Peer Revenue Publish or profit

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Multimedia

cs.MM Watch Multimedia

Sunday 20 September

Multimedia

If You Hear It, Help Find It: Orthogonal Knowledge Distillation for Open-Vocabulary Audio-Visual Event Localization

Yi Xu, Cheng Chen and Wenzhuo Lei

Open-vocabulary audio-visual event localization (OV-AVEL) grounds a text-queried event in time from video, audio, and language. The supervision sources available to this task can differ in temporal-boundary reliability: on OV-AVEBench, our configured visual teacher gives more reliable boundary cues than the configured audio teacher, although the latter is a strong pretrained audio model and remains semantically informative. This is a setting-specific diagnostic rather than a universal ranking of vision and audio. We formulate the resulting challenge as supervision placement: which teacher signals may shape the localization decision, and which should remain auxiliary. Based on this view, we propose OV-OrthKD, a reliability-aware asymmetric distillation framework. Visual feature transfer shapes a decision-aligned representation, audio feature transfer enriches a complementary auxiliary subspace, a text prototype anchors seen/unseen category semantics, and an orthogonality loss limits directional overlap between the two teacher-specific projections. The student continues to use both modalities through query-aware fusion at inference, while the default training recipe keeps audio-teacher supervision off the segment-logit path. On OV-AVEBench, OV-OrthKD achieves 0.816 segment AP and improves F1@0.5 over the official fine-tuning baseline by 2.7 points overall and 3.4 points on unseen categories. Path-assignment, role-swap, corruption, and transfer analyses consistently support supervision placement as a task-specific design axis for OV-AVEL.
Read the full abstract

Saturday 19 September

Multimedia · Cross-listed from cs.CV

MM-ContextFold: Context Folding for Multimodal Agentic Retrieval

Yang Tian, Fan Liu, Jingyuan Zhang et al. (+3 more)

Multimodal Agentic Retrieval (MAR) requires agents to solve complex information-seeking tasks by iteratively invoking external tools. Typical frameworks such as ReAct maintain raw multimodal inputs and the accumulating interaction history in a single, ever-growing context, leading to the context explosion problem. While existing methods alleviate this issue by compressing redundant text, effective strategies for managing token-intensive visual content remain largely underexplored. To address this gap, we first conduct a systematic empirical study of approximately 10,000 trajectories. The results show that as visual cues are progressively extracted through external tools and textualized into the context, raw images become increasingly redundant. Continued image retention is associated with higher output entropy and can even degrade task accuracy. Motivated by these findings, we propose MM-ContextFold, a training-free framework that loads raw images only when needed. It maintains a persistent, text-only main context for high-level planning and spawns ephemeral branch contexts for image-dependent subtasks. Within each branch, the agent loads the relevant images, completes the subtask, and folds the result back into the main context as a concise textual summary; the images and branch trace are then discarded. Experiments on seven MAR benchmarks across five backbone models show that MM-ContextFold improves average accuracy by 6.3 percentage points over ReAct while reducing the working context length by 27.5%.
Read the full abstract

All authors Yang Tian, Fan Liu, Jingyuan Zhang, Zhenyang Li, Yupeng Hu, Liqiang Nie

Multimedia · Cross-listed from cs.CV

MixiMotion: One-Step Text-to-Motion Generation via Asymmetric Set Distillation

Hung Dinh, Binh Mai, Tran Quoc Bao Le et al. (+2 more)

Iterative text-to-motion generation delivers high-quality and semantically aligned motions but requires multiple network evaluations, resulting in substantial inference latency. We present MixiMotion, a strict one-step text-to-motion generation framework based on offline set distillation. Instead of distilling a single teacher trajectory for each text prompt, MixiMotion constructs an offline bank of multiple teacher motions and aligns teacher and student sample sets through asymmetric bidirectional matching. The teacher-to-student direction promotes coverage of diverse teacher-supported motions, while the student-to-teacher direction suppresses unsupported generations. We further introduce differentiable decoded-space kinematic supervision to complement normalized representation matching with constraints in the decoded motion space. At inference, MixiMotion generates a complete motion sequence with a single network evaluation, without teacher queries, iterative sampling, or candidate ranking. On ViMoGen, MixiMotion achieves a semantic alignment score of $0.835$, outperforming the evaluated one-step baselines and approaching the $0.858$ score of its 50-step HY-Motion-1.0-Lite teacher. In blinded human evaluation, MixiMotion obtains an overall rating of $4.33$, compared with $4.50$ for the teacher, while outperforming the evaluated one-/few-step baselines. Meanwhile, generation latency is reduced from $829.58$\,ms to $9.30$\,ms, corresponding to an $89.2\times$ speedup. These results demonstrate an effective quality–efficiency trade-off for strict one-step text-to-motion generation.
Read the full abstract

All authors Hung Dinh, Binh Mai, Tran Quoc Bao Le, Lam Nguyen, Cong Tran

Multimedia · Cross-listed from eess.IV

Scalable SSIM Estimation from PSNR for Per-Title and Context-Adaptive Encoding Workflows

Luc Trudeau and Maria G. Martini

Modern streaming pipelines run hundreds of candidate encodes per asset to support per-title encoding, shot-based optimization, and context-adaptive ABR ladder construction. These techniques have moved perceptual quality metrics into the critical path: SSIM and VMAF now guide encoding decisions rather than passively monitor them. We measure that SSIM evaluation accounts for 7-35% of x264 encode time at production speed presets, with the cost ratio rising as encoders run faster. We propose ApproxSSIMate, a low-complexity method for estimating SSIM from PSNR combined with reference-sequence statistics computed once per sequence and reused across every candidate encode. This decouples quality estimation from the encode-decode-compare loop, enabling perceptual quality feedback in live encoding and amortizing quality measurement across candidate encodes in per-title workflows. We validate the approach across H.264/AVC, H.265/HEVC, and AV1 on the Objective-1-fast dataset and release the implementation as free and open-source software.
Read the full abstract

