Peer Revenue Publish or profit

Papers

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

Computer Science Multimedia

cs.MM Watch Multimedia

Thursday 13 August

Multimedia · Cross-listed from cs.SD

Alignment Drift in Single-Model Speculative Decoding for ASR: Mechanism, Correction, and Cost

Xinyu Wang, Huapeng Zhou, Ziyu Zhao et al. (+5 more)

Speculative decoding speeds up generation by letting a cheap draft propose several tokens that a target model checks in one pass. In the single-model form, the draft is a lightweight module attached to the target rather than a separate model. Applying this design to Automatic Speech Recognition (ASR) introduces an extra problem. The draft can read the whole audio at every step, yet its proposals get worse as it runs on its own. Access is not localization. The accepted text keeps the transcript position explicit, but the draft must also track the changing audio position. In the primary matched comparison, per-step audio access changes the first proposal modestly but roughly doubles later-proposal acceptance. Fixed-width windows show that the audio position explains part of this gap. A correctly placed window recovers continuation, while an equally narrow window at the wrong position reduces it. Late-draft median error reaches 21 frames in the hardest reported condition, while target attention during verification stays within a 2-frame median. We test two ways to reduce this drift. The first reads the audio position from verification attention and uses it to guide the next draft round. It saves time only when the extra accepted tokens offset the readout cost. The second is AnchorDraft, which teaches the draft to track the audio position during training without changing the inference graph. The trained draft improves end-to-end speed at both tested target scales. These results show that ASR self-speculation depends on token prediction, audio-position tracking, and draft cost.
Read the full abstract

All authors Xinyu Wang, Huapeng Zhou, Ziyu Zhao, Silin Meng, Ke Bai, Dongming Shen, Xiao-Wen Chang, Alex Smola

Wednesday 12 August

Multimedia · Cross-listed from eess.IV

LoopVSR: A Loop Engineering Framework for Automated Repair of Visual Speech Recognition Inference Pipelines

Fei Qin, Bowen Zhang, Chao Fan et al. (+2 more)

Visual speech recognition (VSR) recovers speech from lip movements when audio is noisy or unavailable. Its multi-stage inference pipeline spans video decoding, mouth-region extraction, preprocessing, model invocation, and decoding, where upstream failures can mask downstream faults. Pipeline maintenance therefore still relies largely on predefined checks and manual debugging. We propose LoopVSR, a Loop Engineering framework that enables a code agent to automatically diagnose and repair VSR inference pipelines using end-to-end execution evidence. It couples constrained repository-level diagnosis and patching with an external controller that audits changes, runs real inference, and accepts or rolls back patches using failures and character error rate (CER). The resulting feedback loop returns newly observed exceptions, tensor statistics, and recognition errors to the agent, progressively exposing faults masked by upstream failures. On the CMLR VSR system, LoopVSR repairs all 11 main faults with 100% mean recovery, whereas the Static guard repairs 2 of 11 with 18.13% mean recovery. It also resolves three cascading tasks in seven accepted iterations and preserves recovery on an independent 200-video hidden set. These results demonstrate that LoopVSR enables measurable, end-to-end automated repair of VSR inference pipelines.
Read the full abstract

All authors Fei Qin, Bowen Zhang, Chao Fan, Pengcheng Luo, Genke Yang

Multimedia

MASCOT: Model-Aware Submodular Coverage for Composite-Attribute Text-to-Image Retrieval

Aaryan Sharma, Vishak Prasad C, Virendra Singh et al. (+1 more)

Vision-Language Models (VLMs) are highly effective in retrieving semantically relevant images. However, in practice, relevance alone is often insufficient. Systems must also achieve Result Diversification (RD) across composite attributes such as geography and time, a task for which precise control remains challenging. Current re-ranking methods, such as Multi-Source Determinantal Point Processes (MS-DPP), address this using manifold-based repulsion over similarity representations. Although this strategy is effective for broad exploration, it exposes a key limitation in manifold-based models: when subjected to diversity-decrease tasks on discrete metadata, they suffer substantial degradation in early-rank recall. To bridge this gap, we introduce MASCOT (Model-Aware Submodular Coverage for Composite-Attribute Text-to-Image Retrieval). Instead of relying on manifold repulsion, MASCOT formulates multi-attribute diversity as a resource allocation problem, projecting attributes into a soft-binning space weighted by query-driven importance. Averaged across the three PixelProse diversity-decrease tasks, MASCOT preserves an early-rank recall (R@10) of 88.58%, while MS-DPP retains 67.63%. The margin widens under composite constraints: on PP_geo_hour, where temporal and geographic diversity must be suppressed simultaneously, MS-DPP's recall collapses from 0.9737 to 0.4931 and its top-ranked result degrades to R@1 = 0.23, while MASCOT holds R@10 = 0.9410 and R@1 = 0.7202 at a diversity metric above the unconstrained baseline. We do not claim uniform superiority: on aggregate diversity-relevance scores our own simpler ablations attain higher harmonic means on all three decrease tasks, and MASCOT's advantage is specific to recall beyond rank 1 under composite constraints.
Read the full abstract

All authors Aaryan Sharma, Vishak Prasad C, Virendra Singh, Ganesh Ramakrishnan

Multimedia · Cross-listed from cs.CV

Beyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence

Aman Tyagi, Hemanth Boinpally, Jonathan Chen et al. (+2 more)

