Apprenticeship-Inspired Elegance: Synergistic Knowledge Distillation Empowers Spiking Neural Networks for Efficient Single-Eye Emotion Recognition
On the map: Knowledge distillation → Multimodal distillation
Abstract (arXiv)
We introduce a novel multimodality synergistic knowledge distillation scheme tailored for efficient single-eye motion recognition tasks. This method allows a lightweight, unimodal student spiking neural network (SNN) to extract rich knowledge from an event-frame multimodal teacher network. The core strength of this approach is its ability to utilize the ample, coarser temporal cues found in conventional frames for effective emotion recognition. Consequently, our method adeptly interprets both temporal and spatial information from the conventional frame domain, eliminating the need for specialized sensing devices, e.g., event-based camera. The effectiveness of our approach is thoroughly demonstrated using both existing and our compiled single-eye emotion recognition datasets, achieving unparalleled performance in accuracy and efficiency over existing state-of-the-art methods.
Key facts. Cited by 3 papers in the map (data through 13 Oct 2026). Placed in Multimodal distillation, one of 12 directions in Knowledge distillation. Builds on 23 of its 43 references that are in the map. First posted on arXiv 20 Jun 2024.
Builds on
23 of 43 references.
References · 23
- 2015Deep Residual Learning for Image Recognitioncited by 51,950
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,223
- 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
- 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 898
- 2017Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?cited by 551
- 2019High Speed and High Dynamic Range Video with an Event Cameracited by 344
- 2021Deep Residual Learning in Spiking Neural Networkscited by 329
- 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 196
- 2021TransFER: Learning Relation-aware Facial Expression Representations with Transformerscited by 85
- 2021Feature Decomposition and Reconstruction Learning for Effective Facial Expression Recognitioncited by 49
- 2023Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillationcited by 43
- 2019MIMAMO Net: Integrating Micro- and Macro-motion for Video Emotion Recognitioncited by 17
11 more
- 2020Effective AER Object Classification Using Segmented Probability-Maximization Learning in Spiking Neural Networkscited by 16
- 2021Affective Processes: stochastic modelling of temporal context for emotion and facial expression recognitioncited by 15
- 2024Event-Driven Learning for Spiking Neural Networkscited by 15
- 2019Unsupervised AER Object Recognition Based on Multiscale Spatio-Temporal Features and Spiking Neuronscited by 14
- 2017Eyemotion: Classifying facial expressions in VR using eye-tracking camerascited by 12
- 2023Biologically inspired structure learning with reverse knowledge distillation for spiking neural networkscited by 11
- 2023Temporal Knowledge Sharing enable Spiking Neural Network Learning from Past and Futurecited by 10
- 2023Event-Enhanced Multi-Modal Spiking Neural Network for Dynamic Obstacle Avoidancecited by 8
- 2020Facial Expression Recognition Under Partial Occlusion from Virtual Reality Headsets based on Transfer Learningcited by 7
- 2019Recognizing Facial Expressions of Occluded Faces using Convolutional Neural Networkscited by 5
- 2023In the Blink of an Eye: Event-based Emotion Recognitioncited by 4
Built on by
Citing papers per year: 2025: 3.
3 papers.