Friday 18 September

Multimedia · Cross-listed from cs.GR

GS-PQM: A Parameter-Domain Quality Metric for Compressed Gaussian Splatting

Pedro Martin, António Rodrigues, João Ascenso et al. (+1 more)

Recent advances in Gaussian Splatting (GS) compression have enabled substantial reductions in GS model size. Reliable objective quality assessment is therefore essential for comparing compression methods and guiding the development of more efficient GS codecs. Existing GS quality assessment typically relies on image and video quality metrics, requiring rendering of predefined viewpoints and making the quality estimate dependent on the selected views. This paper introduces GS-PQM, a novel full-reference quality metric for post-training GS compression that operates directly in the GS parameter domain. GS-PQM estimates perceptual quality from a set of parameter-domain distortion errors using a Support Vector Regression model. Experimental results show that GS-PQM outperforms 25 existing image, video, and point-cloud quality metrics in assessing compressed GS content, providing an accurate and computationally efficient alternative to rendering-based quality assessment.
Read the full abstract

All authors Pedro Martin, António Rodrigues, João Ascenso, Maria Paula Queluz

Multimedia · Cross-listed from cs.CV

Style as Cover: Deep Image Steganography via Stylized Transmission

Qi Li, Jidong Yang, Huaike Yu et al. (+6 more)

Image steganography hides secret message within normal images, with most existing works relying on cover-preserving transmission. However, such a paradigm becomes vulnerable once the original cover is exposed or can be reliably approximated. In this paper, we propose StyleStegaNet, a stylized image hiding framework that replaces cover matching with style-concealment transmission. Instead of transmitting a cover-like stego image, StyleStegaNet generates stylized stego images conditioned on publicly available style references, redefining steganography invisibility from cover-preserving concealment to behavior-level camouflage based on style transformation. Such a setting poses a substantial challenge to reliable secret recovery, since neural stylization can significantly alter the feature statistics exploited by deep hiding methods. To address this challenge, StyleStegaNet decouples the overall task into four coordinated stages: stego generation, stylized transmission, structure-preserving reconstruction, and secret recovery. Moreover, StyleStegaNet is optimized with a progressive three-stage training strategy, in which wavelet-domain constraints and perceptual supervision guide the recoverable information toward structural representations. We further provide an analysis showing that secret recoverability is largely restricted to the normalized structural subspace, offering a mechanistic explanation for why directly stylized baselines fail and why a reconstruction-guided recovery path is necessary. Extensive experiments on DIV2K and MS-COCO datasets demonstrate the effectiveness of StyleStegaNet. And few-shot image steganalysis with two deep detectors further shows detection accuracy near random guessing, approximately 51%.
Read the full abstract

All authors Qi Li, Jidong Yang, Huaike Yu, Chunpeng Wang, Suo Gao, Herbert Ho-Ching Iu, Yuantian Miao, Bin Ma, Xiao Chen

Multimedia · Cross-listed from eess.AS

The Spoken Wikipedia Presentation Corpus

Thomas Ranzenberger, Steffen Freisinger, Tobias Bocklet et al. (+1 more)

We present the Spoken Wikipedia Presentation Corpus, an extension of the Spoken Wikipedia Corpora featuring LLM-generated slide decks for multimodal ASR. Slides are created from LLM-segmented sections using a hybrid pipeline that combines LLM-based content planning with rule-based design decisions. For each section, an LLM generates a slide title, bullet points, a takeaway message, and a visual description that is used to create an illustration. Rule-based matching then selects layouts, themes, and styles to produce the final slides. A vision LLM extracts slide text as Markdown. We evaluate multiple ASR and spoken language models (SLMs). The best model achieves an average micro-WER of 10.23% and an average micro-CER of 6.48% on audio-only inputs. English yields the lowest error rates, followed by German and Dutch, while performance declines across lower-resource languages. Although audio-only baselines are strong, multimodal zero-shot prompting of omni models remains challenging. The aligned slide, text, and audio data show a strong potential to improve recognition through cross-modal context.
Read the full abstract

All authors Thomas Ranzenberger, Steffen Freisinger, Tobias Bocklet, Korbinian Riedhammer

Multimedia · Cross-listed from cs.CL

Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal Interaction

Qi Chen, Yunfei Chu, Haolin He et al. (+15 more)

Natural audio-visual interaction is emerging as an important interface for AI assistants, allowing users to communicate through speech and vision rather than carefully composed text prompts. However, existing benchmarks of interactive capabilities still focus primarily on response quality, leaving a more fundamental question underexplored: can a model correctly infer the user's underlying demand from complex multimodal interaction? Real-world user demands are often underspecified in speech and must be inferred from multimodal cues and dialogue history. This inference is further complicated by ambiguous or disfluent expression and noisy acoustic environments. Conversely, request-like speech may not constitute a demand to the assistant, leading to false triggers. We establish Omni Demand Understanding (ODU) as a distinct multimodal contextual inference problem: given an interaction stream, a model must detect whether a user demand is present and infer intent from multimodal and conversational context. ODU evaluates this capability along five dimensions, covering both single-turn and multi-turn interactions. We construct ODU-Bench using a challenge-driven taxonomy, taxonomy-guided agentic video generation, and human-recorded interactions, followed by media-grounded annotation and human verification. We evaluate 14 native MLLMs. Even the strongest, Gemini 3.1 Pro, recovers only 44.7% of key information that must be inferred from visual, acoustic, or conversational context. Moreover, 11 of the 14 models exhibit false-trigger rates above 50% on non-demand scenarios. These results reveal a systematic capability gap in current MLLMs' ability to infer contextual user demands. We hope ODU can establish the evaluation of a previously underexplored yet essential capability in multimodal interaction: correctly understanding user demands before generating an appropriate response.
Read the full abstract

