CMTM: Cross-Modal Token Modulation for Unsupervised Video Object Segmentation

• URL: http://arxiv.org/abs/2604.14630v1
• Date: Thu, 16 Apr 2026 05:14:32 GMT
• Title: CMTM: Cross-Modal Token Modulation for Unsupervised Video Object Segmentation
• Abstract summary: We introduce cross-modality token modulation, a novel approach designed to strengthen the interaction between appearance and motion cues.<n>Our method establishes dense connections between tokens from each modality, enabling efficient intra-modal and inter-modal information propagation.<n>Our approach achieves state-of-the-art performance across all public benchmarks, outperforming existing methods.
• Score: 34.58388311597622
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in unsupervised video object segmentation have highlighted the potential of two-stream architectures that integrate appearance and motion cues. However, fully leveraging these complementary sources of information requires effectively modeling their interdependencies. In this paper, we introduce cross-modality token modulation, a novel approach designed to strengthen the interaction between appearance and motion cues. Our method establishes dense connections between tokens from each modality, enabling efficient intra-modal and inter-modal information propagation through relation transformer blocks. To improve learning efficiency, we incorporate a token masking strategy that addresses the limitations of relying solely on increased model complexity. Our approach achieves state-of-the-art performance across all public benchmarks, outperforming existing methods.

Related papers

• Modality-Agnostic Prompt Learning for Multi-Modal Camouflaged Object Detection [61.36976558603528]
  We propose a novel framework that generates modality-agnostic multi-modal prompts for the Segment Anything Model (SAM)<n>Specifically, we model multi-modal learning through interactions between a data-driven content domain and a knowledge-driven prompt domain.<n>We further introduce a lightweight Mask Refine Module to calibrate coarse predictions by incorporating fine-grained prompt cues.
  arXiv  Detail & Related papers  (2026-04-14T07:13:28Z)
• CrossWeaver: Cross-modal Weaving for Arbitrary-Modality Semantic Segmentation [2.9550741910325153]
  CrossWeaver is a simple yet effective framework for arbitrary-modality semantic segmentation.<n>Its core is a Modality Interaction Block (MIB), which enables selective and reliability-aware cross-modal interaction within the encoder.<n>Our framework achieves state-of-the-art performance with minimal additional parameters and strong generalization to unseen modality combinations.
  arXiv  Detail & Related papers  (2026-04-03T10:32:02Z)
• NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching [64.10695425442164]
  We introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms.<n>Trained on large-scale interleaved text, image, video, and audio data, NExT-OMNI delivers competitive performance on multimodal generation and understanding benchmarks.<n>To advance further research, we release training details, data protocols, and open-source both the code and model checkpoints.
  arXiv  Detail & Related papers  (2025-10-15T16:25:18Z)
• MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing [53.98607267063729]
  MotionVerse is a framework to comprehend, generate, and edit human motion in both single-person and multi-person scenarios.<n>We employ a motion tokenizer with residual quantization, which converts continuous motion sequences into multi-stream discrete tokens.<n>We also introduce a textitDelay Parallel Modeling strategy, which temporally staggers the encoding of residual token streams.
  arXiv  Detail & Related papers  (2025-09-28T04:20:56Z)
• HeLoFusion: An Efficient and Scalable Encoder for Modeling Heterogeneous and Multi-Scale Interactions in Trajectory Prediction [11.30785902722196]
  HeLoFusion is an efficient and scalable encoder for modeling heterogeneous and multi-scale agent interactions.<n>Our work demonstrates that a locality-grounded architecture, which explicitly models multi-scale and heterogeneous interactions, is a highly effective strategy for advancing motion forecasting.
  arXiv  Detail & Related papers  (2025-09-15T09:19:41Z)
• Co-AttenDWG: Co-Attentive Dimension-Wise Gating and Expert Fusion for Multi-Modal Offensive Content Detection [0.0]
  Multi-modal learning has emerged as a crucial research direction.<n>Existing approaches often suffer from insufficient cross-modal interactions and rigid fusion strategies.<n>We propose Co-AttenDWG, co-attention with dimension-wise gating, and expert fusion.<n>We show that Co-AttenDWG achieves state-of-the-art performance and superior cross-modal alignment.
  arXiv  Detail & Related papers  (2025-05-25T07:26:00Z)
• Learning Motion and Temporal Cues for Unsupervised Video Object Segmentation [49.113131249753714]
  We propose an efficient algorithm, termed MTNet, which concurrently exploits motion and temporal cues.<n> MTNet is devised by effectively merging appearance and motion features during the feature extraction process within encoders.<n>We employ a cascade of decoders all feature levels across all feature levels to optimally exploit the derived features.
  arXiv  Detail & Related papers  (2025-01-14T03:15:46Z)
• M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecture [6.928469290518152]
  We introduce the Joint-Embedding Predictive Architecture (JEPA) on the multimodal tasks.<n>It converts the input embedding into the output embedding space by a predictor and then conducts the cross-modal alignment on the latent space.<n>We show that M3-JEPA can obtain state-of-the-art performance on different modalities and tasks, generalize to unseen datasets and domains, and is computationally efficient in both training and inference.
  arXiv  Detail & Related papers  (2024-09-09T10:40:50Z)
• Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding [62.70450216120704]
  Unsupervised pre-training has shown great success in skeleton-based action understanding. We propose a Unified Multimodal Unsupervised Representation Learning framework, called UmURL. UmURL exploits an efficient early-fusion strategy to jointly encode the multi-modal features in a single-stream manner.
  arXiv  Detail & Related papers  (2023-11-06T13:56:57Z)
• Modeling long-term interactions to enhance action recognition [81.09859029964323]
  We propose a new approach to under-stand actions in egocentric videos that exploits the semantics of object interactions at both frame and temporal levels. We use a region-based approach that takes as input a primary region roughly corresponding to the user hands and a set of secondary regions potentially corresponding to the interacting objects. The proposed approach outperforms the state-of-the-art in terms of action recognition on standard benchmarks.
  arXiv  Detail & Related papers  (2021-04-23T10:08:15Z)

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.