned Long Form Video Question Answering

• URL: http://arxiv.org/abs/2603.19481v1
• Date: Thu, 19 Mar 2026 21:23:15 GMT
• Title: Narrative Aligned Long Form Video Question Answering
• Abstract summary: We introduce NA-VQA, a benchmark designed to evaluate deep temporal and narrative reasoning in long-form videos.<n> NA-VQA contains 88 full-length movies and 4.4K open-ended question-answer pairs, each grounded in multiple evidence spans labeled as Short, Medium, or Far.<n>We propose Video-NaRA, a narrative-centric framework that builds event-level chains and stores them in a structured memory for retrieval during reasoning.
• Score: 12.805359127629215
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent progress in multimodal large language models (MLLMs) has led to a surge of benchmarks for long-video reasoning. However, most existing benchmarks rely on localized cues and fail to capture narrative reasoning, the ability to track intentions, connect distant events, and reconstruct causal chains across an entire movie. We introduce NA-VQA, a benchmark designed to evaluate deep temporal and narrative reasoning in long-form videos. NA-VQA contains 88 full-length movies and 4.4K open-ended question-answer pairs, each grounded in multiple evidence spans labeled as Short, Medium, or Far to assess long-range dependencies. By requiring generative, multi-scene answers, NA-VQA tests whether models can integrate dispersed narrative information rather than rely on shallow pattern matching. To address the limitations of existing approaches, we propose Video-NaRA, a narrative-centric framework that builds event-level chains and stores them in a structured memory for retrieval during reasoning. Extensive experiments show that state-of-the-art MLLMs perform poorly on questions requiring far-range evidence, highlighting the need for explicit narrative modeling. Video-NaRA improves long-range reasoning performance by up to 3 percent, demonstrating its effectiveness in handling complex narrative structures. We will release NA-VQA upon publication.