Modern black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation, yet their lack of fine-grained control and reliability presents significant challenges in professional workflows. Their inherent stochasticity causes minor variations in textual prompts or hyperparameters to yield drastically different outputs often necessitating inefficient, brute-force trial-and-error processes. To address these limitations, we introduce the “Agentic Self-Improvement" framework, which reframes video synthesis into a closed-loop, goal-directed optimization. Our framework systematically navigates the generation parameter space using a novel two-stage approach. In the first stage, an iterative prompt optimization loop uses a multimodal Large Language Model (mLLM) to refine the input prompt. This refinement implements two automated evaluations: Davidsonian Scene Graph (DSG) queries ensure semantic adherence, and Common Mistake Questions (CMQ) for artifact detection. At the second stage, we use Bayesian optimization to efficiently co-optimize stochastic seeds and CFG scales. This search is guided by a suite of quality metrics, including the novel Video-Text Adherence (VTA) score derived from the DSG and CMQ evaluations. Our framework significantly outperforms unguided search methods: in human preference studies, videos generated via our agentic approach were strongly preferred over baseline outputs, achieving win rates up to 69%. This work provides a practical and extensible methodology for enhancing the predictability and control of state-of-the-art video generation models, moving the field beyond speculative curiosities toward reliable, production-ready tools.
Read the full abstract

All authors Aman Tyagi, Hemanth Boinpally, Jonathan Chen, Douglas Gebert, Steven Hickson

Multimedia · Cross-listed from cs.CV

HAMP-LIC: Hessian-Aware Mixed-Precision Post-Training Quantization for Learned Image Compression

Yuefeng Zhang

Use this plain-text version for the arXiv abstract field: Learned image compression (LIC) models achieve strong rate-distortion performance but are hindered by high computational complexity and encoding-decoding mismatches across heterogeneous hardware platforms. Uniform fixed-precision quantization alleviates these issues but suffers severe quality degradation at low bit widths because it ignores differences in the quantization sensitivities of individual layers. To enable efficient and accurate low-bit deployment of pretrained LIC models, we propose HAMP-LIC, a Hessian-aware mixed-precision post-training quantization (PTQ) framework with a four-stage optimization strategy. First, block-wise sensitivity is estimated from the Hessian trace to capture second-order importance. Second, a task-aware refinement module adjusts these sensitivities by jointly considering quantization distortion and rate-distortion performance. Third, guided by the refined sensitivity profile, bit widths are allocated under a global model-size constraint to balance efficiency and reconstruction quality. Finally, block-wise reconstruction using a small calibration set further suppresses quantization error. Experiments on representative LIC models, including Minnen2018 and Cheng2020, demonstrate that HAMP-LIC achieves up to 4.85x model compression with as little as 0.59% BD-rate loss. It consistently outperforms existing fixed- and mixed-precision PTQ methods across multiple datasets while completely eliminating cross-platform encoding-decoding errors.
Read the full abstract

Multimedia · Cross-listed from eess.IV

ResPCC: A Loss-Resilient Neural Point Cloud Codec over Lossy Networks

Xueqin Niu, Mufan Liu, Yifan Wang et al. (+3 more)

Point cloud compression (PCC) is critical for efficient storage and transmission of 3D data. While recent learning-based PCC methods achieve good rate-distortion (R-D) performance, they generally rely on ideal transmission conditions. In practice, packet loss is a common issue and can severely distort latent features, causing coordinate drift and geometric degradation. To address this challenge, we present ResPCC, the first end-to-end neural point cloud codec designed to offer intrinsic resilience against data loss. Our framework is loss-rate-aware and adapts to diverse packet loss conditions. At the encoder, we introduce a Condition-Adaptive Latent Modulation (CALM) module to adjust latent feature distributions according to the perceived loss rate, as well as a Spatial-Channel Interleaving (SCI) mechanism that transforms channel-wise data extinction into spatially scattered element-wise missing patterns. At the decoder, we develop a Mask-Aware Graph-based Latent Restoration (MGLR) module, followed by a Dictionary-based Refinement (DBR) stage to recover corrupted features and align them with canonical priors. Evaluations on ShapeNet and SemanticKITTI under 5% to 30% packet loss rates show that ResPCC consistently delivers superior stability and R-D performance over baselines. Our framework maintains high reconstruction fidelity under lossy conditions, providing a reliable solution for 3D data transmission over practical networks. Code is available at https://github.com/starrynight314/ResPCC.
Read the full abstract

All authors Xueqin Niu, Mufan Liu, Yifan Wang, Le Yang, Jun Sun, Yiling Xu

Multimedia · Cross-listed from cs.CV

Learning from Multimodal Pseudo-Labels for Robust Open-Vocabulary Instance and Panoptic Segmentation

Duy Tran Thanh, Yeejin Lee and Byeongkeun Kang

This work addresses the challenge of open-vocabulary instance segmentation (OVIS) and open-set panoptic segmentation (OSPS), which aim to recognize both predefined and unseen object categories without exhaustive human annotations. Existing methods often suffer from noisy pseudo-masks, limited visual-textual grounding, and difficulty handling synonyms or out-of-vocabulary (OOV) words. To overcome these challenges, we propose a multimodal framework that leverages pre-trained vision-language models for automatic pseudo-label generation, CLIP-guided synonym filtering, and GPT-based caption reconstruction. In our target-vocabulary-assisted pseudo-labeling setting, the framework first constructs pseudo segmentation masks, descriptive captions, and semantically aligned synonym sets using Grounded SAM, LLaVA, and CLIP, providing multimodal supervision without manual annotation. We then enhance visual-textual alignment through three complementary training objectives: an extended grounding loss that incorporates visually grounded synonyms, a semantic consistency loss, and a generative caption reconstruction loss. Extensive experiments on the COCO dataset demonstrate that the proposed method consistently outperforms previous state-of-the-art approaches under this protocol, achieving substantial improvements on both OVIS and OSPS benchmarks.
Read the full abstract

