Hierarchical Semantic Correlation-Aware Masked Autoencoder for Unsupervised Audio-Visual Representation Learning

• URL: http://arxiv.org/abs/2604.04229v1
• Date: Sun, 05 Apr 2026 19:08:51 GMT
• Title: Hierarchical Semantic Correlation-Aware Masked Autoencoder for Unsupervised Audio-Visual Representation Learning
• Abstract summary: We propose a dual-path teacher-student framework that enforces semantic consistency across three complementary levels of representation.<n> Experiments on AVE and VEGAS demonstrate substantial mAP improvements over strong unsupervised baselines.
• Score: 3.055416693231887
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Learning aligned multimodal embeddings from weakly paired, label-free corpora is challenging: pipelines often provide only pre-extracted features, clips contain multiple events, and spurious co-occurrences. We propose HSC-MAE (Hierarchical Semantic Correlation-Aware Masked Autoencoder), a dual-path teacher-student framework that enforces semantic consistency across three complementary levels of representation - from coarse to fine: (i) global-level canonical-geometry correlation via DCCA, which aligns audio and visual embeddings within a shared modality-invariant subspace; (ii) local-level neighborhood-semantics correlation via teacher-mined soft top-k affinities, which preserves multi-positive relational structure among semantically similar instances; and (iii) sample-level conditional-sufficiency correlation via masked autoencoding, which ensures individual embeddings retain discriminative semantic content under partial observation. Concretely, a student MAE path is trained with masked feature reconstruction and affinity-weighted soft top-k InfoNCE; an EMA teacher operating on unmasked inputs via the CCA path supplies stable canonical geometry and soft positives. Learnable multi-task weights reconcile competing objectives, and an optional distillation loss transfers teacher geometry into the student. Experiments on AVE and VEGAS demonstrate substantial mAP improvements over strong unsupervised baselines, validating that HSC-MAE yields robust and well-structured audio-visual representations.

