Watch and Listen: Understanding Audio-Visual-Speech Moments with Multimodal LLM

• URL: http://arxiv.org/abs/2505.18110v2
• Date: Fri, 20 Jun 2025 16:28:03 GMT
• Title: Watch and Listen: Understanding Audio-Visual-Speech Moments with Multimodal LLM
• Authors: Zinuo Li, Xian Zhang, Yongxin Guo, Mohammed Bennamoun, Farid Boussaid, Girish Dwivedi, Luqi Gong, Qiuhong Ke,
• Abstract summary: TriSense is a triple-modality large language model designed for holistic video temporal understanding.<n>Central to TriSense is a Query-Based Connector that adaptively reweights modality contributions based on the input query.<n>TriSense-2M is a dataset of over 2 million curated samples generated via an automated pipeline.
• Score: 32.06547791451391
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Humans naturally understand moments in a video by integrating visual and auditory cues. For example, localizing a scene in the video like "A scientist passionately speaks on wildlife conservation as dramatic orchestral music plays, with the audience nodding and applauding" requires simultaneous processing of visual, audio, and speech signals. However, existing models often struggle to effectively fuse and interpret audio information, limiting their capacity for comprehensive video temporal understanding. To address this, we present TriSense, a triple-modality large language model designed for holistic video temporal understanding through the integration of visual, audio, and speech modalities. Central to TriSense is a Query-Based Connector that adaptively reweights modality contributions based on the input query, enabling robust performance under modality dropout and allowing flexible combinations of available inputs. To support TriSense's multimodal capabilities, we introduce TriSense-2M, a high-quality dataset of over 2 million curated samples generated via an automated pipeline powered by fine-tuned LLMs. TriSense-2M includes long-form videos and diverse modality combinations, facilitating broad generalization. Extensive experiments across multiple benchmarks demonstrate the effectiveness of TriSense and its potential to advance multimodal video analysis. Code and dataset will be publicly released.

Related papers

• CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval [70.9990850395981]
  We introduce CLaMR, a multimodal, late-interaction retriever that jointly indexes 4 modalities: video frames, transcribed speech, on-screen text, and metadata.<n>CLaMR is trained to enhance dynamic modality selection via two key innovations.
  arXiv  Detail & Related papers  (2025-06-06T15:02:30Z)
• MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions [69.9122231800796]
  We present MMTrail, a large-scale multi-modality video-language dataset incorporating more than 20M trailer clips with visual captions.<n>We propose a systemic captioning framework, achieving various modality annotations with more than 27.1k hours of trailer videos.<n>Our dataset potentially paves the path for fine-grained large multimodal-language model training.
  arXiv  Detail & Related papers  (2024-07-30T16:43:24Z)
• Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time [73.7845280328535]
  We present Meerkat, an audio-visual LLM equipped with a fine-grained understanding of image and audio. Meerkat can tackle challenging tasks such as audio referred image grounding, image guided audio temporal localization, and audio-visual fact-checking. We achieve state-of-the-art performance on all these downstream tasks with a relative improvement of up to 37.12%.
  arXiv  Detail & Related papers  (2024-07-01T23:32:25Z)
• SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos [77.55518265996312]
  We propose a novel self-supervised embedding to learn how actions sound from narrated in-the-wild egocentric videos. Our multimodal contrastive-consensus coding (MC3) embedding reinforces the associations between audio, language, and vision when all modality pairs agree.
  arXiv  Detail & Related papers  (2024-04-08T05:19:28Z)
• AudioVisual Video Summarization [103.47766795086206]
  In video summarization, existing approaches just exploit the visual information while neglecting the audio information. We propose to jointly exploit the audio and visual information for the video summarization task, and develop an AudioVisual Recurrent Network (AVRN) to achieve this.
  arXiv  Detail & Related papers  (2021-05-17T08:36:10Z)
• Self-Supervised MultiModal Versatile Networks [76.19886740072808]
  We learn representations using self-supervision by leveraging three modalities naturally present in videos: visual, audio and language streams. We demonstrate how such networks trained on large collections of unlabelled video data can be applied on video, video-text, image and audio tasks.
  arXiv  Detail & Related papers  (2020-06-29T17:50:23Z)
• Deep Multimodal Feature Encoding for Video Ordering [34.27175264084648]
  We present a way to learn a compact multimodal feature representation that encodes all these modalities. Our model parameters are learned through a proxy task of inferring the temporal ordering of a set of unordered videos in a timeline. We analyze and evaluate the individual and joint modalities on three challenging tasks: (i) inferring the temporal ordering of a set of videos; and (ii) action recognition.
  arXiv  Detail & Related papers  (2020-04-05T14:02:23Z)

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.