Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation

• URL: http://arxiv.org/abs/2503.13068v1
• Date: Mon, 17 Mar 2025 11:19:03 GMT
• Title: Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation
• Authors: Henghui Du, Guangyao Li, Chang Zhou, Chunjie Zhang, Alan Zhao, Di Hu,
• Abstract summary: We propose a unified learning method which achieves explicit inter-task cooperation from both perspectives of data and model thoroughly.<n>Our method not only surpasses existing unified audio-visual model on multiple tasks, but also outperforms most specialized models for certain tasks.
• Score: 36.37023296057912
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, numerous tasks have been proposed to encourage model to develop specified capability in understanding audio-visual scene, primarily categorized into temporal localization, spatial localization, spatio-temporal reasoning, and pixel-level understanding. Instead, human possesses a unified understanding ability for diversified tasks. Therefore, designing an audio-visual model with general capability to unify these tasks is of great value. However, simply joint training for all tasks can lead to interference due to the heterogeneity of audiovisual data and complex relationship among tasks. We argue that this problem can be solved through explicit cooperation among tasks. To achieve this goal, we propose a unified learning method which achieves explicit inter-task cooperation from both the perspectives of data and model thoroughly. Specifically, considering the labels of existing datasets are simple words, we carefully refine these datasets and construct an Audio-Visual Unified Instruction-tuning dataset with Explicit reasoning process (AV-UIE), which clarifies the cooperative relationship among tasks. Subsequently, to facilitate concrete cooperation in learning stage, an interaction-aware LoRA structure with multiple LoRA heads is designed to learn different aspects of audiovisual data interaction. By unifying the explicit cooperation across the data and model aspect, our method not only surpasses existing unified audio-visual model on multiple tasks, but also outperforms most specialized models for certain tasks. Furthermore, we also visualize the process of explicit cooperation and surprisingly find that each LoRA head has certain audio-visual understanding ability. Code and dataset: https://github.com/GeWu-Lab/Crab