All authors Qi Chen, Yunfei Chu, Haolin He, Yifan Yang, Zihan Liu, Yuxuan Wang, Ziyang Ma, Ruiyang Xu, Meng Gao, Yinsong Yan, Ling Wang, Hui Wang, Wen Huang, Yiheng Chen, Guanrou Yang, Qiuqiang Kong, Jin Xu, Xie Chen

Thursday 17 September

Multimedia · Cross-listed from cs.CV

MemeTAG: Keyword-Driven Meme Classification through Tag Embedding Reconstruction

Akshit Sharma and Prashant W. Patil

The proliferation of harmful internet memes poses a significant societal threat, yet their automated classification remains a formidable algorithmic challenge due to the nuanced, multimodal nature of their content. To address this, we introduce MemeTAG, a novel dual-objective framework that pioneers a keyword-aware approach to meme classification. Our core innovation is a two-part semantic guidance mechanism: first, we leverage a pretrained Vision-Language Model to generate a set of descriptive keywords, that capture the high-level semantics. Second, we introduce the Aggregated Tag Inference Network (ATIN), an attention-based module that distills these keywords into a single, rich semantic embedding. This embedding serves as a target for a novel auxiliary reconstruction loss, which compels the model to learn deeply aligned visual and textual features. This approach, combined with an efficient three-stage training strategy, establishes a new state-of-the-art on the HarMeme, Hateful Memes Challenge (HMC), and PrideMM datasets, decisively outperforming existing state-of-the-art methods.
Read the full abstract

Multimedia

Trigger Timing, Deadline Readiness, and Event-Aligned Accounting for Dynamic Ad Insertion

Prashant Chaudhary and Kapil Khandelwal

Dynamic ad insertion comparisons can conflate trigger, reach, readiness, playback, billability and measurement even when the accounting is arithmetically correct. We separate these events with an observed-event ledger, a candidate-invariant reference deadline and pod-level contribution accounting. The deadline rule is fixed before candidate assignment and tests whether an admissible transition state remains valid, not whether preparation merely finished earlier. A restricted monotone-playback representation states when media-position summaries suffice; a counterexample shows why they fail over a wider path class. An offline synthetic study exercises the definitions over nine short-lifetime conditions informative for the readiness comparison and nine long-lifetime conditions serving as analytic controls. Across 45,000 shared scripts, two trigger policies share imposed playback paths, latency draws and hypothetical value and cost coefficients. Playhead summaries substantially misclassify reach events in the nonmonotone mixtures, yet neither shortcut reverses the contribution contrast in this grid, because some errors cancel under the shared design. Replacing validity at the deadline with completion by the deadline reverses the comparison in three of the nine informative conditions, all at one of the three latency settings. Scoring readiness at actual viewer arrival rather than at the reference deadline shifts pause-path readiness but changes no contribution sign. These outcomes are consequences of the event definitions applied to established misclassification mechanisms. Conservative bounds retain uncertainty when records are missing, and the artifact records code, seeds, event histories and checking procedures. The evidence is synthetic, uses no commercial telemetry, and ranks neither server-side nor server-guided insertion.
Read the full abstract

Multimedia · Cross-listed from cs.CV

BinoGen: Scaling egocentric binocular data for embodied visual perception and learning

Chunpeng Li and Ya-tang Li

Embodied visual perception relies on temporally coherent visual experience accumulated through continuous engagement with the environment. However, collecting large-scale egocentric binocular observations together with dense annotations remains costly and difficult. Moreover, visual experience is shaped not only by the environment but also by the embodiment of the observer, including viewing height, field of view, binocular geometry, and motion through the scene. To address these challenges, we present BinoGen, an automated framework for generating large-scale, embodiment-aware egocentric binocular visual experiences in indoor environments. BinoGen jointly models environmental and observer variation through generative scene synthesis, probabilistic object instantiation, appearance randomization, stochastic trajectory generation, and configurable binocular camera setups. The framework produces synchronized binocular videos together with dense multimodal supervision, including depth maps, optical flow, surface normals, semantic maps, object coordinates, and camera poses. Using BinoGen, we construct a dataset comprising more than 20 million annotated images for supervised learning. We demonstrate two complementary utilities of BinoGen. First, incorporating BinoGen data consistently improves real-world visual perception, including depth estimation, object detection, and video object tracking. Second, paired human-inspired and mouse-inspired observations from the same environments enable controlled investigation of how observer embodiment affects perceptual learning. Embodiment-specific adaptation substantially improves performance, while joint training enables a single model to perform competitively across both embodiments. Together, these results demonstrate that large-scale, controllable visual experience can improve embodied perception...
Read the full abstract

Multimedia · Cross-listed from cs.NI

PyStream: Enhancing Video Streaming Evaluation

Samuel Radler, Leon Prüller, Emanuele Artioli et al. (+2 more)

As streaming services become more commonplace, analyzing their behavior effectively under different network conditions is crucial. This is normally quite expensive, requiring multiple players with different bandwidth configurations to be emulated by a powerful local machine or a cloud environment. Furthermore, emulating a realistic network behavior or guaranteeing adherence to a real network trace is challenging. This paper presents PyStream, a simple yet powerful way to emulate a video streaming network, allowing multiple simultaneous tests to run locally. By leveraging a network of Docker containers, many of the implementation challenges are abstracted away, keeping the resulting system easily manageable and upgradeable. We demonstrate how PyStream not only reduces the requirements for testing a video streaming system but also improves the accuracy of the emulations with respect to the current state-of-the-art. On average, PyStream reduces the error between the original network trace and the bandwidth emulated by video players by a factor of 2-3 compared to Wondershaper, a common network traffic shaper in many video streaming evaluation environments. Moreover, PyStream decreases the cost of running experiments compared to existing cloud-based video streaming evaluation environments such as CAdViSE.
Read the full abstract