Multimedia · Cross-listed from cs.SD

Dialogue-Aware Video-to-Music Generation Using Public Domain Film Collections

Haven Kim, Zachary Novack, Julian McAuley et al. (+1 more)

Video-to-music generation has drawn growing interest for its role in conveying the emotion of visual media, including film. Progress in the field, however, is hampered by a reproducibility gap: models are often trained on crawled corpora referenced through YouTube URLs that may be deleted, with the underlying data often difficult and time-consuming to retrieve. To address this, we introduce the Open Screen Soundtrack Library version 2 (OSSL-v2), a self-hosted corpus of 34,343 video clips totaling 246.4 hours, sourced from public-domain films. Unlike crawled corpora, OSSL-v2 is reproducible (i.e., not subject to link rot) and copyright-conscious, yet still large enough to train functional video-to-music models. We then use this film-domain corpus to study dialogue as a conditioning signal for video-to-music generation, motivated by the close temporal coupling between film music and on-screen speech. Specifically, we augment existing models' video cross-attention with a time axis and modulate it frame-by-frame with the dialogue track. Evaluated on both public-domain and commercial films, our approach shows improvement over the state-of-the-art baselines. The dataset is available at https://huggingface.co/datasets/McAuley-Lab/OSSL-v2.
Read the full abstract

All authors Haven Kim, Zachary Novack, Julian McAuley, Hao-Wen Dong

Tuesday 11 August

Multimedia · Cross-listed from cs.AI

MobileMem: Learning from a Year of Mobile Experiences

Xinle Deng, Yida Xue, Xiangyuan Ru et al. (+16 more)

The next generation of AI agents is increasingly moving beyond systems that answer isolated questions toward persistent personal assistants that can understand, remember, and continuously learn from users' experiences. Such assistants require long-term memory to accumulate and leverage user-specific experiences over time, yet existing benchmarks remain inadequate for realistic mobile settings, where experiences are heterogeneous, multimodal, evolving, and deeply personal. We introduce MobileMem, a benchmark and framework for studying on-device long-term memory, grounded in a year-scale collection of mobile experiences. MobileMem employs a knowledge-grounded synthesis pipeline to construct coherent and temporally consistent long-horizon trajectories from user-app sessions. It provides complementary text and multimodal settings covering multi-hop and temporal reasoning, knowledge updating, and implicit preference inference. Specifically, MobileMem enables agents to remember the past, understand the present, and adapt to the future. By modeling experiences rather than isolated facts, MobileMem moves memory beyond information retrieval toward experiential intelligence for continuous personal learning.
Read the full abstract

All authors Xinle Deng, Yida Xue, Xiangyuan Ru, Yijun Chen, Buqiang Xu, Mingjun Mao, Xinjie Liu, Haoming Xu, Shuofei Qiao, Mengru Wang, Chen Jiang, Yuchen Eleanor Jiang, Lizhong Wang, Jason Wang, Li Zeng, Haofen Wang, Guilin Qi, Huajun Chen, Ningyu Zhang

Multimedia · Cross-listed from cs.SD

Qwen-MusicAVQA-7B: A Multimodal Model for Music Audio-Visual QA

Maryam Dehdashti

A common approach to adding audio to a vision-language model is to train or adapt a large omni-modal system. We show that a lightweight alternative can be highly effective for music audio-visual question answering (AVQA). Qwen-MusicAVQA-7B connects a frozen Whisper encoder to Qwen2-VL-7B-Instruct through learned linear projections. The same frozen encoder processes both the video's music track and a TTS-spoken question through separate projectors, while the language model fuses visual frames, music, and question audio through pretrained self-attention, with no task-specific fusion network. On MUSIC-AVQA, our system reaches 96.0% +/- 3.9% accuracy across three independent training seeds on the 7,402-question available-video test subset. Our central finding is that downstream accuracy tracks how much fine-grained local temporal information the audio representation preserves. In a matched 32-token comparison, a stride-pooled Whisper frame sequence outperforms a globally pooled PANNs representation expanded to the same budget by 26 percentage points, even though PANNs sees at least as much audio and uses a far larger projector. The effect is not simply sequence versus vector: within Whisper alone, reducing temporal resolution at a fixed token budget costs a comparable amount. Under matched data and inputs, fine-tuned Qwen2.5-Omni-7B reaches 80.9%, against 95.9% for our 30 s variant; because the systems differ in backbone and adaptation, this is a system-level comparison. Accuracy remains high on sampled head and tail splits of the rephrased MUSIC-AVQA-R benchmark (96.5% and 95.6%). Because both encoders stay frozen and the music features are cached, the entire adaptation is cheap to train: the complete two-stage AVQA run takes approximately 5 hours on a single A100 80GB, and every run reported here fits on that one GPU.
Read the full abstract

Multimedia · Cross-listed from eess.IV

Geometry-Based Compression of Plenoptic Point Clouds

Davi R. Freitas, Gustavo L. Sandri and Ricardo L. de Queiroz

Plenoptic point clouds (PPC) are novel data structures that represent the light from different viewing directions in order to provide a higher degree of realism to regular point clouds. This is achieved by associating each point to multiple colors instead of a single one. Here, we present a method to efficiently compress the attributes of a PPC, consisting of a Karhunen-Loève transform over the color attributes followed by multiple attribute coders with intra prediction capability. This compression scheme can be incorporated within the MPEG's geometry-based PCC (G-PCC) standard, using any of G-PCC's existing solutions for attribute coding. Compression performance assessment using PPCs of different spatial resolutions reveals competitive results in comparison to existing methods, such as RAHT-based or video-based PCC solutions. We believe our coder to be the new state of the art.
Read the full abstract

