Accurate dialogue description in audiovisual video captioning is crucial for downstream understanding and generation tasks. However, existing models generally struggle to produce faithful dialogue descriptions within audiovisual captions. To mitigate this limitation, we propose DiaDem, a powerful audiovisual video captioning model capable of generating captions with more precise dialogue descriptions while maintaining strong overall performance. We first synthesize a high-quality dataset for SFT, then employ a difficulty-partitioned two-stage GRPO strategy to further enhance dialogue descriptions. To enable systematic evaluation of dialogue description capabilities, we introduce DiaDemBench, a comprehensive benchmark designed to evaluate models across diverse dialogue scenarios, emphasizing both speaker attribution accuracy and utterance transcription fidelity in audiovisual captions. Extensive experiments on DiaDemBench reveal even commercial models still exhibit substantial room for improvement in dialogue-aware captioning. Notably, DiaDem not only outperforms the Gemini series in dialogue description accuracy but also achieves competitive performance on general audiovisual capti
While Multimodal Large Language Models (MLLMs) have advanced video understanding, achieving precise temporal and cross-modal alignment in audiovisual video captioning remains a formidable challenge. Most existing approaches suffer from modality detachment and temporal incoherence, failing to accurately bind auditory events to visual entities or capture complex causal dynamics. To address these deficiencies, we propose TCA-Captioner, a framework specifically engineered to enhance Temporal and Cross-Modal Alignment for audiovisual video captioning. We first introduce the Observer-Checker-Corrector (OCC) framework, an iterative refinement strategy that generates high-fidelity, meticulously grounded training data. Leveraging a curated high-density human interaction dataset, TCA-Captioner is optimized to model sophisticated audiovisual interactions. Furthermore, we present TCA-Bench, a diagnostic benchmark utilizing a Decoupled Evaluation Protocol to isolate and quantify model proficiency in audiovisual binding and temporal relational reasoning. Extensive experiments demonstrate that TCA-Captioner sets a new standard for temporally-coherent and synchronized audiovisual narratives.
Scriptwriting has traditionally been text-centric, a modality that only partially conveys the produced audiovisual experience. A formative study with professional writers informed us that connecting textual and audiovisual modalities can aid ideation and iteration, especially for writing dialogues. In this work, we present Script2Screen, an AI-assisted tool that integrates scriptwriting with audiovisual scene creation in a unified, synchronized workflow. Focusing on dialogues in scripts, Script2Screen generates expressive scenes with emotional speeches and animated characters through a novel text-to-audiovisual-scene pipeline. The user interface provides fine-grained controls, allowing writers to fine-tune audiovisual elements such as character gestures, speech emotions, and camera angles. A user study with both novice and professional writers from various domains demonstrated that Script2Screen's interactive audiovisual generation enhances the scriptwriting process, facilitating iterative refinement while complementing, rather than replacing, their creative efforts.
There exists limited theoretical guidance on integrating visualization and sonification. In this paper, we address this gap by investigating audiovisual semiotics for uncertainty representation: joining uncertainty visualization and sonification to combine audiovisual channels for enhancing users' perception of uncertainty. We conducted two preregistered crowd-sourced user studies. First, we assessed suitable audio/visual pairs. Then, we investigated audiovisual mappings of uncertainty. Here, we use probability as it is an easily communicated aspect of uncertainty. We analyzed the participants' preferences and reaction times in both user studies. Additionally, we explored the strategies employed by participants through qualitative analysis. Our results reveal audiovisual mappings that lead to particularly strong preferences and low reaction times. Furthermore, we found that preferred audio/visual pairs are not necessarily suitable audiovisual mappings of uncertainty. For example, while pitch paired with brightness was preferred as a pair, it was not well suited as a mapping for uncertainty. We recommend audiovisual mappings of uncertainty that lead to low reaction times and high pr
Emotion understanding is essential for building socially intelligent agents. Although recent multimodal large language models have shown strong performance on this task, two key challenges remain - spurious associations between emotions and irrelevant audiovisual cues, and hallucinations of audiovisual cues driven by text priors in the language model backbone. To quantify and understand these issues, we introduce EmoReAlM, a benchmark designed to evaluate MLLMs for cue-emotion associations, hallucinations and modality agreement. We then propose AVEm-DPO, a preference optimization technique that aligns model responses with both audiovisual inputs and emotion-centric queries. Specifically, we construct preferences over responses exhibiting spurious associations or hallucinations, and audiovisual input pairs guided by textual prompts. We also include a regularization term that penalizes reliance on text priors, thereby mitigating modality-specific cue hallucinations. Experimental results on DFEW, RAVDESS and EMER demonstrate that our method significantly improves the performance of the reference baseline models with 6-19% of relative performance gains in zero-shot settings. By providi
