Captioning for Text-Video Retrieval via Dual-Group Direct Preference Optimization

• URL: http://arxiv.org/abs/2509.16560v1
• Date: Sat, 20 Sep 2025 07:36:53 GMT
• Title: Captioning for Text-Video Retrieval via Dual-Group Direct Preference Optimization
• Authors: Ji Soo Lee, Byungoh Ko, Jaewon Cho, Howoong Lee, Jaewoon Byun, Hyunwoo J. Kim,
• Abstract summary: auxiliary captions are often used to enhance video understanding, bridging the gap between the modalities.<n>We propose $textbfCaRe-DPO, a retrieval framework that directly optimize caption generation using retrieval relevance scores.<n>We show that CaRe-DPO significantly enhances retrieval performance by effectively leveraging auxiliary knowledge to generate fine-grained captions for retrieval.
• Score: 30.445325065182868
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In text-video retrieval, auxiliary captions are often used to enhance video understanding, bridging the gap between the modalities. While recent advances in multi-modal large language models (MLLMs) have enabled strong zero-shot caption generation, we observe that such captions tend to be generic and indistinguishable across visually similar videos, limiting their utility for fine-grained retrieval. Moreover, conventional captioning approaches are typically evaluated using language generation metrics, such as BLEU, which are not typically tailored for retrieval tasks that require making discriminative distinctions between candidates. To address this, we propose $\textbf{CaRe-DPO}$, a retrieval framework that directly optimizes caption generation using retrieval relevance scores. At its core is Dual-Group Direct Preference Optimization (DG-DPO), a novel learning strategy that supervises captioning by modeling preferences across groups of distinct video and caption pairs. In addition, we present an MLLM-based retrieval model that incorporates role-embeddings to better distinguish between textual inputs with different functional roles, such as an auxiliary caption and a text query. Through extensive experiments, we demonstrate that CaRe-DPO significantly enhances retrieval performance by effectively leveraging auxiliary knowledge to generate fine-grained captions for retrieval. Code is available at https://github.com/mlvlab/CaReDPO.