All authors Samuel Radler, Leon Prüller, Emanuele Artioli, Farzad Tashtarian, Christian Timmerer

Wednesday 16 September

Multimedia · Cross-listed from eess.AS

OneVoice: An Intermediate Representation for Agentic Speech Pipelines

Vipul Charugundla, Dancheng Liu and Jinjun Xiong

Agentic speech systems must exchange more than text, including speaker identity, timing, phonetic information, and behavioral annotations. Yet these signals are often produced in incompatible tool-specific formats, making agent-to-agent handoff fragile. We present OneVoice, a lightweight, JSON-native intermediate representation that provides a shared semantic structure for speech pipelines. OneVoice organizes heterogeneous speech evidence into validated session records with stable identifiers, layered transcripts, explicit timing relationships, and provenance information. We evaluate OneVoice in two complementary multi-agent workflows covering event aggregation and acoustic-phonetic temporal linking across three language models. Compared with implicit agent-defined handoffs, OneVoice substantially improves aggregation reliability and the preservation of temporal relationships, demonstrating the value of an explicit speech-specific representation for agent communication.
Read the full abstract

Multimedia

Visual Graph Reasoning via Knowledge Compilation

Rongzheng Wang, Zhe Wang, Ke Qin et al. (+6 more)

Visual graph reasoning requires answering graph-theoretic questions directly from graph images, where graph topology and state are conveyed visually rather than given in symbolic form. Despite recent progress of vision-language models (VLMs), current approaches to visual graph reasoning still fail on simple visual graph problems. This reveals a fundamental limitation of existing approaches: they prioritize final-answer supervision over the intermediate recovery of an explicit graph representation that preserves graph topology and state from visual input. To address this limitation, we propose VGCompiler, a compilation-centric paradigm for visual graph reasoning via knowledge compilation. VGCompiler organizes reasoning around two compilers: a representation compiler that recovers a structure-preserving intermediate graph representation from visual input, and an operation compiler that compiles query intent under the recovered graph state into an executable graph operation. Specifically, we build VGCompiler on Qwen3-VL-8B and train it with reinforcement learning guided by a layered reward over executability, compiled graph validity, representation quality, and operation quality. VGCompiler uses a frozen observer to summarize graph and question conditions into lightweight signatures, enabling archive retrieval and code reuse across similar regimes. Experiments on three benchmarks GVLQA, VisionGraph, and VGCURE, show that Qwen-VGCompiler, built on an 8B backbone, surpasses the strongest closed-source VLM baseline by 28.9% and the strongest code-based baseline by 23.7%, while maintaining high efficiency. We further evaluate VGCompiler on three real-world domains, including metro routing, logistics delivery, and network fault assessment, where it generalizes across heterogeneous visual graphs and domain-grounded tasks.
Read the full abstract

All authors Rongzheng Wang, Zhe Wang, Ke Qin, Rongwei Wang, Muquan Li, Yizhuo Ma, Yihong Huang, Jielei Wang, Shuang Liang

Multimedia

From Models to Systems: A Comprehensive Survey of Efficient Multimodal Learning

Pan Wang, Siwei Song, Hui Ji et al. (+12 more)

The rapid expansion of multimodal models has surfaced formidable bottlenecks in computation, memory, and deployment, catalyzing the rise of Efficient Multimodal Learning (EML) as a pivotal research frontier. Despite intensive progress, a cohesive understanding of what, how, and where efficiency is manifested across the learning stack remains fragmented. This survey systematizes the EML landscape by introducing the first structured, model-to-system taxonomy. We distill insights from over 300 seminal works into three hierarchical levels–model, algorithm, and system–addressing architectural parsimony, execution refinement, and hardware-aware orchestration, respectively. Moving beyond a purely categorical review, we offer a methodological synthesis of the vertical synergies between these layers, elucidating how cross-layer co-design contributes to the fundamental "Efficiency-Utility-Privacy" trade-off. Through an integrative case study of Multimodal Large Language Models (MLLMs), we trace the field's evolutionary trajectory from initial structural adjustments to modern full-stack resource orchestration. Furthermore, we provide a holistic discussion and application-specific optimization blueprints for diverse domains and posit a paradigm shift toward self-regulating intelligence, where efficiency is an intrinsic, emergent property of the model's fundamental design rather than a post-hoc constraint. Finally, we present open challenges and future directions that will define the trajectory of EML research. This survey establishes a structured framework for multimodal systems that are not only high-performing and generalizable but natively efficient and ready for ubiquitous deployment. A continuously updated version is available at https://github.com/pwang322/Efficient-Multimodal-Learning-Survey.
Read the full abstract

All authors Pan Wang, Siwei Song, Hui Ji, Siqi Cao, Heng Yu, Zhijian Liu, Huanrui Yang, Yingyan Celine Lin, Beidi Chen, Mohit Bansal, Xiaoming Liu, Pengfei Zhou, Ming-Hsuan Yang, Tianlong Chen, Jingtong Hu