Automated video-odor matching predicts scents aligned with audiovisual content for scent-enhanced media. Existing methods usually treat odor labels as determined only by scene content, but odor judgment also depends on individual olfactory profiles, including scent sensitivity, tolerance to unpleasant odors, and affective preference. Ignoring this observer context limits current systems' ability to predict scents that match perceived experience. We present OlfactProfile, a framework for profile-conditioned odor prediction from audiovisual content. Our results show that olfactory profiles are not beneficial by default: with matched feature backbones, naive profile concatenation and uniform profile modulation can degrade performance, while structured field-wise profile conditioning consistently improves prediction. Thus, the key challenge is not merely whether observer context is available, but how it is integrated into multimodal reasoning. To study this setting, we construct an audiovisual benchmark pairing temporally aligned odor annotations with annotator olfactory preference profiles. It contains 1,350 video clips, a 99-class scent vocabulary, and three semantic odor tracks: For
The aim of steganography is to hide secret information inside ordinary media so that the existence of communication is hidden rather than encrypted. In audiovisual context, the availability of audio and video streams creates an opportunity to split a payload across these two modes thus, reducing the embedding burden on any single carrier. This paper evaluates whether such split-payload audiovisual steganography can help evade unimodal and multimodal steganalysis under synchronized and asynchronous embedding settings. We create audiovisual samples where the hidden message is divided between the audio and video tracks, and then test how well different detectors can identify them. The single mode detectors performs close to random guessing, thus showing the benefit of this hiding mechanism, while the multimodal model initially appears more effective. However, further checks show that this improvement mostly comes from the video stream, not from a true combined audio-video signal. Overall, the results suggest that splitting the payload across modalities can make detection harder, but multimodal detectors must be evaluated carefully to ensure they are learning the intended signal.
We present Audiovisual Moments in Time (AVMIT), a large-scale dataset of audiovisual action events. In an extensive annotation task 11 participants labelled a subset of 3-second audiovisual videos from the Moments in Time dataset (MIT). For each trial, participants assessed whether the labelled audiovisual action event was present and whether it was the most prominent feature of the video. The dataset includes the annotation of 57,177 audiovisual videos, each independently evaluated by 3 of 11 trained participants. From this initial collection, we created a curated test set of 16 distinct action classes, with 60 videos each (960 videos). We also offer 2 sets of pre-computed audiovisual feature embeddings, using VGGish/YamNet for audio data and VGG16/EfficientNetB0 for visual data, thereby lowering the barrier to entry for audiovisual DNN research. We explored the advantages of AVMIT annotations and feature embeddings to improve performance on audiovisual event recognition. A series of 6 Recurrent Neural Networks (RNNs) were trained on either AVMIT-filtered audiovisual events or modality-agnostic events from MIT, and then tested on our audiovisual test set. In all RNNs, top 1 accura
Multimodal audiovisual perception can enable new avenues for robotic manipulation, from better material classification to the imitation of demonstrations for which only audio signals are available (e.g., playing a tune by ear). However, to unlock such multimodal potential, robots need to learn the correlations between an object's visual appearance and the sound it generates when they interact with it. Such an active sensorimotor experience requires new interaction capabilities, representations, and exploration methods to guide the robot in efficiently building increasingly rich audiovisual knowledge. In this work, we present CAVER, a novel robot that builds and utilizes rich audiovisual representations of objects. CAVER includes three novel contributions: 1) a novel 3D printed end-effector, attachable to parallel grippers, that excites objects' audio responses, 2) an audiovisual representation that combines local and global appearance information with sound features, and 3) an exploration algorithm that uses and builds the audiovisual representation in a curiosity-driven manner that prioritizes interacting with high uncertainty objects to obtain good coverage of surprising audio wi
Locating a target based on auditory and visual cues$\unicode{x2013}$such as finding a car in a crowded parking lot or identifying a speaker in a virtual meeting$\unicode{x2013}$requires balancing effort, time, and accuracy under uncertainty. Existing models of audiovisual search often treat perception and action in isolation, overlooking how people adaptively coordinate movement and sensory strategies. We present Sensonaut, a computational model of embodied audiovisual search. The core assumption is that people deploy their body and sensory systems in ways they believe will most efficiently improve their chances of locating a target, trading off time and effort under perceptual constraints. Our model formulates this as a resource-rational decision-making problem under partial observability. We validate the model against newly collected human data, showing that it reproduces both adaptive scaling of search time and effort under task complexity, occlusion, and distraction, and characteristic human errors. Our simulation of human-like resource-rational search informs the design of audiovisual interfaces that minimize search cost and cognitive load.