Related papers

• AVC-DPO: Aligned Video Captioning via Direct Preference Optimization [50.08618093204503]
  Video multimodal large language models (video MLLMs) have achieved substantial progress in video captioning tasks.<n>We propose Aligned Video Captioning via Direct Preference Optimization (AVC-DPO), a post-training framework designed to enhance captioning capabilities in video MLLMs through preference alignment.<n>We have achieved exceptional performance in the LOVE@PRCV'25 Workshop Track 1A: Video Detailed Captioning Challenge, achieving first place on the Video Detailed Captioning benchmark.
  arXiv  Detail & Related papers  (2025-07-02T08:51:45Z)
• Classifier-Guided Captioning Across Modalities [69.75111271002137]
  We introduce a method to adapt captioning networks to the semantics of alternative settings, such as capturing audibility in audio captioning.<n>Our framework consists of two main components: (i) a frozen captioning system incorporating a language model (LM), and (ii) a text classifier that guides the captioning system.<n> Notably, when combined with an existing zero-shot audio captioning system, our framework improves its quality and sets state-of-the-art performance in zero-shot audio captioning.
  arXiv  Detail & Related papers  (2025-01-03T18:09:26Z)
• CLIP-SCGI: Synthesized Caption-Guided Inversion for Person Re-Identification [9.996589403019675]
  Person re-identification (ReID) has recently benefited from large pretrained vision-language models such as Contrastive Language-Image Pre-Training (CLIP) We propose one straightforward solution by leveraging existing image captioning models to generate pseudo captions for person images. We introduce CLIP-SCGI, a framework that leverages synthesized captions to guide the learning of discriminative and robust representations.
  arXiv  Detail & Related papers  (2024-10-12T06:24:33Z)
• 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)
• Video Enriched Retrieval Augmented Generation Using Aligned Video Captions [1.0878040851638]
  "aligned visual captions" describe the visual and audio content of videos in a large corpus. Visual captions can be adapted to specific use cases by prompting the original foundational model / captioner for particular visual details or fine tuning.
  arXiv  Detail & Related papers  (2024-05-27T23:39:17Z)
• Learning text-to-video retrieval from image captioning [59.81537951811595]
  We describe a protocol to study text-to-video retrieval training with unlabeled videos. We assume (i) no access to labels for any videos, and (ii) access to labeled images in the form of text. We show that automatically labeling video frames with image captioning allows text-to-video retrieval training.
  arXiv  Detail & Related papers  (2024-04-26T15:56:08Z)
• SHE-Net: Syntax-Hierarchy-Enhanced Text-Video Retrieval [11.548061962976321]
  We propose a novel Syntax-Hierarchy-Enhanced text-video retrieval method (SHE-Net)<n>First, to facilitate a more fine-grained integration of visual content, we employ the text syntax hierarchy, which reveals the grammatical structure of text descriptions.<n>Second, to further enhance the multi-modal interaction and alignment, we also utilize the syntax hierarchy to guide the similarity calculation.
  arXiv  Detail & Related papers  (2024-04-22T10:23:59Z)
• Few-shot Action Recognition with Captioning Foundation Models [61.40271046233581]
  CapFSAR is a framework to exploit knowledge of multimodal models without manually annotating text. Visual-text aggregation module based on Transformer is further designed to incorporate cross-modal-temporal complementary information. experiments on multiple standard few-shot benchmarks demonstrate that the proposed CapFSAR performs favorably against existing methods.
  arXiv  Detail & Related papers  (2023-10-16T07:08:39Z)
• Zero-shot Audio Topic Reranking using Large Language Models [42.774019015099704]
  Multimodal Video Search by Examples (MVSE) investigates using video clips as the query term for information retrieval. This work aims to compensate for any performance loss from this rapid archive search by examining reranking approaches. Performance is evaluated for topic-based retrieval on a publicly available video archive, the BBC Rewind corpus.
  arXiv  Detail & Related papers  (2023-09-14T11:13:36Z)
• Exploiting Auxiliary Caption for Video Grounding [66.77519356911051]
  Video grounding aims to locate a moment of interest matching a given query sentence from an untrimmed video. Previous works ignore the sparsity dilemma in video annotations, which fails to provide the context information between potential events and query sentences in the dataset. We propose an Auxiliary Caption Network (ACNet) for video grounding. Specifically, we first introduce dense video captioning to generate dense captions and then obtain auxiliary captions by Non-Auxiliary Caption Suppression (NACS) To capture the potential information in auxiliary captions, we propose Caption Guided Attention (CGA) project the semantic relations between auxiliary captions and
  arXiv  Detail & Related papers  (2023-01-15T02:04:02Z)
• Open-book Video Captioning with Retrieve-Copy-Generate Network [42.374461018847114]
  In this paper, we convert traditional video captioning task into a new paradigm, ie, Open-book Video Captioning. We propose a novel Retrieve-Copy-Generate network, where a pluggable video-to-text retriever is constructed to retrieve sentences as hints from the training corpus effectively. Our framework coordinates the conventional retrieval-based methods with orthodox encoder-decoder methods, which can not only draw on the diverse expressions in the retrieved sentences but also generate natural and accurate content of the video.
  arXiv  Detail & Related papers  (2021-03-09T08:17:17Z)
• Improving Image Captioning with Better Use of Captions [65.39641077768488]
  We present a novel image captioning architecture to better explore semantics available in captions and leverage that to enhance both image representation and caption generation. Our models first construct caption-guided visual relationship graphs that introduce beneficial inductive bias using weakly supervised multi-instance learning. During generation, the model further incorporates visual relationships using multi-task learning for jointly predicting word and object/predicate tag sequences.
  arXiv  Detail & Related papers  (2020-06-21T14:10:47Z)

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.