DANTE-AD: Dual-Vision Attention Network for Long-Term Audio Description

• URL: http://arxiv.org/abs/2503.24096v1
• Date: Mon, 31 Mar 2025 13:49:43 GMT
• Title: DANTE-AD: Dual-Vision Attention Network for Long-Term Audio Description
• Authors: Adrienne Deganutti, Simon Hadfield, Andrew Gilbert,
• Abstract summary: We introduce DANTE-AD, an enhanced video description model leveraging a dual-vision Transformer-based architecture.<n>We propose a novel, state-of-the-art method for sequential cross-attention to achieve contextual grounding for fine-grained audio description generation.
• Score: 19.14915136673913
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Audio Description is a narrated commentary designed to aid vision-impaired audiences in perceiving key visual elements in a video. While short-form video understanding has advanced rapidly, a solution for maintaining coherent long-term visual storytelling remains unresolved. Existing methods rely solely on frame-level embeddings, effectively describing object-based content but lacking contextual information across scenes. We introduce DANTE-AD, an enhanced video description model leveraging a dual-vision Transformer-based architecture to address this gap. DANTE-AD sequentially fuses both frame and scene level embeddings to improve long-term contextual understanding. We propose a novel, state-of-the-art method for sequential cross-attention to achieve contextual grounding for fine-grained audio description generation. Evaluated on a broad range of key scenes from well-known movie clips, DANTE-AD outperforms existing methods across traditional NLP metrics and LLM-based evaluations.

Related papers

• DistinctAD: Distinctive Audio Description Generation in Contexts [62.58375366359421]
  We propose DistinctAD, a framework for generating Audio Descriptions that emphasize distinctiveness to produce better narratives.<n>To address the domain gap, we introduce a CLIP-AD adaptation strategy that does not require additional AD corpora.<n>In Stage-II, DistinctAD incorporates two key innovations: (i) a Contextual Expectation-Maximization Attention (EMA) module that reduces redundancy by extracting common bases from consecutive video clips, and (ii) an explicit distinctive word prediction loss that filters out repeated words in the context.
  arXiv  Detail & Related papers  (2024-11-27T09:54:59Z)
• VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models [38.429386337415785]
  Contrastive Language-Image Pre-training (CLIP) has been widely studied and applied in numerous applications. The emphasis on brief summary texts during pre-training prevents CLIP from understanding long descriptions. We propose the VideoCLIP-XL (eXtra Length) model, which aims to unleash the long-description understanding capability of video CLIP models.
  arXiv  Detail & Related papers  (2024-10-01T14:33:22Z)
• MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrieval [53.417646562344906]
  Video Moment Retrieval (VMR) aims to localize a specific temporal segment within an untrimmed long video given a natural language query. Existing methods often suffer from inadequate training annotations, i.e., the sentence typically matches with a fraction of the prominent video content in the foreground with limited wording diversity. This intrinsic modality imbalance leaves a considerable portion of visual information remaining unaligned with text. In this work, we take an MLLM as a video narrator to generate plausible textual descriptions of the video, thereby mitigating the modality imbalance and boosting the temporal localization.
  arXiv  Detail & Related papers  (2024-06-25T18:39:43Z)
• Contextual AD Narration with Interleaved Multimodal Sequence [50.240534605090396]
  The task aims to generate descriptions of visual elements for visually impaired individuals to help them access long-form video content, like movies.<n>With video feature, text, character bank and context information as inputs, the generated ADs are able to correspond to the characters by name.<n>We propose to leverage pre-trained foundation models through a simple and unified framework to generate ADs.
  arXiv  Detail & Related papers  (2024-03-19T17:27:55Z)
• Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition [63.95111791861103]
  Existing methods typically adapt pretrained image-text models to the video domain. We argue that augmenting text embeddings with human prior knowledge is pivotal for open-vocabulary video action recognition. Our method not only sets new SOTA performance but also possesses excellent interpretability.
  arXiv  Detail & Related papers  (2023-12-04T02:31:38Z)
• 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)
• 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)

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.