Multimedia · Cross-listed from cs.CV

Riemannian–Lorentz Fusion of Vision Transformers and State-Space Models

Badri N. Patro and Vijay S. Agneeswaran

Scaling deep learning faces critical bottlenecks: data exhaustion, exponential training costs, and resource concentration. Model merging combines pre-trained checkpoints without gradient descent, offering orders-of-magnitude savings versus retraining. Combining independently trained vision models is difficult when their architectures and parameter shapes differ. Existing weight-space merging methods generally assume aligned, shape-compatible checkpoints, whereas a Vision Transformer (ViT) and a state-space model (SSM) implement token mixing with different operators. We study a hybrid Heterogeneous merging setting that retains both architectures while aligning parameter groups by semantic role. Our proposed Riemannian–Lorentz Parameter Fusion (RLPF) method projects aligned groups to common coordinates, lifts selected coordinates to the Lorentz hyperboloid model of hyperbolic space, computes a regularized geodesic barycenter, and decodes the result into the two branches. A learned gate then combines branch logits for each input. Component groups use fixed curvature values, with normalization parameters treated as Euclidean. In the results available in this manuscript, the fine-tuned system obtains 82.37% on CIFAR-10, 75.04% on Oxford-IIIT Pet, and 78.58% top-1 accuracy on ImageNet-1K; the corresponding best-parent accuracies are 76.54%, 71.42%, and 76.42%. On ImageNet-1K, the reported pre-fine-tuning initialization reaches 77.80%. These results support further study of geometry-aware heterogeneous fusion, but not a training-free single-checkpoint merge: RLPF is a two-branch hybrid whose gate and reported final models are trained.
Read the full abstract

Multimedia · Cross-listed from eess.IV

Perceptual Refinement of an End-to-End Video Streaming Pipeline via Generative AI Layers

Emanuele Artioli, Farzad Tashtarian and Christian Timmerer

Traditional codecs treat every region of a frame alike; a generative layer can instead degrade the regions a viewer attends to least and reconstruct them at the client. We present PRESLEY, which extends the prior conference work ELVIS by replacing destructive block removal with adaptive in-place degradation under a removability mask, signaling per-block strength in a bit-packed side channel, and restoring via generative backbones conditioned on transmitted visual priors rather than unconditioned in-painting. We separate the problem into three goals: choosing which blocks to degrade, degrading them so the encoder spends fewer bits, and restoring them. Against its predecessor at matched rate, PRESLEY achieves a decisive mean -56.4% BD-rate reduction on delivered background quality across 13 rate ladders spanning multiple codecs and dataset families. Against pristine baselines, PRESLEY defines the operating regime of generative transport: delivering substantial bitrate savings (up to -29.4% BD-rate) and superior background quality (17/23 sequences) in the target bit-starved regime, while maintaining foreground fidelity bit-exact. We further map where the theoretical headroom in this class of architecture lies. Using an exact leave-one-superblock-out combinatorial oracle as an additive empirical bound, we show that existing complexity heuristics already capture 83.3% of bit-cost savings, bounding remaining cost-axis headroom at about 5% of total bitrate. We then identify and model the primary unaddressed axis – post-restoration damage – which disperses widely (4.9-8.4 dB). We prove that this damage is predictable before transmission (held-out rho = +0.400), establishing the feasibility of transmit-time restorability modeling and defining the roadmap for joint rate-distortion-restoration selection rules.
Read the full abstract

Multimedia · Cross-listed from cs.CV

GenStream: Semantic Streaming Framework for Generative Reconstruction of Human-centric Media

Emanuele Artioli, Daniele Lorenzi, Shivi Vats et al. (+2 more)

Video streaming dominates global internet traffic, yet conventional pipelines remain inefficient for structured, human-centric content such as sports, performance, or interactive media. Standard codecs re-encode entire frames, foreground and background alike, treating all pixels uniformly and ignoring the semantic structure of the scene. This leads to significant bandwidth waste, particularly in scenarios where backgrounds are static and motion is constrained to a few salient actors. We introduce GenStream, a semantic streaming framework that replaces dense video frames with compact, structured metadata. Instead of transmitting pixels, GenStream encodes each scene as a combination of skeletal keypoints, camera viewpoint parameters, and a static 3D background model. These elements are transmitted to the client, where a generative model reconstructs photorealistic human figures and composites them into the 3D scene from the original viewpoint. This paradigm enables extreme compression, achieving over 99.9% bandwidth reduction compared to HEVC for the continuous data stream. We partially validate GenStream on Olympic figure skating footage and demonstrate potential for high perceptual fidelity under minimal data. While acknowledging the significant computational costs shifted to the client and challenges in generalization, GenStream opens new directions in volumetric avatar synthesis, canonical 3D actor fusion across views, and personalized viewing experiences, laying the groundwork for scalable, intelligent streaming in the post-codec era.
Read the full abstract

All authors Emanuele Artioli, Daniele Lorenzi, Shivi Vats, Farzad Tashtarian, Christian Timmerer

Multimedia

MoQSplat: Adaptive Progressive Streaming of 3D Gaussian Splatting via MoQ

Emanuele Artioli, Mohammadreza Ghafari, Md Tariqul Islam et al. (+3 more)

3D Gaussian Splatting (3DGS) enables photorealistic novel view synthesis, but transmitting gigabyte-scale scene data remains challenging for immersive applications. Traditional HTTP Adaptive Streaming over TCP introduces Head-of-Line (HOL) blocking and coarse segmenting ill-suited to fine-grained 3DGS delivery. We propose MoQSplat, which maps 3DGS content onto the Media over QUIC (MoQ) transport hierarchy. MoQSplat partitions scenes into spatial Tracks, clusters splats into semantically coherent Groups, and constructs progressive-quality Subgroups mapped to independent QUIC streams to eliminate connection-level HOL blocking. Using a stateless, subscriber-driven adaptation loop, clients dynamically request spatial regions and quality tiers based on six degrees of freedom (6-DoF) frustum visibility, distance, and foveal alignment. We evaluate the core components on a prototype implementation, showing that opacity-based pruning outperforms scale-based pruning for progressive delivery. The source code is available at https://github.com/emanuele-artioli/MoQSplat.
Read the full abstract

