Controllable Hybrid Captioner for Improved Long-form Video Understanding

• URL: http://arxiv.org/abs/2507.17047v1
• Date: Tue, 22 Jul 2025 22:09:00 GMT
• Title: Controllable Hybrid Captioner for Improved Long-form Video Understanding
• Authors: Kuleen Sasse, Efsun Sarioglu Kayi, Arun Reddy,
• Abstract summary: Video data is extremely dense and high-dimensional.<n>Text-based summaries of video content offer a way to represent content in a much more compact manner than raw.<n>We introduce Vision Language Models (VLMs) to enrich the memory with static scene descriptions.
• Score: 0.24578723416255746
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video data, especially long-form video, is extremely dense and high-dimensional. Text-based summaries of video content offer a way to represent query-relevant content in a much more compact manner than raw video. In addition, textual representations are easily ingested by state-of-the-art large language models (LLMs), which enable reasoning over video content to answer complex natural language queries. To solve this issue, we rely on the progressive construction of a text-based memory by a video captioner operating on shorter chunks of the video, where spatio-temporal modeling is computationally feasible. We explore ways to improve the quality of the activity log comprised solely of short video captions. Because the video captions tend to be focused on human actions, and questions may pertain to other information in the scene, we seek to enrich the memory with static scene descriptions using Vision Language Models (VLMs). Our video understanding system relies on the LaViLa video captioner in combination with a LLM to answer questions about videos. We first explored different ways of partitioning the video into meaningful segments such that the textual descriptions more accurately reflect the structure of the video content. Furthermore, we incorporated static scene descriptions into the captioning pipeline using LLaVA VLM, resulting in a more detailed and complete caption log and expanding the space of questions that are answerable from the textual memory. Finally, we have successfully fine-tuned the LaViLa video captioner to produce both action and scene captions, significantly improving the efficiency of the captioning pipeline compared to using separate captioning models for the two tasks. Our model, controllable hybrid captioner, can alternate between different types of captions according to special input tokens that signals scene changes detected in the video.

Related papers

• Toward Scalable Video Narration: A Training-free Approach Using Multimodal Large Language Models [10.585096070697348]
  We introduce VideoNarrator, a novel training-free pipeline designed to generate dense video captions.<n>VideoNarrator addresses challenges by leveraging a flexible pipeline where off-the-shelf MLLMs and visual-language models can function as caption generators.<n>Our experimental results demonstrate that the synergistic interaction of these components significantly enhances the quality and accuracy of video narrations.
  arXiv  Detail & Related papers  (2025-07-22T22:16:37Z)
• The Devil is in the Distributions: Explicit Modeling of Scene Content is Key in Zero-Shot Video Captioning [89.64905703368255]
  We propose a novel progressive multi-granularity textual prompting strategy for zero-shot video captioning.<n>Our approach constructs three distinct memory banks, encompassing noun phrases, scene graphs of noun phrases, and entire sentences.
  arXiv  Detail & Related papers  (2025-03-31T03:00:19Z)
• Fine-Grained Captioning of Long Videos through Scene Graph Consolidation [44.30028794237688]
  We introduce a novel framework for long video captioning based on graph consolidation.<n>Our approach first generates segment-level captions, corresponding to individual frames or short video intervals.<n>A lightweight graph-to-text decoder then produces the final video-level caption.
  arXiv  Detail & Related papers  (2025-02-23T03:59:05Z)
• CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval [24.203328970223527]
  We present CaReBench, a testing benchmark for fine-grained video captioning and retrieval.<n>Uniquely, it provides manually separated spatial annotations and temporal annotations for each video.<n>Based on this design, we introduce two evaluation metrics, ReBias and CapST, specifically tailored for video retrieval and video captioning tasks.
  arXiv  Detail & Related papers  (2024-12-31T15:53:50Z)
• Vript: A Video Is Worth Thousands of Words [54.815686588378156]
  Vript is an annotated corpus of 12K high-resolution videos, offering detailed, dense, and script-like captions for over 420K clips. Each clip has a caption of 145 words, which is over 10x longer than most video-text datasets. Vript is a powerful model capable of end-to-end generation of dense and detailed captions for long videos.
  arXiv  Detail & Related papers  (2024-06-10T06:17:55Z)
• ShareGPT4Video: Improving Video Understanding and Generation with Better Captions [93.29360532845062]
  We present the ShareGPT4Video series, aiming to facilitate the video understanding of large video-language models (LVLMs) and the video generation of text-to-video models (T2VMs) via dense and precise captions. The series comprises: ShareGPT4Video, 40K GPT4V annotated dense captions of videos with various lengths and sources, developed through carefully designed data filtering and annotating strategy. We further develop ShareCaptioner-Video, a superior captioner capable of efficiently generating high-quality captions for arbitrary videos.
  arXiv  Detail & Related papers  (2024-06-06T17:58:54Z)
• VideoCon: Robust Video-Language Alignment via Contrast Captions [80.08882631838914]
  Video-language alignment models are not robust to semantically-plausible contrastive changes in the video captions. Our work identifies a broad spectrum of contrast misalignments, such as replacing entities, actions, and flipping event order. Our model sets new state of the art zero-shot performance in temporally-extensive video-language tasks.
  arXiv  Detail & Related papers  (2023-11-15T19:51:57Z)
• HowToCaption: Prompting LLMs to Transform Video Annotations at Scale [72.69268311756082]
  We propose to leverage the capabilities of large language models (LLMs) to obtain high-quality video descriptions aligned with videos at scale. We introduce a prompting method that is able to take into account a longer text of subtitles, allowing us to capture the contextual information beyond one single sentence. We apply our method to the subtitles of the HowTo100M dataset, creating a new large-scale dataset, HowToCaption.
  arXiv  Detail & Related papers  (2023-10-07T19:32:55Z)
• HierVL: Learning Hierarchical Video-Language Embeddings [108.77600799637172]
  HierVL is a novel hierarchical video-language embedding that simultaneously accounts for both long-term and short-term associations. We introduce a hierarchical contrastive training objective that encourages text-visual alignment at both the clip level and video level. Our hierarchical scheme yields a clip representation that outperforms its single-level counterpart as well as a long-term video representation that achieves SotA.
  arXiv  Detail & Related papers  (2023-01-05T21:53:19Z)
• Enriching Video Captions With Contextual Text [9.994985014558383]
  We propose an end-to-end sequence-to-sequence model which generates video captions based on visual input. We do not preprocess the text further, and let the model directly learn to attend over it.
  arXiv  Detail & Related papers  (2020-07-29T08:58:52Z)
• Multi-modal Dense Video Captioning [18.592384822257948]
  We present a new dense video captioning approach that is able to utilize any number of modalities for event description. We show how audio and speech modalities may improve a dense video captioning model.
  arXiv  Detail & Related papers  (2020-03-17T15:15:17Z)

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.