A Benchmarking Methodology to Assess Open-Source Video Large Language Models in Automatic Captioning of News Videos

• URL: http://arxiv.org/abs/2603.27662v1
• Date: Sun, 29 Mar 2026 12:28:35 GMT
• Title: A Benchmarking Methodology to Assess Open-Source Video Large Language Models in Automatic Captioning of News Videos
• Abstract summary: This work presents a comparative study of eight state-of-the-art open-source VidLLMs for automatic news video captioning.<n>We employ lexical metrics (METEOR, ROUGE-L), semantic metrics (BERTScore, CLIPScore, Text Similarity, Mean Reciprocal Rank), and two novel fidelity metrics proposed in this work.<n>Our analysis reveals that standard metrics exhibit limited discrimi power for news video captioning due to surface-form dependence, static-frame insensitivity, and function-word inflation.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: News videos are among the most prevalent content types produced by television stations and online streaming platforms, yet generating textual descriptions to facilitate indexing and retrieval largely remains a manual process. Video Large Language Models (VidLLMs) offer significant potential to automate this task, but a comprehensive evaluation in the news domain is still lacking. This work presents a comparative study of eight state-of-the-art open-source VidLLMs for automatic news video captioning, evaluated on two complementary benchmark datasets: a Chilean TV news corpus (approximately 1,345 clips) and a BBC News corpus (9,838 clips). We employ lexical metrics (METEOR, ROUGE-L), semantic metrics (BERTScore, CLIPScore, Text Similarity, Mean Reciprocal Rank), and two novel fidelity metrics proposed in this work: the Thematic Fidelity Score (TFS) and Entity Fidelity Score (EFS). Our analysis reveals that standard metrics exhibit limited discriminative power for news video captioning due to surface-form dependence, static-frame insensitivity, and function-word inflation. TFS and EFS address these gaps by directly assessing thematic structure preservation and named-entity coverage in the generated captions. Results show that Gemma~3 achieves the highest overall performance across both datasets and most evaluation dimensions, with Qwen-VL as a consistent runner-up.

Related papers

• From Content to Audience: A Multimodal Annotation Framework for Broadcast Television Analytics [1.6639892342953113]
  multimodal large language models (MLLMs) have demonstrated strong general-purpose video understanding capabilities.<n>This paper presents a systematic evaluation of multimodal annotation pipelines applied to broadcast television news in the Italian setting.
  arXiv  Detail & Related papers  (2026-03-24T13:46:51Z)
• Diffusion-Pretrained Dense and Contextual Embeddings [3.1271035100823643]
  pplx-embed is a family of multilingual embedding models that employ multi-stage contrastive learning on a diffusion-pretrained language model backbone for web-scale retrieval.<n>We release two model types: pplx-embed-v1 for standard retrieval, and pplx-embed-context-v1 for contextualized embeddings.
  arXiv  Detail & Related papers  (2026-02-11T18:59:08Z)
• Prompts to Summaries: Zero-Shot Language-Guided Video Summarization [12.200609701777907]
  We introduce Prompts-to-Summaries: the first zero-shot, text-queryable video summarizer.<n>It converts off-the-shelf video-language models (VidLMs) captions into user-guided skims via large language models (LLMs) judging.<n>Our pipeline generates rich scene-level descriptions through a memory-efficient, batch-style VidLM prompting scheme.<n>On SumMe and TVSum, our data-free approach surpasses all prior data-hungry unsupervised methods.
  arXiv  Detail & Related papers  (2025-06-12T15:23:11Z)
• VidText: Towards Comprehensive Evaluation for Video Text Understanding [56.121054697977115]
  VidText is a benchmark for comprehensive and in-depth evaluation of video text understanding.<n>It covers a wide range of real-world scenarios and supports multilingual content.<n>It introduces a hierarchical evaluation framework with video-level, clip-level, and instance-level tasks.
  arXiv  Detail & Related papers  (2025-05-28T19:39:35Z)
• 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)
• CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness [30.44039177018447]
  CAPability is a comprehensive benchmark for evaluating visual captioning across 12 dimensions spanning six critical views.<n>We curate nearly 11K human-annotated images and videos with visual element annotations to evaluate the generated captions.
  arXiv  Detail & Related papers  (2025-02-19T07:55:51Z)
• Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach [56.610806615527885]
  A key challenge in text-video retrieval (TVR) is the information asymmetry between video and text.<n>This paper introduces a data-centric framework to bridge this gap by enriching textual representations to better match the richness of video content.<n>We propose a query selection mechanism that identifies the most relevant and diverse queries, reducing computational cost while improving accuracy.
  arXiv  Detail & Related papers  (2024-08-14T01:24:09Z)
• Towards A Better Metric for Text-to-Video Generation [102.16250512265995]
  Generative models have demonstrated remarkable capability in synthesizing high-quality text, images, and videos. We introduce a novel evaluation pipeline, the Text-to-Video Score (T2VScore) This metric integrates two pivotal criteria: (1) Text-Video Alignment, which scrutinizes the fidelity of the video in representing the given text description, and (2) Video Quality, which evaluates the video's overall production caliber with a mixture of experts.
  arXiv  Detail & Related papers  (2024-01-15T15:42:39Z)
• UATVR: Uncertainty-Adaptive Text-Video Retrieval [90.8952122146241]
  A common practice is to transfer text-video pairs to the same embedding space and craft cross-modal interactions with certain entities. We propose an Uncertainty-language Text-Video Retrieval approach, termed UATVR, which models each look-up as a distribution matching procedure.
  arXiv  Detail & Related papers  (2023-01-16T08:43:17Z)
• Watch and Learn: Mapping Language and Noisy Real-world Videos with Self-supervision [54.73758942064708]
  We teach machines to understand visuals and natural language by learning the mapping between sentences and noisy video snippets without explicit annotations. For training and evaluation, we contribute a new dataset ApartmenTour' that contains a large number of online videos and subtitles.
  arXiv  Detail & Related papers  (2020-11-19T03:43:56Z)
• Video captioning with stacked attention and semantic hard pull [0.0]
  The task of generating a semantically accurate description of a video is quite complex. This paper proposes a novel architecture, namely Semantically Sensible Video Captioning (SSVC) The paper reports that the use of the novelties improves the performance of state-of-the-art architectures.
  arXiv  Detail & Related papers  (2020-09-15T19:34:37Z)
• Abstractive Summarization of Spoken and Written Instructions with BERT [66.14755043607776]
  We present the first application of the BERTSum model to conversational language. We generate abstractive summaries of narrated instructional videos across a wide variety of topics. We envision this integrated as a feature in intelligent virtual assistants, enabling them to summarize both written and spoken instructional content upon request.
  arXiv  Detail & Related papers  (2020-08-21T20:59:34Z)

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.