All authors Emanuele Artioli, Mohammadreza Ghafari, Md Tariqul Islam, Farzad Tashtarian, Christian Rothenberg, Christian Timmerer

Multimedia · Cross-listed from cs.SD

TTM-Bench: A Framework for Text-to-Music System Performance Benchmarking

Giorgia Adorni, Michela Papandrea, Battista Rimoldi et al. (+1 more)

Text-to-music (TTM) systems are increasingly used to generate musical audio from natural-language descriptions. Robust evaluation is therefore essential, yet reliable performance comparison remains challenging. This difficulty stems from differences in system architecture, supported conditioning information, and access mode, as well as heterogeneous and fragmented metrics that cannot be applied uniformly across systems. To address these challenges, we introduce TTM-Bench, a framework that defines a common protocol for systematic, reproducible performance benchmarking of contemporary TTM systems. It evaluates performance along two dimensions: musical-content alignment, quantified by interpretable semantic, genre, and musical-descriptor agreement scores against a common musical specification and summarized by an aggregate score; and computational efficiency, characterized by generation latency and real-time factor, alongside resource use for local models and cost for hosted services. We demonstrate the framework through a preliminary comparative case study, illustrating the complementary evidence captured by these dimensions. The results show that higher musical-content alignment does not systematically coincide with lower computational demands, highlighting the importance of assessing TTM performance through distinct, interpretable measures rather than a reductive overall indicator.
Read the full abstract

All authors Giorgia Adorni, Michela Papandrea, Battista Rimoldi, Tiziano Leidi

Multimedia

Divide and Conquer: Mixture-of-Bottleneck Experts in Informative Ordinal Space for Video-based Multimodal Sentiment Analysis

Ronghao Lin, Qiaolin He, Zefeng Lu et al. (+5 more)

Video-based Multimodal sentiment analysis (MSA) must handle information from text, audio, and image sequence in human speaking videos, yet current methods often fail to integrate modalities with task awareness. Most models treat video sentiment prediction as a single task, overlooking its ordinal nature, and their fusion strategies struggle to capture diverse unique and synergic cues across modalities. To address these limitations, we adopt a divide-and-conquer perspective by reformulating MSA as an ordinal regression problem and decoupling it into polarity recognition and intensity prediction. Driven by information theory, we introduce a Mixture-of-Bottleneck (MoB) framework that assigns different latents to polarity- and intensity-specific experts for different modalities. With the learning of information bottleneck, each expert learns compact and task-relevant representations while filtering out redundancy and noise. A multimodal bottleneck routing fusion module then fuses these expert latents with hard mining strategy, guiding the prediction in the ordinal sentiment space. Extensive experiments on 4 MSA datasets and 4 language models show that MoB effectively leverages informative latents from diverse modalities and captures general sentiment structure. Beyond stronger performance, MoB comprehensively captures fine-grained intra- and inter-modal dynamics, enabling more trustworthy localization of nuanced video sentiment signals.
Read the full abstract

All authors Ronghao Lin, Qiaolin He, Zefeng Lu, Yichu Liu, Li Huang, Sijie Mai, Haifeng Hu, Yap-peng Tan

Multimedia

Multimodal Aspect-Level Sentiment Analysis Based on Gated Noise Filtering and Emotion-Relevance Interaction

Chen Huang, Liangwei Guo, Yamin Li et al. (+4 more)

Multimodal Aspect-Based Sentiment Analysis (MABSA) infers fine-grained sentiment polarity toward specific aspects by jointly modeling text and images. Despite progress in cross-modal fusion, two challenges remain in multi-aspect settings: (1) multimodal noise, where aspect-irrelevant content distracts sentiment learning; and (2) weak cross-modal sentiment alignment, as visual evidence can be ambiguous and textual–visual sentiments may conflict, limiting multimodal complementarity. To address these issues, we propose a Gated Noise-filtered Sentiment-Relevance Interaction (GNSRI) framework. It employs a gated noise-filtering module to suppress sentiment-irrelevant features and enhance aspect-aware sentiment cues, and a sentiment-relevance interaction module to capture consistent and conflicting cross-modal signals at micro and macro levels. Finally, a learnable decision fusion mechanism adaptively combines predictions from textual, visual, and cross-modal branches at the aspect level. Experiments on public MABSA benchmarks show that GNSRI outperforms state-of-the-art methods, improving accuracy by 1.94% and 2.06% on Twitter-2015 and Twitter-2017, respectively.
Read the full abstract

All authors Chen Huang, Liangwei Guo, Yamin Li, Yan Zhang, Chao Yang, Li Yang, Jianhua Song

Multimedia · Cross-listed from cs.CV

Visual Autoregressive Priors for RAW-to-sRGB Image Signal Processing

Tailai Chen, Xiaotong Luo, Yuan Gao et al. (+2 more)

RAW-to-sRGB image signal processing (ISP) must recover perceptually faithful colors and fine details from sensor measurements, often under imperfect spatial alignment and missing camera metadata. This paper presents, to the best of our knowledge, the first application of visual autoregressive (VAR) next-scale prediction over a discrete image codebook to the RAW-to-sRGB ISP task. We adapt a frozen 1.10\,B-parameter VAR backbone for RAW-conditioned ISP with only 32.93\,M trainable parameters (2.99%), and propose a frequency-decomposed color loss that separately supervises low-frequency tone via wavelet LL cosine similarity and chromatic edges via detail-band $\ell_1$. On the Zurich RAW-to-sRGB benchmark, the method improves PSNR-Y from 21.31 to 21.89\,dB and reduces LPIPS from 0.276 to 0.218 on the full 1,204-image test set. Diagnostic experiments show that the VAR prior preserves structure well, but continuous color transfer remains the dominant bottleneck: oracle affine correction recovers 3.8\,dB, while learned color heads yield marginal gains.
Read the full abstract

