Spikingformer: A Key Foundation Model for Spiking Neural Networks (AAAI 2026)

Offical implementation of "Spike-driven Transformer" (NeurIPS2023)

real-time network architecture for mobile devices and semantic segmentation

Variational Recurrent Autoencoder for timeseries clustering in pytorch

A GCN-based generative adversarial network for skeleton sequence generation

Methods for video, inertial and multimodal activity recognition

A sample code of data augmentation methods for wearable sensor data (time-series data)

Official code for "Action Transformer: A Self-attention Model for Short-time Pose-based Human Action Recognition", Pattern Recognition (2022).

CZU-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and 10 wearable inertial sensors

Transformer for Human Activity Recognition

Integrate deep learning models for image classification | Backbone learning/comparison/magic modification project

[BMVC2021] "TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation"

Unsupervised time series anomaly detection library

Track emissions from Compute and recommend ways to reduce their impact on the environment.

The implementation for "Extremely Lightweight Skeleton-Based Action Recognition with ShiftGCN++." (TIP 2021).

[ECCV 2022] Source code of "EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers"

Densely Guided Knowledge Distillation using Multiple Teacher Assistants

Implementation of "Slow-Fast Auditory Streams for Audio Recognition, ICASSP, 2021" in PyTorch

The official implementation of CVPR 2021 Paper: Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation.

A real-time motion capture system that estimates poses and global translations using only 6 inertial measurement units

Complementary Relation Contrastive Distillation

[ICCV'21] Learning Spatio-Temporal Transformer for Visual Tracking

Intertial-based Human Activity Recognition with Transformers

Transformer Network for Time-Series, Sensor and Wearable Data

Code on selecting an action based on multimodal inputs. Here in this case inputs are voice and text.

[ECCV 2020] Code for "Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction"

Time-Aware Transformer-based Network for Clinical Notes Series Prediction