Multimedia · Cross-listed from eess.AS

MAJEPPA: Morphing and Assessing in a Unified Piano Performance Space

Jinwen Zhou, Huan Zhang, Weixi Zhai et al. (+3 more)

We present MAJEPPA, a self-supervised framework to learn piano performance representations that span the full skill spectrum, from beginner practice sessions to virtuoso concert recordings. We curate the MAJEPPA dataset, comprising ~4,000 annotated recordings across six expertise levels and six recording contexts. We adapt a single pre-trained MIDI autoregressive model with a joint objective: next-token prediction learns score-conditioned performance generation at various skill levels, while InfoNCE and supervised contrastive losses align abstract score and performance representations in a joint embedding space. The proposed model both generates and understands performances in a unified framework. By introducing the EVPMR benchmark, a suite of downstream tasks spanning quality assessment, competition ranking, mistake and technique classification, we evaluate the learnt representations, demonstrating progress towards a real-world model for the piano performance space.
Read the full abstract

All authors Jinwen Zhou, Huan Zhang, Weixi Zhai, Jinhua Liang, Aidan O. T. Hogg, Simon Dixon

Multimedia · Cross-listed from cs.CV

R4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric Video

Ke Ma, Yamin Mao, Weiming Li et al. (+5 more)

Long-horizon egocentric video is a rich substrate for wearable AI assistants, but object-centric questions such as where an item was moved, when it last changed state, or why it was relocated remain difficult because caption- and transcript-based memories rarely preserve persistent object identity or structured spatial change. Existing long-video QA methods mainly emphasize temporal grounding and clip retrieval, while prior 3D scene-graph methods typically assume stronger geometry than free-motion wearable RGB video provides, including point clouds, RGB-D input, posed views, sparse reconstruction, or reconstructed scenes. R4DSG introduces a relative 4D scene graph memory for long egocentric video. Instead of storing raw graph sequences, R4DSG converts video into compact queryable memory entries indexed by time, place, persistent objects, anchor-relative change, and local interaction context. The main idea is to separate stable anchors from dynamic objects, maintain persistent object identity across frames, and represent object state through anchor-relative transitions rather than a globally aligned world model. Built on recent RGB-only advances in promptable video segmentation, temporal propagation, and relative 3D lifting, the method produces a retrieval-ready memory directly usable for long-horizon question answering. Evaluation on a 255-question object-related subset from EgoLifeQA shows, under question-only retrieval, a 6.7-point overall gain over EgoRAG-Text and a 12.5-point gain on when questions, which highlights the value of temporally organized object memory. These results position relative 4D scene graphs as a practical memory substrate for wearable assistants, AR systems, and embodied multimedia agents. GitHub Page: https://dualtransparency.github.io/R4DSG/.
Read the full abstract

All authors Ke Ma, Yamin Mao, Weiming Li, Shuai Tan, Yijie Zhong, Hao Chen, Haofen Wang, Meng Wang

Multimedia · Cross-listed from cs.NI

Media-over-Multipath-QUIC for Realtime Video Applications

Tanya Shreedhar, Zuji Zhou, Nitinder Mohan et al. (+1 more)

Multipath transports place a client's WiFi, cellular, and satellite networks under one connection, yet real-time video gains little from them. The scheduler that assigns packets to paths sees only bytes, so it cannot tell a keyframe that anchors a second of video from an enhancement frame whose loss costs one image. We show that the limiting factor is not a shortage of path diversity but the absence of a channel through which the application can name what the transport cannot see. Media over QUIC Transport (MoQT), already deployed on production CDNs, carries media as named Objects, and relays forward each Object's metadata without interpreting it. The knowledge the scheduler lacks therefore already flows through the subscriber's relay. We present MoMQ, a MoQT extension that turns this metadata into path decisions. Applications and relay operators install declarative rules at the edge relay that match Object metadata and express delivery preferences against labeled paths. The relay evaluates the rules mechanically, so it acts on video semantics while containing no video logic. On a live testbed spanning Starlink and WiFi, four rules cut P99.9 frame completion time from 384.7 ms under the best transport-only scheduler to 114.1 ms and reduce the required playback buffer by 61.5%. MoMQ is the only configuration that meets the 150 ms interactive latency target. Across relays in two countries and subscribers on two continents, the same rules apply unchanged and retain their advantage wherever the paths remain disjoint.
Read the full abstract

All authors Tanya Shreedhar, Zuji Zhou, Nitinder Mohan, Fernando Kuipers

Multimedia · Cross-listed from cs.CV

MMArt: A Multi-Perspective Multimodal Dataset for Visual Art Understanding

Shuai Wang, Wangyuan Ding, Yixian Shen et al. (+5 more)

Recent vision-language models demonstrate impressive general visual understanding, yet their art interpretation remains shallow: they describe surface content but struggle with formal analysis, grounded historical interpretation, or affective characterization. We argue this is not only a model but also a dataset limitation. Existing art datasets are single perspective resources, where no dataset provides narrative, formal, emotional, and historical perspectives simultaneously for the same artworks. We introduce MMArt, a large-scale dataset of 74,234 WikiArt paintings, each annotated with four independently annotated perspectives plus a harmonized unified caption, produced by specialized vision-language models or human annotation and validated through complementary quality evaluations. Two complementarity analyses establish that perspectives encode genuinely distinct information. A generative analysis shows that formal analysis descriptions best preserve compositional style, and historical descriptions carry strong affective signal in reconstructed images. A discriminative retrieval analysis reveals task-asymmetry: narrative descriptions drive retrieval (R@1 = 44.0%), while formal descriptions, strongest for reconstruction, are nearly nondiscriminative at retrieval scale (R@1 = 7.8%). Leave-one-out analysis further confirms that historical descriptions are the least replaceable perspective across both tasks. Together, the two analyses establish that no single perspective suffices for all tasks, directly motivating MMArt multi-perspective design. The dataset, code, and additional information are available at https://shuaiwang97.github.io/MMArt/.
Read the full abstract