All authors Tailai Chen, Xiaotong Luo, Yuan Gao, Xin Jin, Wenjun Zeng

Multimedia

SemABR: Measuring Video Semantic Fidelity with Multimodal LLMs for Adaptive Bitrate Streaming

Shiqi Xu, Soung Chang Liew and Yuyang Du

Conventional video metrics such as PSNR, SSIM, and VMAF measure visual distortion or perceptual quality, but they do not directly capture semantic preservation: whether compression retains a video's objects, actions, and temporal narrative. Existing Quality-of-Experience (QoE)-driven bitrate-selection and resource-allocation methods primarily aim to minimize rebuffering and bitrate switching while maximizing perceptual video quality, without explicitly considering semantic preservation. To address this gap, we introduce video semantic fidelity (SF), a metric that quantifies how well a compressed video preserves the semantic content of its source. An offline multimodal large language model (MLLM) generates structured descriptions of the reference and compressed versions of the video, and a separate text-only large language model (LLM) evaluates their semantic correspondence. The resulting content-dependent SF–bitrate profiles are cached and queried by the online bitrate selector without invoking MLLMs at runtime. Evaluations on three subjective QoE benchmarks show a consistent positive association between SF and mean opinion scores (MOS). A separate human semantic-rating study evaluates semantic preservation and shows that SF correlates more strongly with human judgments than conventional video metrics. We then embed these profiles into a 5G MEC-assisted video-on-demand (VoD) resource-allocation framework at the base station. When wireless resources cannot support high bitrate levels for all users, the framework uses the SF–bitrate profiles to select bitrate levels jointly across users and reduce the semantic loss caused by the required bitrate reductions. NS-3 simulations with the 5G NR module show that the proposed framework achieves higher average and worst-user SF than the evaluated baselines, with a widening advantage as the wireless resources available to each user decrease.
Read the full abstract

Tuesday 15 September

Multimedia · Cross-listed from eess.IV

TTTIR: Unlocking Instance-Specific State Evolution via Test-Time Training for Image Restoration

Kaihang Zheng, Jun Li, Hang Guo et al. (+5 more)

Image restoration is inherently challenging due to the diverse and highly input-dependent nature of real-world degradations. While recent architectures like Transformers and state-space models have advanced the field, they predominantly rely on static, globally shared parameters, which struggle to fully accommodate instance-specific degradation patterns. Test-Time Training (TTT) offers a promising paradigm for generating data-dependent operators, yet its standard self-supervised inner loop lacks the explicit guidance required to transition degraded features toward clean structures. To address this, we propose TTTIR, a novel framework that reformulates image restoration as an instance-specific state evolution process. Specifically, we design Progressive State Sequence Generation (PSSG) to construct complementary spatial-frequency target states (defining what to recover), and State Transition Evolution (STE) to adapt lightweight transition operators via a restoration-oriented TTT inner loop (determining how the features should evolve). Extensive experiments demonstrate that TTTIR consistently outperforms state-of-the-art models across multiple image restoration benchmarks, achieving dynamic instance-specific recovery with favorable computational scalability. The code is available at https://github.com/Elysiaaaaaaaa/TTTIR.git.
Read the full abstract

All authors Kaihang Zheng, Jun Li, Hang Guo, Hongyu Chi, Zimo Liu, Tao Dai, Jinpeng Wang, Yaowei Wang

Multimedia · Cross-listed from cs.SD

The Internet Archive Music Dataset

Paraskevas Stamatiadis, Bernardo V Miranda, Clémentine Berger et al. (+3 more)

We introduce the Internet Archive Music Dataset (IAMD), a large-scale collection of captioned music segments derived from the Internet Archive. To the best of our knowledge, IAMD constitutes the largest publicly available music-caption dataset to date with over 34,000 hours of audio, providing a valuable benchmark for training and evaluating music understanding and generative models. The dataset is built from content declared to be distributed under Creative Commons licenses, and cross-referencing with MusicBrainz is done to improve license information reliability. To annotate IAMD, we present an automatic captioning pipeline that augments base captions produced by an audio-language model (ALM) with textual metadata sourced from the Internet Archive and imputed metadata obtained using audio classification models. Caption quality is assessed objectively and subjectively, and results indicate that the annotation pipeline is reliable and does not degrade caption quality with scaling.
Read the full abstract

All authors Paraskevas Stamatiadis, Bernardo V Miranda, Clémentine Berger, Gaël Richard, Mathieu Fontaine, Slim Essid

Multimedia · Cross-listed from cs.AI

VideoMM: Adaptive Macro-Micro Inference for Efficient Video MLLMs

Haoyu Guo, Yuan Feng, Junlin Lv et al. (+3 more)

