GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection

• URL: http://arxiv.org/abs/2512.15707v1
• Date: Wed, 17 Dec 2025 18:56:52 GMT
• Title: GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection
• Abstract summary: GateFusion is a novel architecture that combines strong pretrained unimodal encoders with a Hierarchical Gated Fusion Decoder (HiGate)<n>HiGate enables progressive, multi-depth fusion by adaptively injecting contextual features from one modality into the other at multiple layers of the Transformer backbone.
• Score: 19.80016468034245
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Active Speaker Detection (ASD) aims to identify who is currently speaking in each frame of a video. Most state-of-the-art approaches rely on late fusion to combine visual and audio features, but late fusion often fails to capture fine-grained cross-modal interactions, which can be critical for robust performance in unconstrained scenarios. In this paper, we introduce GateFusion, a novel architecture that combines strong pretrained unimodal encoders with a Hierarchical Gated Fusion Decoder (HiGate). HiGate enables progressive, multi-depth fusion by adaptively injecting contextual features from one modality into the other at multiple layers of the Transformer backbone, guided by learnable, bimodally-conditioned gates. To further strengthen multimodal learning, we propose two auxiliary objectives: Masked Alignment Loss (MAL) to align unimodal outputs with multimodal predictions, and Over-Positive Penalty (OPP) to suppress spurious video-only activations. GateFusion establishes new state-of-the-art results on several challenging ASD benchmarks, achieving 77.8% mAP (+9.4%), 86.1% mAP (+2.9%), and 96.1% mAP (+0.5%) on Ego4D-ASD, UniTalk, and WASD benchmarks, respectively, and delivering competitive performance on AVA-ActiveSpeaker. Out-of-domain experiments demonstrate the generalization of our model, while comprehensive ablations show the complementary benefits of each component.

