# Point to Span: Zero-Shot Moment Retrieval for Navigating Unseen Hour-Long Videos

arXiv: https://arxiv.org/abs/2512.10363 · HTML: https://mlsanity.com/paper/2512.10363/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 35 references that are in the map.
- First posted on arXiv 11 Dec 2025.

## Builds on (most cited first, 29 of 29)

- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding](https://mlsanity.com/paper/2312.02051/) (2023)
- [Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning](https://mlsanity.com/paper/2302.14115/) (2023)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [UniVTG: Towards Unified Video-Language Temporal Grounding](https://mlsanity.com/paper/2307.16715/) (2023)
- [A Simple LLM Framework for Long-Range Video Question-Answering](https://mlsanity.com/paper/2312.17235/) (2023)
- [Query-Dependent Video Representation for Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2303.13874/) (2023)
- [LITA: Language Instructed Temporal-Localization Assistant](https://mlsanity.com/paper/2403.19046/) (2024)
- [SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models](https://mlsanity.com/paper/2407.15841/) (2024)
- [Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning](https://mlsanity.com/paper/2402.11435/) (2024)
- [VideoLLM: Modeling Video Sequence with Large Language Models](https://mlsanity.com/paper/2305.13292/) (2023)
- [MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions](https://mlsanity.com/paper/2112.00431/) (2021)
- [GroundingGPT:Language Enhanced Multi-modal Grounding Model](https://mlsanity.com/paper/2401.06071/) (2024)
- [HawkEye: Training Video-Text LLMs for Grounding Text in Videos](https://mlsanity.com/paper/2403.10228/) (2024)
- [QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries](https://mlsanity.com/paper/2107.09609/) (2021)
- [ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System](https://mlsanity.com/paper/2304.14407/) (2023)
- [SnAG: Scalable and Accurate Video Grounding](https://mlsanity.com/paper/2404.02257/) (2024)
- [Training-free Video Temporal Grounding using Large-scale Pre-trained Models](https://mlsanity.com/paper/2408.16219/) (2024)
- [CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding](https://mlsanity.com/paper/2209.10918/) (2022)
- [Localizing Moments in Long Video Via Multimodal Guidance](https://mlsanity.com/paper/2302.13372/) (2023)
- [Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos](https://mlsanity.com/paper/2303.08345/) (2023)
- [Zero-Shot Video Moment Retrieval from Frozen Vision-Language Models](https://mlsanity.com/paper/2309.00661/) (2023)
- [ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos](https://mlsanity.com/paper/2411.14901/) (2024)
- [Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models](https://mlsanity.com/paper/2501.07972/) (2025)
- [RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos](https://mlsanity.com/paper/2312.06729/) (2023)
- [MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval](https://mlsanity.com/paper/2502.12558/) (2025)
- [Zero-shot Video Moment Retrieval With Off-the-Shelf Models](https://mlsanity.com/paper/2211.02178/) (2022)

## Built on by (most cited first, 2 of 2)

- [D'ej`a Cue: Localizing States in Object Histories via Vocabulary-Relative Coordinates](https://mlsanity.com/paper/2608.02044/) (2026)
- [Training-Free Temporal Abstraction for General Video Understanding](https://mlsanity.com/paper/2608.27929/) (2026)

## Abstract (arXiv)

Zero-shot Long Video Moment Retrieval (ZLVMR) is the task of identifying temporal segments in hour-long videos using a natural language query without task-specific training. The core technical challenge of LVMR stems from the computational infeasibility of processing entire lengthy videos in a single pass. This limitation has established a 'Search-then-Refine' approach, where candidates are rapidly narrowed down, and only those portions are analyzed, as the dominant paradigm for LVMR. However, existing approaches to this paradigm face severe limitations. Conventional supervised learning suffers from limited scalability and poor generalization, despite substantial resource consumption. Yet, existing zero-shot methods also fail, facing a dual challenge: (1) their heuristic strategies cause a 'search' phase candidate explosion, and (2) the 'refine' phase, which is vulnerable to semantic discrepancy, requires high-cost VLMs for verification, incurring significant computational overhead. We propose Point-to-Span (P2S), a novel training-free framework to overcome this challenge of inefficient 'search' and costly 'refine' phases. P2S overcomes these challenges with two key innovations: an 'Adaptive Span Generator' to prevent the search phase candidate explosion, and 'Query Decomposition' to refine candidates without relying on high-cost VLM verification. To our knowledge, P2S is the first zero-shot framework capable of temporal grounding in hour-long videos, outperforming supervised state-of-the-art methods by a significant margin (e.g., +3.7% on R5@0.1 on MAD).