Scaling Multimodal Large Language Models (MLLMs) to long-form video understanding is bottlenecked by the explosion of visual tokens, which saturates context windows and incurs prohibitive costs. Current solutions predominantly rely on auxiliary models for token reduction but face a fundamental dilemma: lightweight encoder-driven approaches often overlook critical semantic information, whereas heavyweight MLLM-driven reduction negates the efficiency gains. {In this work, we identify a more fundamental inefficiency underlying this dilemma: while fine-grained visual details are essential for detailed understanding, they are largely redundant for the preliminary task of selecting semantically relevant regions. } Motivated by this, we introduce VideoMM, which marks a paradigm shift from model-centric downsizing to adaptive perceptual granularity. Specifically, our framework {decouples selection from reasoning} by executing semantic filtering on a cost-effective Macro Proxy (derived from downscaled frames), and projecting the selected regions onto high-fidelity Micro Tokens for detailed understanding only when necessary. Extensive evaluations show that VideoMM significantly outperforms existing solutions. It achieves a 6.13$\times$ speedup and a 7.4% accuracy gain over full-context baselines on LongVideoBench, and further accelerates inference by 2.73$\times$ over current leading methods, establishing a highly scalable paradigm for long-video understanding. Our code is available at: https://github.com/adfh917k/VideoMM.
Read the full abstract

All authors Haoyu Guo, Yuan Feng, Junlin Lv, Mingjun Xiao, S Kevin Zhou, Xike Xie

Multimedia

Mechanism-Level Evaluation for Vision-Language Models: Controlled Activation-Replacement Diagnosis of Gender Bias

Zhipeng Zhao, Wenxu Wang, Peishun Liu et al. (+1 more)

Behavioral benchmarking reveals what biases exist in vision-language models but not which internal components are most sensitive to targeted intervention, precluding principled intervention. We argue for mechanism-level evaluation as a necessary complement, demonstrating causal mediation analysis as a diagnostic instrument for gender bias. We decompose gender-cue effects into controlled indirect effects attributable to specific-layer activations and direct effects through all other pathways, producing layer-by-layer mechanistic signatures. Across six models spanning three architectural families (LLaVA-1.5, LLaVA-NeXT, InstructBLIP at 7B/13B) and two 8B-scale architectures, three findings emerge: language-layer activations exhibit the greatest output sensitivity under controlled intervention, with the direct component often carrying the opposite sign; architectural choices redistribute layer-wise sensitivity to activation replacement; and counterfactual scores diverge from surface-level scores, exposing implicit associations. Systematic ablation validates internal consistency. An intervention experiment finds that the average indirect effect (AIE) and downstream intervention effectiveness are only weakly correlated (Pearson $r = 0.33$), and the layer with the second-largest AIE produces near-zero bias change—indicating that mechanistic diagnosis captures activation-replacement sensitivity but does not, by itself, identify optimal intervention targets. These results show mechanism-level evaluation captures architecture-specific sensitivity patterns that behavioral benchmarks cannot; pairing both should become standard NLP practice. Code: https://github.com/zhaozhipeng1997/CARD-GenderBias.
Read the full abstract

All authors Zhipeng Zhao, Wenxu Wang, Peishun Liu, Ruichun Tang

Multimedia · Cross-listed from cs.CV

ViD: Vision-Dominant Gender Bias Mitigation for Large Vision-Language Models

Zhipeng Zhao, Zhaoqiang Wei, Peishun Liu et al. (+2 more)

Gender bias in large vision-language models (LVLMs) undermines their fairness and reliability, compromising output trustworthiness. Current mitigation methods rely on training-phase adjustments or post-hoc calibration, but face limitations in dynamic visual bias mitigation. These include inability to capture real-time visual-textual incongruence, dependence on predefined gender bias taxonomies, and degraded cross-modal alignment with emergent bias patterns. To address these challenges, we propose ViD, a causally-inspired framework that analyzes attention mechanisms across five distinct patterns, revealing confounding effects from strong language priors. ViD demonstrates that visual-to-language cross-attention effectively suppresses bias while preserving general reasoning capabilities and text generation quality. ViD incorporates dual mechanisms: backdoor adjustment counters strong language priors, while refined token selection in decoding layers optimizes processing. This enhances model robustness and inference efficiency. Our integrated approach significantly mitigates gender bias across multidimensional social attributes in LVLMs, improving visual grounding and output fairness. Cross-benchmark validation shows ViD reduces gender bias by 14.7% on single-attribute evaluations (FACET) and achieves significant improvements on image captioning tasks (MS COCO), with gender bias score improving from 0.6708 to 0.9978 for LLaVA. Crucially, these improvements require no additional training overhead, making ViD a scalable and practical solution for bias mitigation in LVLMs.
Read the full abstract

All authors Zhipeng Zhao, Zhaoqiang Wei, Peishun Liu, Youwei Zhao, Ruichun Tang

Multimedia · Cross-listed from cs.CV

What Do Hallucinations Reveal About Multimodal Reasoning? Diagnosing Visual Grounding Failures via Contrastive Decoding Probes

Zhipeng Zhao, Wenxu Wang, Peishun Liu et al. (+1 more)

When strong multimodal models are widely available, progress requires new scientific methodologies beyond benchmark scores—using models as instruments for understanding behavior. We address this by asking: can we use large vision-language models (LVLMs) as experimental instruments for studying their own failure dynamics? Focusing on visual hallucination, we introduce SAFE, a training-free decoding framework that contrasts visually-grounded and vision-ablated generation paths to produce a token-level contrastive grounding score that identifies when the model favors linguistic priors over visual evidence. This signal serves dual roles: as a practical proxy for detecting visually-ungrounded tokens, and as the basis for decoding-time penalties. Our analysis yields three empirical observations: visual dependency decays over generation, hallucinations co-occur in temporal clusters, and early intervention reduces clustering without substantially degrading fluency. On MMHalBench, SAFE substantially outperforms all compared baselines; results elsewhere are more mixed. We argue that designing contrastive probes exemplifies a broader mission: using models as instruments for scientific understanding. Code: https://github.com/zhaozhipeng1997/SAFE_public.
Read the full abstract

All authors Zhipeng Zhao, Wenxu Wang, Peishun Liu, Ruichun Tang