As video becomes increasingly central to information dissemination and multimodal large language models (MLLMs) continue to advance, evaluating video retrieval has become increasingly important. In realistic search scenarios, this requires matching short user queries to long-form content using both visual and auditory evidence. Yet existing retrieval benchmarks are still dominated by short clips, single modalities, and caption-based evaluation. We introduce FLARE, a full-modality long-video audiovisual retrieval benchmark with user-simulated queries. Built from 399 carefully screened Video-MME videos (10--60 min, 225.4 h) to ensure source quality and diversity, FLARE contains 87,697 clips annotated with vision, audio, and unified audiovisual captions, together with 274,933 user-style queries. Cross-modal queries are further filtered by a hard bimodal constraint, requiring retrieval to fail under either modality alone but succeed when both are combined. FLARE evaluates models under two regimes, caption-based and query-based retrieval, across vision, audio, and unified audiovisual settings. Experiments with 15 representative retrievers show that user-style queries substantially chang
Satellite communications face severe bottlenecks in supporting high-fidelity synchronized audiovisual services, as conventional schemes struggle with cross-modal coherence under fluctuating channel conditions, limited bandwidth, and long propagation delays. To address these limitations, this paper proposes an adaptive multimodal semantic transmission system tailored for satellite scenarios, aiming for high-quality synchronized audiovisual reconstruction under bandwidth constraints. Unlike static schemes with fixed modal priorities, our framework features a dual-stream generative architecture that flexibly switches between video-driven audio generation and audio-driven video generation. This allows the system to dynamically decouple semantics, transmitting only the most important modality while employing cross-modal generation to recover the other. To balance reconstruction quality and transmission overhead, a dynamic keyframe update mechanism adaptively maintains the shared knowledge base according to wireless scenarios and user requirements. Furthermore, a large language model based decision module is introduced to enhance system adaptability. By integrating satellite-specific kno
While recent advances in Multimodal Large Language Models (MLLMs) have improved image-based localization, precise global geolocation remains a formidable challenge due to the inherent ambiguity of visual landscapes and the largely untapped potential of auditory cues. In this paper, we introduce Audiovisual Geolocation, a framework designed to resolve geographic ambiguity through interpretable perception and reasoning. We present AVG, a high-quality global-scale video benchmark for geolocation, comprising 20,000 curated clips across 1,000 distinct locations. To address the complexity of audiovisual geolocation, we propose a three-stage framework: (1) a Perception stage that utilizes a mixture-autoregressive sparse autoencoder to decompose noisy audio into semantically grounded "acoustic atoms"; (2) a Multimodal Reasoning stage that employs an MLLM finetuned via Group Relative Policy Optimization (GRPO) to synthesize these atoms with visual features; and (3) a Precision Prediction stage using Riemannian Flow Matching on the $S^2$ manifold. Our experiments demonstrate that our framework significantly outperforms unimodal baselines. These results entail that interpretable perception of
Audiovisual video captioning aims to generate semantically rich descriptions with temporal alignment between visual and auditory events, thereby benefiting both video understanding and generation. In this paper, we present AVoCaDO, a powerful audiovisual video captioner driven by the temporal orchestration between audio and visual modalities. We propose a two-stage post-training pipeline: (1) AVoCaDO SFT, which fine-tunes the model on a newly curated dataset of 107K high-quality, temporally-aligned audiovisual captions; and (2) AVoCaDO GRPO, which leverages tailored reward functions to further enhance temporal coherence and dialogue accuracy while regularizing caption length and reducing collapse. Experimental results demonstrate that AVoCaDO significantly outperforms existing open-source models across four audiovisual video captioning benchmarks, and also achieves competitive performance on the VDC and DREAM-1K benchmark under visual-only settings.
Deepfakes generated by advanced generative models have rapidly posed serious threats, yet existing audiovisual deepfake detection approaches struggle to generalize to unseen manipulation methods. To address this, we propose a novel reference-aware audiovisual deepfake detection method, called Referee to capture fine-grained identity discrepancies. Unlike existing methods that overfit to transient spatiotemporal artifacts, Referee employs identity bottleneck and matching modules to model the relational consistency of speaker-specific cues captured by a single one-shot example as a biometric anchor. Extensive experiments on FakeAVCeleb, FaceForensics++, and KoDF demonstrate that Referee achieves state-of-the-art results on cross-dataset and cross-language evaluation protocols, including a 99.4% AUC on KoDF. These results highlight that explicitly correlating reference-based biometric priors is a key frontier for achieving generalized and reliable audiovisual forensics. The code is available at https://github.com/ewha-mmai/referee.
