Related papers: State-Anchored Complete-View Distillation for Robu…

Large language models (LLMs) achieve state-of-the-art (SOTA) performance across language tasks, but are costly to deploy due to their size and resource demands. Knowledge Distillation (KD) addresses this by training smaller Student models…

Dense visual prediction tasks, such as detection and segmentation, are crucial for time-critical applications (e.g., autonomous driving and video surveillance). While deep models achieve strong performance, their efficiency remains a…

Multimodal affective computing aims to predict humans' sentiment, emotion, intention, and opinion using language, acoustic, and visual modalities. However, current models often learn spurious correlations that harm generalization under…

Multimodal sentiment analysis has become an increasingly popular research area as the demand for multimodal online content is growing. For multimodal sentiment analysis, words can have different meanings depending on the linguistic context…

Recently, the advance in deep learning has brought a considerable improvement in the end-to-end speech recognition field, simplifying the traditional pipeline while producing promising results. Among the end-to-end models, the connectionist…

Multimodal emotion recognition (MER) is crucial for human-computer interaction, yet real-world challenges like dynamic modality incompleteness and asynchrony severely limit its robustness. Existing methods often assume consistently complete…

Referring image segmentation (RIS) is a fundamental vision-language task that intends to segment a desired object from an image based on a given natural language expression. Due to the essentially distinct data properties between image and…

In this paper, we propose MMER, a novel Multimodal Multi-task learning approach for Speech Emotion Recognition. MMER leverages a novel multimodal network based on early-fusion and cross-modal self-attention between text and acoustic…

We present XKD, a novel self-supervised framework to learn meaningful representations from unlabelled videos. XKD is trained with two pseudo objectives. First, masked data reconstruction is performed to learn modality-specific…

Multimodal transfer learning aims to transform pretrained representations of diverse modalities into a common domain space for effective multimodal fusion. However, conventional systems are typically built on the assumption that all…

Multimodal speech emotion recognition (SER) has emerged as pivotal for improving human-machine interaction. Researchers are increasingly leveraging both speech and textual information obtained through automatic speech recognition (ASR) to…

Multimodal Emotion Recognition in Conversations remains a challenging task due to the complex interplay of textual, acoustic and visual signals. While recent models have improved performance via advanced fusion strategies, they often lack…

Multimodal emotion recognition (MER) benefits from combining text, audio, and vision, yet standard fusion often fails when modalities conflict. Crucially, conflicts differ in resolvability: benign conflicts stem from missing, weak, or…

Vision-Language Models (VLMs) trained with contrastive loss have achieved significant advancements in various vision and language tasks. However, the global nature of the contrastive loss makes VLMs focus predominantly on foreground…

Lack of labeled data is a main obstacle in relation extraction. Semi-supervised relation extraction (SSRE) has been proven to be a promising way for this problem through annotating unlabeled samples as additional training data. Almost all…

This research combines Knowledge Distillation (KD) and Mixture of Experts (MoE) to develop modular, efficient multilingual language models. Key objectives include evaluating adaptive versus fixed alpha methods in KD and comparing modular…

While large vision-language models (VLMs) demonstrate strong long-context understanding, their prevalent small branches fail on linguistics-photography alignment for a limited window size. We discover that knowledge distillation improves…

Knowledge distillation as an efficient knowledge transfer technique, has achieved remarkable success in unimodal scenarios. However, in cross-modal settings, conventional distillation methods encounter significant challenges due to data and…

Multimodal Emotion Recognition (MER) aims to automatically identify and understand human emotional states by integrating information from various modalities. However, the scarcity of annotated multimodal data significantly hinders the…

This paper proposes a novel method for depth completion, which leverages multi-view improved monitored distillation to generate more precise depth maps. Our approach builds upon the state-of-the-art ensemble distillation method, in which we…