Related papers

• Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System [90.64481646805855]
  unified multimodal models (UMMs) jointly perform visual understanding and generation within a single model.<n>We investigate their relationship at the representation, task, and system levels in a controlled, structurally native setting.<n>We show that the value of UMMs extends beyond a unified interface: appropriate specialization, shared task knowledge, and end-to-end optimization can turn coexistence into synergy.
  arXiv  Detail & Related papers  (2026-09-01T17:59:59Z)
• Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning [14.508049757681862]
  LLM-powered coding agents spend the majority of their token budget reading repository files.<n>We show that this formulation creates a modeling bottleneck.<n>We propose LaMR, a structured pruning framework that decomposes code relevance into two interpretable quality dimensions.
  arXiv  Detail & Related papers  (2026-05-14T18:30:10Z)
• Bidirectional Learning of Facial Action Units and Expressions via Structured Semantic Mapping across Heterogeneous Datasets [85.74213192818668]
  We propose a Structured Semantic Mapping (SSM) framework for bidirectional AU--FE learning under different data domains and heterogeneous supervision.<n>SSM consists of three key components: (1) a shared visual backbone that learns unified facial representations from dynamic AU and FE videos; (2) semantic mediation via a Textual Semantic Prototype (TSP) module; and (3) a Dynamic Prior Mapping (DPM) module that incorporates prior knowledge derived from the Facial Action Coding System.
  arXiv  Detail & Related papers  (2026-04-12T09:08:32Z)
• PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation [58.1914505657064]
  This paper proposes a simple yet effective parallel cost aggregation (PCA-Seg) paradigm to alleviate the challenge of knowledge interference between class-level semantics and spatial context.<n>Experiments on eight benchmarks show that each parallel block in PCA-Seg adds merely 0.35M parameters while achieving state-of-the-art OSPS performance.
  arXiv  Detail & Related papers  (2026-03-18T09:26:43Z)
• CurConMix+: A Unified Spatio-Temporal Framework for Hierarchical Surgical Workflow Understanding [1.0692208281858493]
  Surgical action triplet recognition aims to understand fine surgical behaviors by modeling interactions among instruments, actions, and anatomical targets.<n>Despite its clinical importance for workflow analysis and skill assessment, progress has been hindered by severe class imbalance, subtle visual variations, and the interdependence among triplet components.<n>This study builds upon CurConMix, a spatial representation framework, to address these challenges.
  arXiv  Detail & Related papers  (2026-01-18T08:42:10Z)
• Multi-label Classification with Panoptic Context Aggregation Networks [61.82285737410154]
  This paper introduces the Deep Panoptic Context Aggregation Network (PanCAN), a novel approach that hierarchically integrates multi-order geometric contexts.<n>PanCAN learns multi-order neighborhood relationships at each scale by combining random walks with an attention mechanism.<n>Experiments on NUS-WIDE, PASCAL VOC,2007, and MS-COCO benchmarks demonstrate that PanCAN consistently achieves competitive results.
  arXiv  Detail & Related papers  (2025-12-29T14:16:21Z)
• SG-XDEAT: Sparsity-Guided Cross-Dimensional and Cross-Encoding Attention with Target-Aware Conditioning in Tabular Learning [0.0]
  We propose SG-XDEAT, a novel framework for supervised learning on tabular data.<n>At its core, SG-XDEAT employs a dual-stream encoder that decomposes each input feature into two parallel representations.<n>These dual representations are then propagated through a hierarchical stack of attention-based modules.
  arXiv  Detail & Related papers  (2025-10-14T15:56:40Z)
• TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised Learning [15.638836465479619]
  TRiCo is a novel triadic game-theoretic co-training framework that rethinks the structure of semi-supervised learning.<n>By addressing key limitations in existing SSL frameworks, TRiCo provides a principled and generalizable solution.
  arXiv  Detail & Related papers  (2025-09-25T20:10:41Z)
• A Generalized Learning Framework for Self-Supervised Contrastive Learning [9.01200351672698]
  Self-supervised contrastive learning (SSCL) has recently demonstrated superiority in multiple downstream tasks.<n>We generalize the standard SSCL methods to a Generalized Learning Framework (GLF) consisting of two parts: the aligning part and the constraining part.
  arXiv  Detail & Related papers  (2025-08-19T08:00:29Z)
• MoSAiC: Multi-Modal Multi-Label Supervision-Aware Contrastive Learning for Remote Sensing [10.207026975603503]
  We introduce MoSAiC, a unified framework that jointly optimize intra- and inter-modality contrastive learning with a multi-label supervised contrastive loss.<n>MoSAiC consistently outperforms both fully supervised and self-supervised baselines in terms of accuracy, cluster coherence, and generalization.
  arXiv  Detail & Related papers  (2025-07-11T15:33:51Z)
• Semantic-Aligned Learning with Collaborative Refinement for Unsupervised VI-ReID [82.12123628480371]
  Unsupervised person re-identification (USL-VI-ReID) seeks to match pedestrian images of the same individual across different modalities without human annotations for model learning.<n>Previous methods unify pseudo-labels of cross-modality images through label association algorithms and then design contrastive learning framework for global feature learning.<n>We propose a Semantic-Aligned Learning with Collaborative Refinement (SALCR) framework, which builds up objective for specific fine-grained patterns emphasized by each modality.
  arXiv  Detail & Related papers  (2025-04-27T13:58:12Z)
• Connecting Multi-modal Contrastive Representations [50.26161419616139]
  Multi-modal Contrastive Representation learning aims to encode different modalities into a semantically shared space. This paper proposes a novel training-efficient method for learning MCR without paired data called Connecting Multi-modal Contrastive Representations (C-MCR) C-MCR achieves audio-visual state-of-the-art performance on audio-image retrieval, audio-visual source localization, and counterfactual audio-image recognition tasks.
  arXiv  Detail & Related papers  (2023-05-22T09:44:39Z)
• Dense Contrastive Visual-Linguistic Pretraining [53.61233531733243]
  Several multimodal representation learning approaches have been proposed that jointly represent image and text. These approaches achieve superior performance by capturing high-level semantic information from large-scale multimodal pretraining. We propose unbiased Dense Contrastive Visual-Linguistic Pretraining to replace the region regression and classification with cross-modality region contrastive learning.
  arXiv  Detail & Related papers  (2021-09-24T07:20:13Z)

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.