This report, authored in 2003, presents an innovative approach to the management and utilization of audiovisual archives in the humanities and social sciences. Developed by the research team ESCoM, under the auspices of the Maison des Sciences de l'Homme (MSH) in Paris, this program predated platforms like YouTube and was groundbreaking in its vision for the digital preservation, segmentation, and classification of audiovisual content. Its objectives included creating a heritage of scientific knowledge, developing advanced tools for its annotation and reuse, and facilitating the dissemination of specialized research to a broad audience.At its core, the report outlines the development of an integrated environment that allows users to index, annotate, and classify audiovisual segments through personalized ontologies and thematic grids. The proposed methods rely on cutting-edge concepts, such as semantic web technologies, knowledge representation, and conceptual graph editing, to enable researchers and educators to create tailored archives and new multimedia resources. This forward-thinking approach aligns with modern practices of content reuse and republication, demonstrating a visio
"Intangible Victory" is an audiovisual installation in the form of the intangible being of the Victory of Samothrace that uses interactive digital media. Specifically, through this installation, we redefine the visual symbolism of the ancient sculpture, paying attention to time as a wear factor (entropy) and the special importance of the void as an absence of the sculptural form. Emptiness completes the intangible essence of the sculpture in the field of symbolism as well as in that of artistic significance for the interpretation of the work today. The function of the void and the interaction of the viewer with the work, causes the emergence of a new experience-dialogue between space and time. The use of digital media and technology reveals the absence of the sculptural form as it is visualized in the Victory of Samothrace. The sculptural form is reconstructed from fibers in space in a cylindrical arrangement. The form is rendered with colored strings - conductive sensors, that allow the visitor to interact with the work, creating a sound environment through movement. The sound completely replaces the volume, as the void of the sculptural form together with the viewer in unison pre
Audiovisual active speaker detection (ASD) is conventionally performed by modelling the temporal synchronisation of acoustic and visual speech cues. In egocentric recordings, however, the efficacy of synchronisation-based methods is compromised by occlusions, motion blur, and adverse acoustic conditions. In this work, a novel framework is proposed that exclusively leverages cross-modal face-voice associations to determine speaker activity. An existing face-voice association model is integrated with a transformer-based encoder that aggregates facial identity information by dynamically weighting each frame based on its visual quality. This system is then coupled with a front-end utterance segmentation method, producing a complete ASD system. This work demonstrates that the proposed system, Self-Lifting for audiovisual active speaker detection(SL-ASD), achieves performance comparable to, and in certain cases exceeding, that of parameter-intensive synchronisation-based approaches with significantly fewer learnable parameters, thereby validating the feasibility of substituting strict audiovisual synchronisation modelling with flexible biometric associations in challenging egocentric sce
In this paper, we present a multimodal and dynamical VAE (MDVAE) applied to unsupervised audio-visual speech representation learning. The latent space is structured to dissociate the latent dynamical factors that are shared between the modalities from those that are specific to each modality. A static latent variable is also introduced to encode the information that is constant over time within an audiovisual speech sequence. The model is trained in an unsupervised manner on an audiovisual emotional speech dataset, in two stages. In the first stage, a vector quantized VAE (VQ-VAE) is learned independently for each modality, without temporal modeling. The second stage consists in learning the MDVAE model on the intermediate representation of the VQ-VAEs before quantization. The disentanglement between static versus dynamical and modality-specific versus modality-common information occurs during this second training stage. Extensive experiments are conducted to investigate how audiovisual speech latent factors are encoded in the latent space of MDVAE. These experiments include manipulating audiovisual speech, audiovisual facial image denoising, and audiovisual speech emotion recognit
An important challenge in emotion recognition is to develop methods that can leverage unlabeled training data. In this paper, we propose the VQ-MAE-AV model, a self-supervised multimodal model that leverages masked autoencoders to learn representations of audiovisual speech without labels. The model includes vector quantized variational autoencoders that compress raw audio and visual speech data into discrete tokens. The audiovisual speech tokens are used to train a multimodal masked autoencoder that consists of an encoder-decoder architecture with attention mechanisms. The model is designed to extract both local (i.e., at the frame level) and global (i.e., at the sequence level) representations of audiovisual speech. During self-supervised pre-training, the VQ-MAE-AV model is trained on a large-scale unlabeled dataset of audiovisual speech, for the task of reconstructing randomly masked audiovisual speech tokens and with a contrastive learning strategy. During this pre-training, the encoder learns to extract a representation of audiovisual speech that can be subsequently leveraged for emotion recognition. During the supervised fine-tuning stage, a small classification model is tra