Related papers

• More Perspectives, Stronger Signals: Multi-Perspective Enhancement and Progressive Fusion for Multimodal Entity Representation Learning [6.4639268448773946]
  We propose PrismF, a unified framework that synergizes multi-perspective enhancement with progressive fusion to extract stronger signals from diverse inputs.<n>PrismF enhances fine-grained intra-modal semantics through a multi-perspective mechanism that decomposes each modality into complementary views.<n>Experiments show that PrismF achieves the strongest overall performance, including relative improvements of 4.04% in MRR and 11.17% in Hits@1 on KVC16K.
  arXiv  Detail & Related papers  (2026-08-29T08:29:43Z)
• Multimodal Ambivalence and Hesitancy Recognition via Cross-Attention and Gated Fusion [1.6950215926321557]
  We present a framework for Ambivalence/Hesitancy (A/H) recognition in video, developed for the ABAW11 challenge at ECCV 2026.<n>The proposed approach fuses textual, acoustic, and visual modalities extracted from the BAH dataset.<n>This model achieves a Macro F1 of textbf0.7394 on the validation set, a relative improvement of 11.0% over the best unimodal baseline.
  arXiv  Detail & Related papers  (2026-07-17T09:23:36Z)
• Team RAS in 11th ABAW Competition: Multimodal Ambivalence Recognition Approach [52.92973028971813]
  We present a single text-centered multimodal approach for video-level ambivalence and hesitancy recognition.<n>The proposed approach combines linguistic, acoustic, facial, and scene features using text-centered multimodal fusion model.<n>Experiments on the Behavioural Ambivalence/Hesitancy (BAH) corpus confirm that text is the strongest unimodal modality.
  arXiv  Detail & Related papers  (2026-07-16T08:04:23Z)
• Not All Modalities Are Equal: Instruction-Aware Gating for Multimodal Videos [70.78278988781882]
  We present a unified multimodal video understanding framework, named UniMVU, that performs instruction-aware fusion across video, audio, depth map, or any other modality inputs.<n>Our analysis shows that the gating mechanism aligns with the human-interpretable modality relevance, and ablations show the contributions of inner-modality and modality-level gating.
  arXiv  Detail & Related papers  (2026-05-25T18:02:20Z)
• Team LEYA in 10th ABAW Competition: Multimodal Ambivalence/Hesitancy Recognition Approach [43.09390014734485]
  This paper presents a multimodal approach for ambivalence/hesitancy recognition in unconstrained videos.<n>The proposed approach integrates four complementary modalities: scene, face, audio, and text.<n>Experiments on the BAH corpus demonstrate clear gains of multimodal fusion over all unimodal baselines.
  arXiv  Detail & Related papers  (2026-03-13T09:50:03Z)
• Complementarity-Supervised Spectral-Band Routing for Multimodal Emotion Recognition [60.20529806857076]
  Multimodal emotion recognition fuses cues such as text, video, and audio to understand individual emotional states.<n>Prior methods face two main limitations: mechanically relying on independent unimodal performance, and coarse-grained fusion conflicting with the fine-grained representations required by emotion tasks.<n>We propose the Complementarity-Supervised Multi-Band Expert Network, named Atsuko, to model fine-grained complementary features via multi-scale band decomposition and expert collaboration.
  arXiv  Detail & Related papers  (2026-03-07T03:58:48Z)
• PRISM: Performer RS-IMLE for Single-pass Multisensory Imitation Learning [51.24484551729328]
  We introduce PRISM, a single-pass policy based on a batch-global rejection-sampling variant of IMLE.<n> PRISM couples a temporal multisensory encoder with a linear-attention generator using a Performer architecture.<n>We demonstrate the efficacy of PRISM on a diverse real-world hardware suite, including loco-manipulation using a Unitree Go2 with a 7-DoF arm D1 and tabletop manipulation with a UR5 manipulator.
  arXiv  Detail & Related papers  (2026-02-02T17:57:37Z)
• Revealing the Truth with ConLLM for Detecting Multi-Modal Deepfakes [16.165111143799617]
  ConLLM is a hybrid framework for robust multimodal deepfake detection.<n>It reduces audio deepfake EER by up to 50%, improves video accuracy by up to 8%, and achieves approximately 9% accuracy gains in audio-visual tasks.
  arXiv  Detail & Related papers  (2026-01-24T17:07:51Z)
• Pyramidal Adaptive Cross-Gating for Multimodal Detection [0.0]
  PACGNet is an architecture designed to perform deep fusion within the backbone.<n>The P module reconstructs the feature hierarchy via a progressive hierarchical gating mechanism.<n>Our PACGNet sets a new state-of-the-art benchmark, with mAP50 scores reaching 81.7% and 82.1% respectively.
  arXiv  Detail & Related papers  (2025-12-20T09:32:18Z)
• Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model [62.889356203346985]
  We propose DUal-STream diffusion (DUST), a world-model augmented VLA framework that handles the modality conflict.<n>DUST achieves up to 6% gains over a standard VLA baseline and implicit world-modeling methods.<n>On real-world tasks with the Franka Research 3, DUST outperforms baselines in success rate by 13%.
  arXiv  Detail & Related papers  (2025-10-31T16:32:12Z)
• Pay More Attention To Audio: Mitigating Imbalance of Cross-Modal Attention in Large Audio Language Models [60.857389526958485]
  MATA is a training-free method that dynamically pushes LALMs to pay textbfMore textbfAttention textbfTo textbfAudio tokens within the self-attention mechanism.<n>Experiments on the MMAU and MMAR benchmarks confirm MATA's effectiveness, with consistent performance gains.
  arXiv  Detail & Related papers  (2025-09-23T09:02:15Z)
• MVCL-DAF++: Enhancing Multimodal Intent Recognition via Prototype-Aware Contrastive Alignment and Coarse-to-Fine Dynamic Attention Fusion [13.589965279250185]
  We propose MVCL-DAF++, which extends MVCL-DAF with two key modules.<n>On MIntRec and MIntRec2.0, MVCL-DAF++ achieves new state-of-the-art results, improving rare-class recognition by +1.05% and +4.18% WF1, respectively.
  arXiv  Detail & Related papers  (2025-09-22T07:38:53Z)
• Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion [2.403252956256118]
  This study examines the effectiveness of Mel-Frequency Cepstral Coefficients (MFCCs) and pre-trained model (PTM) features, including wav2vec 2.0, HuBERT, WavLM, UniSpeech, MMS, and Whisper.<n>We propose FusionVAD, a unified framework that combines both feature types using three fusion strategies: concatenation, addition, and cross-attention.
  arXiv  Detail & Related papers  (2025-06-02T06:47:42Z)
• Baichuan-Omni-1.5 Technical Report [78.49101296394218]
  Baichuan- Omni-1.5 is an omni-modal model that not only has omni-modal understanding capabilities but also provides end-to-end audio generation capabilities.<n>We establish a comprehensive data cleaning and synthesis pipeline for multimodal data, obtaining about 500B high-quality data.<n>Second, an audio-tokenizer has been designed to capture both semantic and acoustic information from audio, enabling seamless integration and enhanced compatibility with MLLM.
  arXiv  Detail & Related papers  (2025-01-26T02:19:03Z)
• Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition [48.84506301960988]
  Cued Speech (CS) is a pure visual coding method used by hearing-impaired people. automatic CS recognition (ACSR) seeks to transcribe visual cues of speech into text.
  arXiv  Detail & Related papers  (2024-01-31T05:20:29Z)
• TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored Models [18.485290653242853]
  We present a Multimodal Backdoor Defense technique TIJO (Trigger Inversion using Joint Optimization) Recent work arXiv:2112.07668 has demonstrated successful backdoor attacks on multimodal models for the Visual Question Answering task. We propose TIJO that defends against dual-key attacks through a joint optimization that reverse-engineers the trigger in both the image and text modalities.
  arXiv  Detail & Related papers  (2023-08-07T20:48:07Z)
• Object Segmentation by Mining Cross-Modal Semantics [68.88086621181628]
  We propose a novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features. Specifically, we propose a novel network, termed XMSNet, consisting of (1) all-round attentive fusion (AF), (2) coarse-to-fine decoder (CFD), and (3) cross-layer self-supervision.
  arXiv  Detail & Related papers  (2023-05-17T14:30:11Z)
• A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition [46.443866373546726]
  We focus on dimensional emotion recognition based on the fusion of facial and vocal modalities extracted from videos. We propose a joint cross-attention model that relies on the complementary relationships to extract the salient features. Our proposed A-V fusion model provides a cost-effective solution that can outperform state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-03-28T14:09:43Z)
• Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis [96.46952672172021]
  Bi-Bimodal Fusion Network (BBFN) is a novel end-to-end network that performs fusion on pairwise modality representations. Model takes two bimodal pairs as input due to known information imbalance among modalities.
  arXiv  Detail & Related papers  (2021-07-28T23:33:42Z)
• Attention Bottlenecks for Multimodal Fusion [90.75885715478054]
  Machine perception models are typically modality-specific and optimised for unimodal benchmarks. We introduce a novel transformer based architecture that uses fusion' for modality fusion at multiple layers. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple audio-visual classification benchmarks.
  arXiv  Detail & Related papers  (2021-06-30T22:44:12Z)

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.