Applied & Human-Centered · Computer Science & AI
Multimedia
The newest papers in Multimedia that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
192 papers, from 6 September 2026 to 5 November 2026: 192 arXiv preprints.
Get the few papers worth your time in Multimedia every morning.
Follow Multimedia and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 2
Confident First, Reflective Second: Reinforcement Learning of Confidence-Preserving Reflection for Video Understanding
Video models answer from sampled frames and may miss the decisive moment.Zero-Shot Multimodal Event Spotting in Soccer Broadcasts
Automatic soccer event spotting supports highlight generation, video indexing, and sports analytics, but existing methods depend on large annotated datasets and soccer-specific training.From Speech Tokens to Stolen Voices: Attacker-Chosen-Text Speaker Impersonation via Representation Inversion
Speech interaction systems have gradually evolved from traditional cascaded systems that use text as intermediate information to end-to-end speech language models that directly process speech…EEGaze: Multimodal Attention Prediction in Visual Search via EEG-Based Saliency Refinement
Visual search is ubiquitous in daily life, from locating keys in a messy apartment to finding a tool in a cluttered workshop or an application icon on a desktop screen.Multimodal Concert Video Editing: System Design and Exploratory Evaluation
Editing multi-camera concerts requires coordinated decisions about musical relevance, visual quality and cut timing.Immersive Commons: Designing Ephemeral Spatial Dialogue for Co-Located Mixed Reality Environments
Head-mounted mixed reality (MR) often prioritises individual immersion, potentially drawing attention away from others sharing the room.Hierarchical Multimodal Interaction Reasoning for Dyadic Relationship Recognition
Dyadic relationship recognition aims to identify the latent social relationship between two individuals from their multimodal interactions.Freeze What Is Settled, Cache What Is Smooth: Spatial Freezing Keeps Step Caching in Its Low-Error Regime
Instruction-based image editors built on diffusion transformers run tens of denoising steps.AdShot: Benchmarking Multimodal Large Language Models for Video Advertisement Clipping
Advertisers routinely create multiple duration variants of ads to meet marketing budgets and viewer preferences, a labor-intensive and costly process.AV-FABLE: Audio-Visual Manipulation Forensics in Long-Form Videos
Localized AI manipulations in long-form videos often affect brief events within otherwise authentic content, making video-level classification insufficient for forensic analysis.4DMemory: Benchmarking Long-Horizon Spatiotemporal Memory with Harness-Augmented Agents
Humans efficiently process multimodal streams spanning hours to years, building persistent, fine-grained spatiotemporal memories that support reasoning about and predicting long-horizon events.Past as State, Present as Attention: Persistent-State Blockwise Flow Matching for Long-Horizon Co-Speech Motion Generation
Co-speech motion generation remains challenging over long horizons due to the need for temporal coherence and consistent style.SREdit: Scene Response Guided Appearance Editing for Projection Mapping
Projection-based appearance editing changes selected visual attributes of a physical object through projection mapping (PM).The Paired Thermal Channel Is Two Orthogonal Axes: A Controlled Attribution Study of Calibration Cost and Detection Gain in Infrared Person Detection
The calibrated thermal channel in infrared person detection comprises two structurally orthogonal axes.Beyond Visible Speakers: Context-Aware Active Speaker Detection with Speaker Registration
Active speaker detection (ASD) relies on audiovisual correspondence between speech and visible faces, yet this correspondence becomes unreliable in crowded scenes, or when visual evidence is…ConsMSA: Semantic Distribution Consistency Learning for Multimodal Sentiment Analysis
Multimodal sentiment analysis (MSA) aims to predict human sentiments by integrating signals from different modalities such as text, video, and audio.Resonance and Depth: Composing Timbral Identity and Spatial Form in an Artist-in-the-Loop Co-Creative Multi-Agent Percussive Performance
This research-creation artistic report presents Resonance and Depth, a 9-minute immersive electroacoustic/acousmatic performance that treats timbre and space as primary compositional materials.Progressive Learning from Content to Relevance to Personalization for CTR Prediction
Multimodal click-through rate (CTR) prediction is central to search systems, where ranking depends on item content, query relevance, and user preference.Multi-Scale Latent Temporal Compression Attention and Video-Text Cross Attention Fusion for Video Action Detection
In video action detection, modeling the temporal dependencies in continuous video streams is crucial.OACap: Caption-Guided Active Observation for Detailed Video Captioning
Unlike question answering, where a query specifies a perceptual target, open-ended detailed captioning must determine what evidence to acquire and how to integrate it into a coherent global…