arXiv:2606. 05931v1 Announce Type: cross Abstract: When retrieving a person from a video archive by voice and face, should the system be multimodal or not?
arXiv:2501.18157v2 Announce Type: replace-cross Abstract: Building reliable speech systems often requires combining multiple modalities, like audio and visual cues. While such multimodal solutions fr...
arXiv:2609.26648v1 Announce Type: cross Abstract: Active speaker detection (ASD) requires reliable association between visible faces and acoustic speech, yet existing systems often degrade under chal...
arXiv:2606. 29335v1 Announce Type: cross Abstract: Multimodal speaker identification systems face two key challenges in real-world deployment: missing modalities and language mismatch between training and testing conditions.
The paper introduces SCALAR, a query‑conditioned spherical centroid aggregator that assigns relevance‑based weights to each available modality before computing a spherical centroid. SCALAR supports arbitrary modality subsets, is trained with rank‑8 LoRA adapters on masked views, and achieves positive aggregation gains on four of five benchmarks, outperforming prior symmetric aggregators. With only 4.8 million trainable parameters, SCALAR attains the highest text‑to‑video R@1 on three benchmarks and surpasses the released GRAM checkpoint under test‑time modality dropout by 3.2 to 10.9 R@1.
arXiv:2606. 02679v1 Announce Type: new Abstract: Multimodal systems often benefit from combining information across language, sound, and visual streams, but this benefit is not guaranteed.
arXiv:2511. 14143v2 Announce Type: replace-cross Abstract: Video Moment Retrieval is a task in video understanding that aims to localize a specific temporal segment in an untrimmed video based on a natural language query.
arXiv:2607. 07907v1 Announce Type: cross Abstract: With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associations that originate from their training data.
Conventional face recognition relies on static appearance cues and degrades in unconstrained settings with expression variation, occlusion, and poor lighting. We hypothesize that audiovisual expression dynamics carry identity-discriminative information complementary to static appearance, and that extracting this signal requires multimodal representations robust to the variable input quality of in-the-wild video.
arXiv:2609.15320v1 Announce Type: new Abstract: Volume-based multimodal retrieval jointly scores a text query with a candidate's video, audio, and subtitle embeddings. While this approach captures hi...
ReH-FUSE is a reliability‑aware hierarchical fusion framework for multimodal emotion recognition in conversation. It uses a decision‑level router to first compare the relative preference between text and audio, then balances this unimodal mixture with a cross‑modal expert, thereby separating unimodal competition from cross‑modal selection. Experiments on IEMOCAP and MELD show that ReH-FUSE achieves state‑of‑the‑art weighted and macro F1 scores, and ablation studies confirm that learned routing outperforms uniform expert averaging and benefits from cross‑modal interaction.
The paper introduces RAFM-SER++, a lightweight multimodal speech emotion recognition framework designed for real‑time surveillance systems. It replaces heavy bidirectional cross‑modal transformers with an asymmetric Residual Attention Fusion Mechanism that injects affective speech cues into text representations via a one‑directional residual attention pathway. Experiments on IEMOCAP and ESD show RAFM‑SER++ outperforms the HuBERT‑Base baseline and MemoCMT, reducing trainable parameters by over 60%, achieving 79.60 it/s inference speed, and reaching BACC scores of 81.10% on IEMOCAP and 95.39% on ESD.
arXiv:2606. 07643v1 Announce Type: cross Abstract: Recent advances in Omni-Multimodal Large Language Models (Omni-MLLMs) have enabled strong integration of vision, audio, and language.