Related papers: EVOKE: Emotion Enabled Virtual Avatar Mapping Usin…
The extensive amounts of data required for training deep neural networks pose significant challenges on storage and transmission fronts. Dataset distillation has emerged as a promising technique to condense the information of massive…
Knowledge distillation is a popular technique for transferring the knowledge from a large teacher model to a smaller student model by mimicking. However, distillation by directly aligning the feature maps between teacher and student may…
It has been revealed that efficient dense image prediction (EDIP) models designed for AI chips, trained using the knowledge distillation (KD) framework, encounter two key challenges, including \emph{maintaining boundary region completeness}…
In this paper, we introduce a novel knowledge distillation approach for the semantic segmentation task. Unlike previous methods that rely on power-trained teachers or other modalities to provide additional knowledge, our approach does not…
Micro-expression recognition can obtain the real emotion of the individual at the current moment. Although deep learning-based methods, especially Transformer-based methods, have achieved impressive results, these methods have high…
Foundation models deliver strong perception but are often too computationally heavy to deploy, and adapting them typically requires costly annotations. We introduce a semi-supervised knowledge distillation (SSKD) framework that compresses…
Diffusion models, widely used in image generation, rely on iterative refinement to generate images from noise. Understanding this data evolution is important for model development and interpretability, yet challenging due to its…
This paper presents an emotion-regularized conditional variational autoencoder (Emo-CVAE) model for generating emotional conversation responses. In conventional CVAE-based emotional response generation, emotion labels are simply used as…
We present a novel deep learning-based framework to generate embedding representations of fine-grained emotions that can be used to computationally describe psychological models of emotions. Our framework integrates a contextualized…
An advanced emotion classification model was developed using a CNN-Transformer architecture for emotion recognition from EEG brain wave signals, effectively distinguishing among three emotional states, positive, neutral and negative. The…
Visual Emotion Analysis (VEA) aims at predicting people's emotional responses to visual stimuli. This is a promising, yet challenging, task in affective computing, which has drawn increasing attention in recent years. Most of the existing…
Knowledge distillation becomes a de facto standard to improve the performance of small neural networks. Most of the previous works propose to regress the representational features from the teacher to the student in a one-to-one spatial…
This paper proposes a multimodal emotion recognition system, VIsual Spoken Textual Additive Net (VISTANet), to classify emotions reflected by input containing image, speech, and text into discrete classes. A new interpretability technique,…
Ensemble knowledge distillation can extract knowledge from multiple teacher models and encode it into a single student model. Many existing methods learn and distill the student model on labeled data only. However, the teacher models are…
Large language models (LLMs) have achieved remarkable performance across diverse domains, yet their enormous computational and memory requirements hinder deployment in resource-constrained environments. Knowledge distillation offers a…
Real-world driving involves intricate interactions among vehicles navigating through dense traffic scenarios. Recent research focuses on enhancing the interaction awareness of autonomous vehicles to leverage these interactions in…
Deep learning models for multimodal expression recognition have reached remarkable performance in controlled laboratory environments because of their ability to learn complementary and redundant semantic information. However, these models…
Tracking using bio-inspired event cameras has drawn more and more attention in recent years. Existing works either utilize aligned RGB and event data for accurate tracking or directly learn an event-based tracker. The first category needs…
In this paper, we study the task of facial expression recognition under strong occlusion. We are particularly interested in cases where 50% of the face is occluded, e.g. when the subject wears a Virtual Reality (VR) headset. While previous…
In visual tasks, large teacher models capture essential features and deep information, enhancing performance. However, distilling this information into smaller student models often leads to performance loss due to structural differences and…