All authors Shuai Wang, Wangyuan Ding, Yixian Shen, Jia-Hong Huang, Stevan Rudinac, Monika Kackovic, Nachoem Wijnberg, Marcel Worring

Multimedia · Cross-listed from cs.HC

Visual-to-Haptic Augmentation in XR: A Wearable Glove for Perceptual Grounding in Multimodal Interaction

Faisal Mohd, Hamdi Elsaddik, Erhan Baturay Onural et al. (+3 more)

Extended Reality (XR) systems increasingly deliver high-fidelity visual and auditory experiences, yet tactile perception remains comparatively underutilized as a modality for enriching embodied interaction. This work presents a visual-to-haptic wearable glove and a feature-based visual-to-haptic mapping algorithm that translates spatial and temporal visual features from images and videos into distributed vibrotactile patterns. The proposed method extracts motion, edge, and brightness cues and fuses them into actuator-level intensity maps aligned with a 29-actuator glove arranged in a five-by-seven layout. The system is implemented through a modular four-layer architecture comprising the XR environment, media content handling, visual-to-haptic processing, and embedded haptic hardware. A within-subject user study (N = 20) compared visual-only interaction with visual-plus-haptic augmentation across texture-based and dynamic video scenarios. Results indicate that tactile augmentation significantly improves perceived realism in dynamic video scenarios and enhances immersion and visual-tactile correspondence across conditions, with stronger and more consistent effects observed for dynamic visual events. While the current implementation operates in a single-user, offline-synchronized configuration, the findings demonstrate that vision-driven tactile augmentation can function as a perceptual enhancement layer within multimodal XR systems. Such a layer may provide a foundation for future socially enriched XR environments where coherent multisensory grounding supports higher-level interaction and communication.
Read the full abstract

All authors Faisal Mohd, Hamdi Elsaddik, Erhan Baturay Onural, Jihong Zhang, Fedwa Laamarti, Abdulmotaleb El Saddik

Monday 10 August

Multimedia · Cross-listed from cs.CV

Deep Analog: Open-Set Film Emulation with Reference-Conditioned 3D LUTs

Yitong Mu

Film emulation reproduces the look of an analog film stock on a new digital photograph. We target its open-set form – matching any reference film frame from a single example – with a 3D lookup table (LUT) predicted from that reference. Real-time image enhancement predicts per-image weights over a fixed bank of 3D LUTs and blends them. We show this is a gated mixture of experts and inherits its failure: trained end-to-end against reconstruction, the gate collapses onto a single expert, so a bank of K LUTs delivers the capacity of one. An entropy term, the enhancement-setting analogue of mixture-of-experts load balancing, restores utilization and recovers about 1 dB PSNR. The deeper constraint survives: a fixed LUT basis is closed-set, freezing the achievable looks at training time. We therefore discard the basis and predict a single 3D LUT as a residual from a reference image (StyleLUTNet), trained by self-supervision on procedurally generated color transforms. The conditional design removes the gate and generalizes open-set to unseen film stocks without paired data or retraining. Around this color backbone we build Deep Analog, a film-emulation pipeline that adds histogram-based tone matching and a physics-informed optical renderer – multi-scale grain and per-channel halation driven by parameters an inverse network regresses from the reference. On 350 self-supervised pairs the color stage reaches 22.05 dB PSNR / 0.925 SSIM and the full pipeline 21.72 dB / 0.923; the color path runs in 5.2 ms at 1080p (192 FPS) and exports a portable .cube LUT for standard editing tools. A second degeneracy in conditional LUT training – residual-scale collapse – shares the root cause and yields a general principle: auxiliary regularization must stay subordinate to reconstruction.
Read the full abstract

Multimedia · Cross-listed from cs.CV

UniMod: Enhancing Multi-Modal Medical Diagnosis through Cross-Modality and Within-Modality Alignment

Zijian Gu, Weikai Lin, Shuang Zhou et al. (+2 more)

Multi-modal learning combining medical images and clinical text is promising for disease diagnosis. However, standard multi-modal training leads to shortcut learning: models exploit the easier modality (e.g., diagnostic cues in text) while neglecting harder-to-learn features (e.g., subtle visual patterns). We propose UniMod, a framework that mitigates shortcut learning by requiring each modality to predict the diagnosis on its own. It supervises image-only, text-only, and multi-modal classification simultaneously, so each modality must extract diagnostic features. We add cross-modality alignment for knowledge transfer and within-modality supervised contrastive alignment over same-diagnosis patients. On Harvard-Glaucoma, UniMod reaches 0.850 AUC, outperforming OGM-GE and Gradient Blending by 1.6-1.8%; on CheXpert Plus, it reaches 0.966 AUC, surpassing them by over 5%. UniMod also extends to 5-class multi-label diagnosis without architectural change, improving mean AUC by 0.097 over CGGM.
Read the full abstract

