Related papers: EVOKE: Emotion Enabled Virtual Avatar Mapping Usin…
Despite exciting progress in pre-training for visual-linguistic (VL) representations, very few aspire to a small VL model. In this paper, we study knowledge distillation (KD) to effectively compress a transformer-based large VL model into a…
This paper presents an innovative approach to address the challenges of translating multi-modal emotion recognition models to a more practical and resource-efficient uni-modal counterpart, specifically focusing on speech-only emotion…
The domain of computer vision has experienced significant advancements in facial-landmark detection, becoming increasingly essential across various applications such as augmented reality, facial recognition, and emotion analysis. Unlike…
Mapping discrete and dimensional models of emotion remains a persistent challenge in affective science and computing. This incompatibility hinders the combination of valuable data sets, creating a significant bottleneck for training robust…
Facial expressions are the most common universal forms of body language. In the past few years, automatic facial expression recognition (FER) has been an active field of research. However, it is still a challenging task due to different…
Open-vocabulary 3D instance segmentation seeks to segment and classify instances beyond the annotated label space. Existing methods typically map 3D instances to 2D RGB-D images, and then employ vision-language models (VLMs) for…
Visual encoders are fundamental components in vision-language models (VLMs), each showcasing unique strengths derived from various pre-trained visual foundation models. To leverage the various capabilities of these encoders, recent studies…
Individual differences of Electroencephalogram (EEG) could cause the domain shift which would significantly degrade the performance of cross-subject strategy. The domain adversarial neural networks (DANN), where the classification loss and…
The utilization of multi-modal sensor data in visual place recognition (VPR) has demonstrated enhanced performance compared to single-modal counterparts. Nonetheless, integrating additional sensors comes with elevated costs and may not be…
Affective computing with Electroencephalogram (EEG) is a challenging task that requires cumbersome models to effectively learn the information contained in large-scale EEG signals, causing difficulties for real-time smart-device deployment.…
We introduce EV3, a novel meta-optimization framework designed to efficiently train scalable machine learning models through an intuitive explore-assess-adapt protocol. In each iteration of EV3, we explore various model parameter updates,…
This paper studies the potential of distilling knowledge from pre-trained models, especially Masked Autoencoders. Our approach is simple: in addition to optimizing the pixel reconstruction loss on masked inputs, we minimize the distance…
Emotion recognition in multi-speaker conversations faces significant challenges due to speaker ambiguity and severe class imbalance. We propose a novel framework that addresses these issues through three key innovations: (1) a speaker…
Vision-Language-Action models have shown great promise for autonomous driving, yet they suffer from degraded perception after unfreezing the visual encoder and struggle with accumulated instability in long-term planning. To address these…
Large-scale multi-view reconstruction models have made remarkable progress, but most existing approaches still rely on fully supervised training with ground-truth 3D/4D annotations. Such annotations are expensive and particularly scarce for…
Knowledge distillation is typically realized by transferring a teacher model's knowledge into a student's parameters through supervised or reinforcement-based optimization. While effective, such approaches require repeated parameter updates…
Dataset distillation is an emerging technique for reducing the computational and storage costs of training machine learning models by synthesizing a small, informative subset of data that captures the essential characteristics of a much…
Image enhancement finds wide-ranging applications in real-world scenarios due to complex environments and the inherent limitations of imaging devices. Recent diffusion-based methods yield promising outcomes but necessitate prolonged and…
Although deep neural networks and in particular Convolutional Neural Networks have demonstrated state-of-the-art performance in image classification with relatively high efficiency, they still exhibit high computational costs, often…
Model distillation enables the transfer of knowledge from large-scale models to compact student models, facilitating deployment in resource-constrained environments. However, conventional distillation approaches often suffer from…