多媒体

Multimodal Emotion Recognition in Conversation (MERC) significantly enhances emotion recognition performance by integrating complementary emotional cues from text, audio, and visual modalities. While existing methods commonly utilize…

Forward Error Correction (FEC) remains essential for protecting video streaming against packet loss, yet most real deployments still rely on static, coarse-grained configurations that cannot react to rapid shifts in loss rate, goodput, or…

We present the software architecture and implementation of our web-based multiparty video conference application. It does not use a media server. For call signaling, it either piggybacks on existing push notifications via a lightweight…

Generative models have substantially expanded video generation capabilities, yet practical thought-to-video creation remains a multi-stage, multi-modal, and decision-intensive process. However, existing tools either hide intermediate…

Stickers are multimodal resources widely used in everyday digital conversations. Despite their popularity, most studies have focused on emojis and emoticons. Therefore, this study analyzes, from a sociopragmatic perspective, the use of…

This paper introduces a generalized federated prompt-tuning framework for practical scenarios where local datasets are multi-modal and exhibit different distributional patterns of missing features at the input level. The proposed framework…

Embedding models are a fundamental component of modern AI systems such as semantic search and retrieval-augmented generation. Recent advances in large foundation models have substantially accelerated the development of embedding models,…

Explainable Multimodal Emotion Recognition plays a crucial role in applications such as human-computer interaction and social media analytics. However, current approaches struggle with cue-level perception and reasoning due to two main…

Multimodal emotion analysis is shifting from static classification to generative reasoning. Beyond simple label prediction, robust affective reasoning must synthesize fine-grained signals such as facial micro-expressions and prosodic which…

This paper introduces TRAILDREAMS, a framework that uses a large language model (LLM) to automate the production of movie trailers. The purpose of LLM is to select key visual sequences and impactful dialogues, and to help TRAILDREAMS to…

Multimodal Sentiment Analysis (MSA) integrates multiple modalities to infer human sentiment, but real-world noise often leads to missing or corrupted data. However, existing feature-disentangled methods struggle to handle the internal…

As deepfake videos become increasingly difficult for people to recognise, understanding the strategies humans use is key to designing effective media literacy interventions. We conducted a study with 195 participants between the ages of 21…

Effective multimodal fusion requires mechanisms that can capture complex cross-modal dependencies while remaining computationally scalable for real-world deployment. Existing audio-visual fusion approaches face a fundamental trade-off:…

This paper presents a system for detecting fake audio-visual content (i.e., video deepfake), developed for Track 2 of the DDL Challenge. The proposed system employs a two-stage framework, comprising unimodal detection and multimodal score…

Trailers are short promotional videos designed to provide audiences with a glimpse of a movie. The process of creating a trailer typically involves selecting key scenes, dialogues and action sequences from the main content and editing them…

Online video streaming has evolved into an integral component of the contemporary Internet landscape. Yet, the disclosure of user requests presents formidable privacy challenges. As users stream their preferred online videos, their requests…

Recent advances in multimodal large language models (MLLM) for audio music have demonstrated strong capabilities in music understanding, yet symbolic music, a fundamental representation of musical structure, remains unexplored. In this…

Multi-modal stance detection (MSD) aims to determine an author's stance toward a given target using both textual and visual content. While recent methods leverage multi-modal fusion and prompt-based learning, most fail to distinguish…

Robust cross-subject emotion recognition from multimodal physiological signals remains a challenging problem, primarily due to modality heterogeneity and inter-subject distribution shift. To tackle these challenges, we propose a novel…

We present an AI-based framework for semantic transmission of multimedia data over band-limited, time-varying channels. The method targets scenarios where large content is split into multiple packets, with an unknown number potentially…