Align and Adapt: Multimodal Multiview Human Activity Recognition under Arbitrary View Combinations

• URL: http://arxiv.org/abs/2602.08755v3
• Date: Wed, 18 Feb 2026 16:47:35 GMT
• Title: Align and Adapt: Multimodal Multiview Human Activity Recognition under Arbitrary View Combinations
• Abstract summary: AliAd is a model that combines multiview contrastive learning with a mixture-of-experts module to support arbitrary view availability during both training and inference.<n>AliAd is validated on four datasets encompassing inertial and human pose modalities, with the number of views ranging from three to nine, demonstrating its performance and flexibility.
• Score: 5.37133760455631
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Multimodal multiview learning seeks to integrate information from diverse sources to enhance task performance. Existing approaches often struggle with flexible view configurations, including arbitrary view combinations, numbers of views, and heterogeneous modalities. Focusing on the context of human activity recognition, we propose AliAd, a model that combines multiview contrastive learning with a mixture-of-experts module to support arbitrary view availability during both training and inference. Instead of trying to reconstruct missing views, an adjusted center contrastive loss is used for self-supervised representation learning and view alignment, mitigating the impact of missing views on multiview fusion. This loss formulation allows for the integration of view weights to account for view quality. Additionally, it reduces computational complexity from $O(V^2)$ to $O(V)$, where $V$ is the number of views. To address residual discrepancies not captured by contrastive learning, we employ a mixture-of-experts module with a specialized load balancing strategy, tasked with adapting to arbitrary view combinations. We highlight the geometric relationship among components in our model and how they combine well in the latent space. AliAd is validated on four datasets encompassing inertial and human pose modalities, with the number of views ranging from three to nine, demonstrating its performance and flexibility.

Related papers

• Multi-View Factorizing and Disentangling: A Novel Framework for Incomplete Multi-View Multi-Label Classification [9.905528765058541]
  We propose a novel framework for incomplete multi-view multi-label classification (iMvMLC)<n>Our method factorizes multi-view representations into two independent sets of factors: view-consistent and view-specific.<n>Our framework innovatively decomposes consistent representation learning into three key sub-objectives.
  arXiv  Detail & Related papers  (2025-01-11T12:19:20Z)
• Balanced Multi-view Clustering [56.17836963920012]
  Multi-view clustering (MvC) aims to integrate information from different views to enhance the capability of the model in capturing the underlying data structures.<n>The widely used joint training paradigm in MvC is potentially not fully leverage the multi-view information.<n>We propose a novel balanced multi-view clustering (BMvC) method, which introduces a view-specific contrastive regularization (VCR) to modulate the optimization of each view.
  arXiv  Detail & Related papers  (2025-01-05T14:42:47Z)
• Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition [23.031934558964473]
  We propose Semantics-based Unpaired Multiview Learning (SUM-L) to tackle this unpaired multiview learning problem. Key idea is to build cross-view pseudo-pairs and do view-invariant alignment by leveraging the semantic information of videos. Our method also outperforms multiple existing view-alignment methods, under the more challenging scenario.
  arXiv  Detail & Related papers  (2023-08-22T15:10:42Z)
• M$^3$Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition [80.21796574234287]
  M$3$Net is a matching-based framework for few-shot fine-grained (FS-FG) action recognition. It incorporates textitmulti-view encoding, textitmulti-view matching, and textitmulti-view fusion to facilitate embedding encoding, similarity matching, and decision making. Explainable visualizations and experimental results demonstrate the superiority of M$3$Net in capturing fine-grained action details.
  arXiv  Detail & Related papers  (2023-08-06T09:15:14Z)
• An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training [79.78201886156513]
  We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently. Our approach achieves comparable results to single-task state-of-the-art models and demonstrates strong generalization on downstream tasks.
  arXiv  Detail & Related papers  (2023-06-29T17:59:57Z)
• Cross-view Graph Contrastive Representation Learning on Partially Aligned Multi-view Data [52.491074276133325]
  Multi-view representation learning has developed rapidly over the past decades and has been applied in many fields. We propose a new cross-view graph contrastive learning framework, which integrates multi-view information to align data and learn latent representations. Experiments conducted on several real datasets demonstrate the effectiveness of the proposed method on the clustering and classification tasks.
  arXiv  Detail & Related papers  (2022-11-08T09:19:32Z)
• MORI-RAN: Multi-view Robust Representation Learning via Hybrid Contrastive Fusion [4.36488705757229]
  Multi-view representation learning is essential for many multi-view tasks, such as clustering and classification. We propose a hybrid contrastive fusion algorithm to extract robust view-common representation from unlabeled data. Experimental results demonstrated that the proposed method outperforms 12 competitive multi-view methods on four real-world datasets.
  arXiv  Detail & Related papers  (2022-08-26T09:58:37Z)
• V3H: View Variation and View Heredity for Incomplete Multi-view Clustering [65.29597317608844]
  Incomplete multi-view clustering is an effective method to integrate these incomplete views. We propose a novel View Variation and View Heredity approach (V3H) to overcome this limitation. V3H presents possibly the first work to introduce genetics to clustering algorithms for learning simultaneously the consistent information and the unique information from incomplete multi-view data.
  arXiv  Detail & Related papers  (2020-11-23T03:24:48Z)
• Deep Partial Multi-View Learning [94.39367390062831]
  We propose a novel framework termed Cross Partial Multi-View Networks (CPM-Nets) We fifirst provide a formal defifinition of completeness and versatility for multi-view representation. We then theoretically prove the versatility of the learned latent representations.
  arXiv  Detail & Related papers  (2020-11-12T02:29:29Z)
• Multi-view Low-rank Preserving Embedding: A Novel Method for Multi-view Representation [11.91574721055601]
  This paper proposes a novel multi-view learning method, named Multi-view Low-rank Preserving Embedding (MvLPE) It integrates different views into one centroid view by minimizing the disagreement term, based on distance or similarity matrix among instances. Experiments on six benchmark datasets demonstrate that the proposed method outperforms its counterparts.
  arXiv  Detail & Related papers  (2020-06-14T12:47:25Z)
• Generalized Multi-view Shared Subspace Learning using View Bootstrapping [43.027427742165095]
  Key objective in multi-view learning is to model the information common to multiple parallel views of a class of objects/events to improve downstream learning tasks. We present a neural method based on multi-view correlation to capture the information shared across a large number of views by subsampling them in a view-agnostic manner during training. Experiments on spoken word recognition, 3D object classification and pose-invariant face recognition demonstrate the robustness of view bootstrapping to model a large number of views.
  arXiv  Detail & Related papers  (2020-05-12T20:35:14Z)

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.