All authors Zijian Gu, Weikai Lin, Shuang Zhou, Zihan Chen, Song Wang

Multimedia · Cross-listed from cs.IR

Sequential Modality Dropout for Robust Multi-Modal Sequential Recommendation

Guanqun Yang and Wenlong Zhang

Multi-modal sequential recommenders assume every item carries every modality, but real product catalogs often miss images or text, and a model trained on complete data loses much of its recommendation accuracy when a modality is unavailable at serving time. We propose Sequential Modality Dropout (SMD): during training, each modality stream (image and text) is independently erased with probability p for an entire user interaction history, so the model learns to predict the next item without relying on any single modality. We measure robustness by retention, the fraction of a model's full-modality accuracy (HR@10) that survives when a modality is removed at test time. Across four backbones (MM-SASRec, IISAN, MISSRec, and fMRLRec) on four Amazon domains, SMD raises text retention by 1.0 to 3.2x at essentially no cost to full-modality accuracy; under an extreme 95% per-item missing rate, it retains 61% of HR@10 versus 22% without (a 2.8x improvement). An optional cross-modal reconstruction loss further lifts retention from 90% to 98% on a simple additive backbone under severe text missingness. SMD is a four-line, architecture-agnostic change that makes multi-modal sequential recommenders robust to the missing modalities they actually encounter in deployment.
Read the full abstract

Multimedia · Cross-listed from cs.RO

TAMS: Task-Aware Multi-View Adaptive Streaming for Wireless Telerobotic Manipulation

Zexin Deng, Zhenhui Yuan, Lu Tian et al. (+2 more)

Wireless telerobotic manipulation relies on timely multi-view video feedback, but the available uplink bandwidth is often limited and dynamic. This paper presents Task-Aware Multi-View Adaptive Streaming (TAMS), a system that allocates video bitrate according to the current manipulation phase. TAMS infers task phase from lightweight robot-side signals and prioritizes the camera view most relevant to the operator while preserving baseline visibility for secondary views. Experiments on a six-degree-of-freedom (6-DoF) teleoperation testbed under three constrained network conditions show that TAMS improves primary view Structural Similarity Index (SSIM), reduces task completion time, and increases trial success rate compared with equal and static allocation baselines. Under the most constrained bandwidth condition, TAMS reduces mean completion time from 68.9 s to 43.9 s relative to equal allocation and increases trial success rate from 48% to 71%. Code is available at: https://github.com/Dzxx623/TAMS.
Read the full abstract

All authors Zexin Deng, Zhenhui Yuan, Lu Tian, Subhash Lakshminarayana, Longhao Zou

Multimedia · Cross-listed from cs.CV

GRASP: Granularity-Aware Region Alignment and Semantic Prototype Learning for Fine-Grained Cross-Modal Understanding in Drone Views

Jiahui Cui, Yan Zhao, Kan Wei et al. (+4 more)

Fine-grained cross-modal understanding in drone views is essential for aerial vision-language navigation. However, the inherent wide field of view and overhead perspective of drone scenarios impose dual challenges on vision-language understanding. At the macro level, overwhelming background clutter in visual representations leads to Cross-Modal Focus Misalignment, where the model prioritizes global environmental similarities over specific object details. At the micro level, Visual Isomorphism creates ambiguity, where candidates share similar geometric structures yet differ only in subtle attributes. To address these challenges, we propose the Granularity-Aware Region Alignment and Semantic Prototype (GRASP) learning framework, enhancing discriminative capability through two synergistic strategies. Specifically, we introduce Region-Focused Alignment (RFA) to promote object-centric cross-modal alignment while suppressing background interference. Concurrently, to tackle visual isomorphism, we propose Semantic Perturbation Enhanced Matching (SPEM), which leverages a foreground-purified Semantic Prototype Codebook (SPC) to construct semantically perturbed negatives for fine-grained semantic discrimination. Extensive experiments on the GeoText-1652 benchmark and the unseen ERA dataset demonstrate that GRASP achieves competitive performance in drone-view fine-grained image-text retrieval, validating its effectiveness for cross-modal understanding in aerial scenarios. Our code implementation is available at https://github.com/UCAS-JC/GRASP.
Read the full abstract

All authors Jiahui Cui, Yan Zhao, Kan Wei, Enze Zhu, Peirong Zhang, Lei Wang, Yiru Wang

Multimedia · Cross-listed from cs.CL

Bridging the Gap Between Semantics and Reconstruction:Unifying Sign Language Translation and Production

Xiao Liu, Shiwei Gan, Yafeng Yin et al. (+5 more)

Recent advances in sign language (SL) research have shown a trend toward unifying multiple sign language understanding (SLU) subtasks, such as isolated sign language recognition (ISLR), continuous sign language recognition (CSLR), and sign language translation (SLT), within a single framework, leading to substantial progress. Meanwhile, sign language production (SLP), which generates sign sequences from text, has also attracted growing attention. This naturally raises an important question: can sign language understanding and production be unified within a single framework? Compared with unifying SLU subtasks, this problem is substantially more challenging. Existing SLU tasks largely share the same direction of mapping, namely from sign inputs to linguistic outputs, whereas SLT and SLP lie in opposite directions of sign-text mapping. A unified framework must therefore address two key challenges: (1) bridging the modality gap between continuous sign motions and discrete text tokens through a shared sign tokenizer that supports both linguistic abstraction and motion reconstruction; and (2) learning a single conditional autoregressive model that can take either sign or text as input and generate the corresponding target sequence in the opposite modality. To this end, we propose Uni-SLTP, a unified framework for SLT and SLP with two key components: (1) a shared sign tokenizer that converts sign sequences into discrete tokens and latent representations, capturing both semantic and reconstructive information; and (2) a unified autoregressive generation model that formulates both tasks as conditional sequence generation. Experiments on widely used public datasets show that Uni-SLTP achieves superior motion accuracy for SLP while maintaining competitive SLT performance.
Read the full abstract

All authors Xiao Liu, Shiwei Gan, Yafeng Yin, Jiaxin Yin, Bowen Guo, Yaqi Sun, Zhiwei Jiang, Lei Xie

Multimedia · Cross-listed from cs.SD

MusicLayout: Explicit Structural Planning for Controllable Text-to-Music Generation

