Multimedia Papers of the Week

We introduce the Voice Identity Perception benchmark (VIPBench), which contains 124,876 same-or-different judgments from 1,290 listeners on 9,800 recording pairs from 100 public figures.

However, they commonly determine the relative contributions of the two representations implicitly, preventing the global-local contributions from adapting to the sample-dependent reliability of local cues and resulting in either insufficient use of informative local cues or excessive interference from unreliable ones. To address these issues, we propose DGC-Net, a Dynamic Gating and Global-Guided Compensation Network for MSA.

We evaluate three audiocapable models on acted, conversational and spontaneous speech (eNTERFACE'05, MELD and CMU-MOSEI).

Methodology: An open-label randomised controlled trial was conducted among 80 dog owners in Kelantan, Malaysia.

This study designed, developed and evaluated an Education for Sustainable Development (ESD)-integrated interactive science e-book using a Design-Based Research (DBR) approach.

We present GazeTags, a camera- and computer-vision-free approach for worn head-gaze object awareness.

One primary challenge for these unsupervised approaches is handling occluded regions, as they rely on photometric consistency. To address these issues, we propose Unsupervised Multi-View Stereo for Large-Scale Scenes With Heavy Occlusions (UMVS).

By simply realigning the window, it preserves precise audio-visual alignment, while a configurable hop size reduces the frontend look-ahead well below the human perceptual threshold. Building on this tunable hop size, we propose the Unified Varhop Framework to accommodate scenarios with diverse latency and computation budgets.

No statistically significant differences in vocabulary outcomes were found between conditions at any assessment point in the study.

While our evaluation assumes a controlled setup with disjoint image clusters, we validate its robustness against automated partitioning and noise. This work establishes a comprehensive evaluation framework to map the structural trade-offs of these paradigms, and validates the effectiveness of the proposed protocol with a tailored user preference study.

However, improving static identity alignment alone creates a fundamental tension between identity fidelity and temporal controllability, which frequently causes identity drift or motion suppression under large pose variations and multi-segment sequential actions. To address this, we propose Chronos, a framework that unifies single-segment facial identity preservation and multi-segment sequential action generation under a common temporal formulation.

We therefore require that explanation training cannot alter the verdict. We introduce FOX, which first builds and locks a specialist DINOv3 detector, then uses its representation to guide a lightweight VLM toward forensic explanation.

We present EDGAR (Efficient Diffusion-Driven Gaussian Avatar Refinement), a conditional diffusion framework designed to enhance the quality of Gaussian avatars by correcting artifacts while preserving identity fidelity.

We introduce Lab2Sim, a benchmark of 218 science experiment videos with evidence-grounded specifications and 11,881 rubric items.