Related papers

• Crab$^{+}$: A Scalable and Unified Audio-Visual Scene Understanding Model with Explicit Cooperation [83.75249714794977]
  We present Crab$+$, a scalable and unified audio-visual scene understanding model.<n>On the data side, we introduce AV-UIE v2, a comprehensive Audio-Visual Unified Instruction-tuning dataset.<n>On the model side, we design a unified interface to align heterogeneous task formulations.<n>We successfully reverse the negative transfer trend, achieving positive transfer where multi-task learning surpasses single-task baselines in nearly 88% of tasks.
  arXiv  Detail & Related papers  (2026-03-04T14:43:57Z)
• Tracking and Segmenting Anything in Any Modality [75.32774085793498]
  We propose a universal tracking and segmentation framework named SATA, which unifies a broad spectrum of tracking and segmentation subtasks with any modality input.<n> SATA demonstrates superior performance on 18 challenging tracking and segmentation benchmarks, offering a novel perspective for more generalizable video understanding.
  arXiv  Detail & Related papers  (2025-11-22T09:09:22Z)
• Contextualized Representation Learning for Effective Human-Object Interaction Detection [17.242400169885453]
  Human-Object Interaction (HOI) detection aims to simultaneously localize human-object pairs and recognize their interactions.<n>We introduce a Contextualized Representation Learning that integrates both affordance-guided reasoning and contextual prompts.<n>Our proposed method demonstrates superior performance on both the HICO-Det and V-COCO datasets in most scenarios.
  arXiv  Detail & Related papers  (2025-09-16T08:03:16Z)
• Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning [23.22385310060951]
  We introduce a three-stage Progressive Homeostatic and Plastic audio-visual prompt (PHP) method.<n>In the shallow phase, we design the task-shared modality aggregating adapter to foster cross-task and cross-modal audio-visual representation learning.<n>In the middle phase, we propose the task-specific modality-shared dynamic generating adapter, which constructs prompts that are tailored to individual tasks.<n>In the deep phase, we introduce the task-specific modality-independent prompts to further refine the understand ability.
  arXiv  Detail & Related papers  (2025-07-29T08:42:36Z)
• Is Visual in-Context Learning for Compositional Medical Tasks within Reach? [68.56630652862293]
  In this paper, we explore the potential of visual in-context learning to enable a single model to handle multiple tasks.<n>We introduce a novel method for training in-context learners using a synthetic compositional task generation engine.
  arXiv  Detail & Related papers  (2025-07-01T15:32:23Z)
• A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning [6.595840767689357]
  Audio-visual correlation learning aims to capture and understand natural phenomena between audio and visual data. The rapid growth of Deep Learning propelled the development of proposals that process audio-visual data. We provide a summarization of the recent progress of Audio-Visual Correlation Learning and discuss the future research directions.
  arXiv  Detail & Related papers  (2024-11-24T03:26:34Z)
• WavLLM: Towards Robust and Adaptive Speech Large Language Model [93.0773293897888]
  We introduce WavLLM, a robust and adaptive speech large language model with dual encoders, and a prompt-aware LoRA weight adapter. We validate the proposed model on universal speech benchmarks including tasks such as ASR, ST, SV, ER, and also apply it to specialized datasets like Gaokao English listening comprehension set for SQA, and speech Chain-of-Thought (CoT) evaluation set.
  arXiv  Detail & Related papers  (2024-03-31T12:01:32Z)
• LLMBind: A Unified Modality-Task Integration Framework [38.95771765322677]
  We introduce textbfLLMBind, a novel framework designed to unify a diverse array of multi-modal tasks. By harnessing a Mixture-of-Experts (MoE) Large Language Model (LLM), LLMBind processes multi-modal inputs and generates task-specific tokens, enabling the invocation of corresponding models to accomplish tasks.
  arXiv  Detail & Related papers  (2024-02-22T12:36:31Z)
• Musketeer: Joint Training for Multi-task Vision Language Model with Task Explanation Prompts [75.75548749888029]
  We present a vision-language model whose parameters are jointly trained on all tasks and fully shared among multiple heterogeneous tasks. With a single model, Musketeer achieves results comparable to or better than strong baselines trained on single tasks, almost uniformly across multiple tasks.
  arXiv  Detail & Related papers  (2023-05-11T17:57:49Z)
• Identifying Auxiliary or Adversarial Tasks Using Necessary Condition Analysis for Adversarial Multi-task Video Understanding [34.75145779372538]
  We propose a generalized notion of multi-task learning by incorporating both auxiliary tasks that the model should perform well on and adversarial tasks that the model should not perform well on. Our novel proposed framework, Adversarial Multi-Task Neural Networks (AMT), penalizes adversarial tasks, determined by NCA to be scene recognition. We show that our approach improves accuracy by 3% and encourages the model to attend to action features instead of correlation-biasing scene features.
  arXiv  Detail & Related papers  (2022-08-22T06:26:11Z)
• Look\&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement [18.488808141923492]
  ADENet is proposed to achieve target speaker detection and speech enhancement with joint learning of audio-visual modeling. Cross-modal relationship between auditory and visual stream is a promising solution for the challenge of audio-visual multi-task learning.
  arXiv  Detail & Related papers  (2022-03-04T09:53:19Z)
• Audio-Visual Fusion Layers for Event Type Aware Video Recognition [86.22811405685681]
  We propose a new model to address the multisensory integration problem with individual event-specific layers in a multi-task learning scheme. We show that our network is formulated with single labels, but it can output additional true multi-labels to represent the given videos.
  arXiv  Detail & Related papers  (2022-02-12T02:56:22Z)
• Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation [97.17517060585875]
  We present a unified approach to visual navigation using a novel modular transfer learning model. Our model can effectively leverage its experience from one source task and apply it to multiple target tasks. Our approach learns faster, generalizes better, and outperforms SoTA models by a significant margin.
  arXiv  Detail & Related papers  (2022-02-05T00:07:21Z)
• Distilling Audio-Visual Knowledge by Compositional Contrastive Learning [51.20935362463473]
  We learn a compositional embedding that closes the cross-modal semantic gap. We establish a new, comprehensive multi-modal distillation benchmark on three video datasets.
  arXiv  Detail & Related papers  (2021-04-22T09:31:20Z)
• Taskology: Utilizing Task Relations at Scale [28.09712466727001]
  We show that we can leverage the inherent relationships among collections of tasks, as they are trained jointly. explicitly utilizing the relationships between tasks allows improving their performance while dramatically reducing the need for labeled data. We demonstrate our framework on subsets of the following collection of tasks: depth and normal prediction, semantic segmentation, 3D motion and ego-motion estimation, and object tracking and 3D detection in point clouds.
  arXiv  Detail & Related papers  (2020-05-14T22:53:46Z)

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.