Related papers

• VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video Understanding [61.00809248898572]
  Long video understanding is a problem in which an agent reads the video turn by turn along the temporal axis, deciding at each turn how fast to watch, what evidence to retain, when to revisit uncertain segments, and when to stop and answer.<n>We propose textbfVideoScout, a multi-turn reasoning agent that instantiates the SEA paradigm through adaptive reasoning pacing.<n>Experiments on long video understanding and reasoning benchmarks demonstrate that our 7B model achieves strong performance compared with existing trained 7B agentic models.
  arXiv  Detail & Related papers  (2026-09-14T14:04:03Z)
• Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events [52.031070006859544]
  Video multimodal large language models (MLLMs) have made rapid progress on general and long-form video understanding, yet their ability to preserve brief answer-critical visual evidence remains underexplored.<n>We introduce Moment-Video, a benchmark for diagnosing the temporal fidelity of video MLLMs through momentary visual event understanding.
  arXiv  Detail & Related papers  (2026-06-01T17:32:20Z)
• 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)
• Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models [56.851611990473174]
  Reasoning over dynamic visual content remains a central challenge for large language models.<n>We propose a reinforcement learning approach that enhances both temporal precision and reasoning consistency.<n>The resulting model, Video R2, achieves consistently higher TAC, VAS, and accuracy across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-11-28T18:59:58Z)
• LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling [87.98096428508181]
  LongVT is an end-to-end agentic framework that enables "Thinking with Long Videos" via interleaved Multimodal Chain-of-Tool-Thought.<n>We exploit LMMs' inherent temporal grounding ability as a native video cropping tool to zoom in on a specific video clip and resample finer-grained video frames.<n>Our training dataset consists of 247.9K samples for tool-integrated cold-start supervised fine-tuning, 1.6K samples for agentic reinforcement learning, and 15.4K samples for agentic reinforcement fine-tuning.
  arXiv  Detail & Related papers  (2025-11-25T19:22:48Z)
• NOAH: Benchmarking Narrative Prior driven Hallucination and Omission in Video Large Language Models [8.6767620170781]
  Video large language models (Video LLMs) have recently achieved strong performance on tasks such as captioning, summarization, and question answering.<n>Many models and training methods explicitly encourage continuity across events to enhance narrative coherence.<n>We identify this bias, which we call narrative prior, as a key driver of two errors: hallucinations, where non-existent events are introduced or existing ones are misinterpreted, and omissions, where factual events are suppressed because they are misaligned with surrounding context.
  arXiv  Detail & Related papers  (2025-11-09T17:41:11Z)
• NeuS-QA: Grounding Long-Form Video Understanding in Temporal Logic and Neuro-Symbolic Reasoning [25.109179044490844]
  Long-Form Question Answering (LVQA) poses challenges beyond traditional visual question answering (VQA)<n> Vanilla approaches, which sample frames uniformly and feed them to a VLM with the question, incur significant token overhead.<n>NeuS-QA translates a natural language question into a formal temporal logic expression, constructs a video automaton from frame-level semantic propositions.
  arXiv  Detail & Related papers  (2025-09-22T17:15:13Z)
• Cinéaste: A Fine-grained Contextual Movie Question Answering Benchmark [47.482960367243756]
  We introduce $mathsfCinacuteeaste$, a comprehensive benchmark for long-form movie understanding.<n>Our dataset comprises 3,119 multiple-choice question-answer pairs derived from 1,805 scenes across 200 movies.<n>Experiments show that existing MLLMs struggle on $mathsfCinacuteeaste$; our analysis reveals that long-range temporal reasoning is a primary bottleneck.
  arXiv  Detail & Related papers  (2025-09-17T17:58:06Z)
• Movie Facts and Fibs (MF$^2$): A Benchmark for Long Movie Understanding [97.05584099530226]
  We introduce MF$2$, a new benchmark for evaluating whether models can comprehend, consolidate, and recall key narrative information from full-length movies.<n>For each pair, models must correctly identify both the true and false claims.<n>Our experiments demonstrate that both open-weight and closed state-of-the-art models fall well short of human performance.
  arXiv  Detail & Related papers  (2025-06-06T17:58:36Z)
• VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs [27.473258727617477]
  Long video understanding presents unique challenges due to the complexity of reasoning over extended timespans. We propose a framework VideoINSTA, i.e. INformative Spatial-TemporAl Reasoning for long-form video understanding. Our model significantly improves the state-of-the-art on three long video question-answering benchmarks.
  arXiv  Detail & Related papers  (2024-09-30T15:04:14Z)
• Long Story Short: a Summarize-then-Search Method for Long Video Question Answering [23.094728230459125]
  We investigate if language models can extend their zero-shot reasoning abilities to long multimodal narratives in multimedia content. We propose Long Story Short, a framework for narrative video QA that first summarizes the narrative of the video to a short plot and then searches parts of the video relevant to the question. Our model outperforms state-of-the-art supervised models by a large margin, highlighting the potential of zero-shot QA for long videos.
  arXiv  Detail & Related papers  (2023-11-02T13:36:11Z)
• Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Model [70.97446870672069]
  Video anomaly detection (VAD) has been paid increasing attention due to its potential applications. Video Anomaly Retrieval ( VAR) aims to pragmatically retrieve relevant anomalous videos by cross-modalities. We present two benchmarks, UCFCrime-AR and XD-Violence, constructed on top of prevalent anomaly datasets.
  arXiv  Detail & Related papers  (2023-07-24T06:22:37Z)
• MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering [73.61182342844639]
  We introduce a new model named Multi-modal Iterative Spatial-temporal Transformer (MIST) to better adapt pre-trained models for long-form VideoQA. MIST decomposes traditional dense spatial-temporal self-attention into cascaded segment and region selection modules. Visual concepts at different granularities are then processed efficiently through an attention module.
  arXiv  Detail & Related papers  (2022-12-19T15:05:40Z)

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.