Shuyu Li, Kejun Zhang, Jiahe Lei et al. (+5 more)

Text-to-music generation has advanced rapidly, but current systems still rely primarily on global text prompts, leaving the structural organization of generated music implicit and difficult to inspect, control, or revise before audio generation. To address this issue, we introduce MusicLayout, an explicit intermediate representation for controlling musical structure in text-to-music generation. MusicLayout describes a musical piece as a time-aligned layout of sections, textures, repetitions, variations, and instrument-level arrangements, serving as an interpretable planning layer between textual intent and the generated music. We integrate MusicLayout into a text-to-music framework built on a unified autoregressive formulation, where the model first generates a MusicLayout representation and subsequently predicts audio tokens conditioned on this representation within a single sequence. The resulting MusicLayout can be inspected and modified prior to audio generation, providing a mechanism for layout-level structural control. We evaluate MusicLayout through layout-conditioned generation, layout manipulation experiments, and matched-data ablations, providing evidence that explicit layout planning can improve long-range structural organization and support layout-level control. We have released the implementation as open source on GitHub at https://github.com/XaryLee/MusicLayout.
Read the full abstract

All authors Shuyu Li, Kejun Zhang, Jiahe Lei, Shulei Ji, Zihao Wang, Jiaxing Yu, Wanying Wu, Lei Wang

Multimedia · Cross-listed from cs.HC

AI-Guided Learning: Research on Knowledge and Skill Acquisition Support Methods Using Deep Learning Audio-Video Processing Techniques

Kazuki Kawamura

Audio and video have become major learning media, but learners face two persistent challenges: the time cost of consuming long-form content sequentially and the lack of scalable feedback for imitation-based skill acquisition. This dissertation proposes an AI-guided learning framework that supports three interconnected stages: Consume, Understand, and Imitate. It develops and evaluates three systems. AIxSpeed dynamically adjusts audio playback speed at the phoneme level using speech-recognition-model confidence as a proxy for listening difficulty. FastPerson generates multimodal video summaries that preserve visual and auditory information and lets learners switch between summarized and full versions by chapter. Profy learns proficiency from largely unannotated speech data and visualizes classifier-relevant regions and model-derived acoustic distances to support pronunciation practice. Technical and user evaluations show that AIxSpeed achieved average playback factors of 1.30x on LibriSpeech and 1.29x on UME-ERJ and received higher mean opinion scores than matched constant-speed playback; FastPerson reduced viewing time by 53% with no statistically significant difference in quiz scores compared with normal playback; and Profy showed an observed improvement in pronunciation intelligibility, with non-overlapping pre- and post-practice confidence intervals. Together, these systems demonstrate how deep learning can support efficient content consumption, multimodal understanding, and repeated skill practice while retaining learner access to the original material.
Read the full abstract

Sunday 9 August

Multimedia · Cross-listed from eess.IV

MD2G-Cast: Relay-Coordinated Multicast for Scalable Volumetric Streaming over MoQ

Ruonan Chai, Yisu Wang, Zili Meng et al. (+1 more)

Volumetric streaming remains difficult to scale because receivers with overlapping fields of view are often served independently, causing repeated transmission of shared content. We present MD2G-Cast, a relay-coordinated multicast framework over Media over QUIC with an application-aware control layer for scalable multi-user volumetric delivery. MD2G-Cast jointly uses viewing overlap, receiver capability, and bandwidth conditions to form reusable multicast groups, share common Base content, and selectively admit Enhanced delivery. We formulate grouping and Enhanced admission as a sequential control problem, realize it with Proximal Policy Optimization (PPO), and train a compact relay model with teacher guidance for Enhanced admission. We implement MD2G-Cast with real MoQ processes and evaluate it with real access and 6DoF viewing traces for up to 100 users. At 20 and 100 users, MD2G-Cast keeps the receiver-side $P_{99}$ delivery interval below 40 ms across all seven access profiles, while Rolling reaches the 500 ms reporting cap in most cases. Across the evaluated user scales, MD2G-Cast achieves the highest or tied-highest mean system utility under homogeneous access and the highest mean utility under heterogeneous access, while reducing aggregate link load by about 27% relative to Clustering at 100 users. A matched relay-control ablation separates the control structure from its optimizer, showing that random feasible actions reduce utility while deterministic control remains competitive with PPO. Together, the results support relay coordination and selective Enhanced admission, rather than a particular policy optimizer, as the central design contribution.
Read the full abstract

All authors Ruonan Chai, Yisu Wang, Zili Meng, Dirk Kutscher

Multimedia · Cross-listed from cs.AI

Deferred Audio Pruning with Local Audio-Visual Dynamics for Omni-LLMs

Kyeongyoon Lee, Hongyeob Kim, Youngeun Kim et al. (+1 more)

Omni-modal LLMs jointly process audio, video, and text, but long multimodal sequences incur substantial prefill and KV-cache costs. Existing omni-modal compression methods primarily focus on pre-LLM token reduction, leaving modality-specific compression across the LLM boundary underexplored. We propose A-PACK, a two-stage framework that defers audio pruning until query-conditioned multimodal interactions emerge. Our analysis shows that audio exhibits higher task-relevant information density and representational diversity per token than video. We further find that local audio-visual dynamics provide a more effective cue for visual selection than token-wise matching. We therefore preserve audio and compress video with local dynamics before the LLM, then progressively prune low-relevance audio and visual tokens and their KV-cache entries inside the LLM. Across four benchmarks on Qwen2.5-Omni-7B/3B, A-PACK achieves the strongest average performance among the evaluated prior methods while reducing prefill FLOPs by up to 78% and improving decoding throughput by up to 2.21x.
Read the full abstract

All authors Kyeongyoon Lee, Hongyeob Kim, Youngeun Kim, Sungeun Hong

Multimedia · Cross-listed from cs.LG

Loss-Resilient Wireless Video Token Communication over Block Fading Channels

Bingyan Xie, Yongjeong Oh, Zihan Chen et al. (+3 more)

Video token communication represents video content as discrete tokens that differ in their importance to reconstruction and exhibit temporal dependencies. When these tokens are packetized for wireless transmission, block fading can cause multiple important or correlated tokens to be lost together, severely degrading video reconstruction. To address this issue, we propose a loss-resilient wireless video token communication (WVTC) framework. WVTC evaluates token importance from the intrinsic predictive structure of video tokens, assigning high priority to structural I-tokens and measuring P-token importance by temporal neighborhood novelty. A shuffled mixed I/P-token packetization scheme disperses structural anchors and correlated temporal regions across packets. Using only current block channel state information, an online scheduler jointly considers packet importance density, MCS-dependent decoding reliability, block capacity, and importance concentration when allocating packets to fading blocks. At the receiver, a fine-tuned detokenizer reconstructs missing content from surviving tokens without retransmission. Numerical results demonstrate improved perceptual quality and more graceful degradation under increasing packet error rates.
Read the full abstract

All authors Bingyan Xie, Yongjeong Oh, Zihan Chen, Jihong Park, Yongpeng Wu, Wenjun Zhang

Multimedia · Cross-listed from cs.CV

MotionCraft: Latent World Modeling with Sparse Attention for Visual Upscaling

Rong Fu, Chunlei Meng, Yangchen Zeng et al. (+9 more)

Video super-resolution (VSR) aims to recover high-fidelity high-resolution videos from low-resolution inputs and is central to applications ranging from mobile capture to streaming and archival restoration. Existing approaches trade off among local-detail fidelity, long-range spatio-temporal modeling, perceptual realism, and efficiency: convolutional alignment techniques preserve local structure but suffer when motion is large or degradations are complex; transformer-based methods capture long-range dependencies yet require architectural or algorithmic adaptations to remain computationally feasible; and recent latent or diffusion-based generators synthesize rich texture but require specialized temporal constraints to maintain coherence. We present MotionCraft, a controllable VSR framework that formulates restoration as motion-aware latent state prediction inspired by world models and integrates adaptive sparse attention with an explicit user-accessible control interface. MotionCraft combines robust motion fusion, a Latent World Transformer that balances locality and targeted non-local interactions, and a compact conditional decoder to deliver temporally consistent, high-quality reconstructions under streaming constraints. Empirical evaluations show that MotionCraft achieves strong reconstruction and perceptual performance while enabling predictable trade-offs between temporal smoothness and reconstruction fidelity.
Read the full abstract

All authors Rong Fu, Chunlei Meng, Yangchen Zeng, Xiaowen Ma, Yongtai Liu, Wangyu Wu, Shuo Yin, Zijian Zhang, Sicheng Li, Yingrui Ji, Chenhao Wang, Simon Fong

Saturday 8 August

Multimedia · Cross-listed from cs.HC

Dramarrator: Object-Based Audio Editing for Audio Drama Production from Books

Karim Benharrak, Oriol Nieto, Bryan Wang et al. (+2 more)

Audio dramas weave dialogue, sound effects, and music into immersive stories. Creators often adapt books into audio dramas, but this process remains labor-intensive, requiring them to interpret source material, author scripts, generate audio assets, and assemble them on a timeline. Because story elements like characters and scenes manifest across many interdependent assets, a single change can ripple into manual updates across the entire project. We present Dramarrator, an audio drama authoring tool built around object-based audio editing, where these story elements are represented as editable objects. Dramarrator extracts these objects from a book, generates linked audio assets (speech, sound effects, and music), and composes a multi-track audio drama. Edits to any object (e.g., a character's voice) automatically propagate to all dependent assets. In a user study with professionals (N=8), Dramarrator significantly lowered task load when creating audio dramas. A listener study (N=300) shows that creator-refined output from Dramarrator approaches the quality of productions made with existing professional tools, and an exploratory study (N=3) suggests object-based editing lowers entry barriers and generalizes beyond audio dramas.
Read the full abstract

All authors Karim Benharrak, Oriol Nieto, Bryan Wang, Zeyu Jin, Amy Pavel

Multimedia · Cross-listed from cs.CV

Your VLM Already Knows When: Training-Free Temporal Grounding by Asking Yes or No

Ji Huang, Barry Devereux and Hui Wang

Multimodal LLMs that recognise events reliably still fail to say when they happen. Prompted for timestamps, strong VLMs reach as little as $3.8\%$ R@0.5 on Charades-STA, and $77$ to $80\%$ of their wrong predictions carry low output entropy: the models are confidently wrong, and entropy-based error detection stays below a random classifier. We show that this failure lives in the task interface, not in perception. Holding the weights fixed, replacing timestamp regression with a coarse-to-fine scan of binary questions, whose first-token probabilities are consumed only as a ranking, raises R@0.5 by $28$ to $50$ points across four frozen backbones. The residual failures decompose into two measurable axes: a perception axis that moves with the backbone, and a geometry axis that is analytically predictable from the ratio of the output-window and event widths. FV-Action, the training-free method built on this analysis, reaches $56.8\%$ R@0.5 on Charades-STA, above the same backbone's native grounding pipeline and the strongest training-free result on this benchmark; it surpasses every TVG-trained model evaluated zero-shot on TACoS, and improves over direct prediction on ActivityNet Captions and QVHighlights, with no temporal supervision at any stage.
Read the full abstract