chuangyu-robotics

Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time

clip-as-service

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

vision_transformer

OpenFace

OpenFace – a state-of-the art tool intended for facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation.

ESL-CN

The Elements of Statistical Learning (ESL)的中文翻译、代码实现及其习题解答。

imitation

Clean PyTorch implementations of imitation and reward learning algorithms

Hands-On-Meta-Learning-With-Python

Learning to Learn using One-Shot Learning, MAML, Reptile, Meta-SGD and more with Tensorflow

fairo

A modular embodied agent architecture and platform for building embodied agents

MocapNET

We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance

FaceFormer

[CVPR 2022] FaceFormer: Speech-Driven 3D Facial Animation with Transformers

rebel

An algorithm that generalizes the paradigm of self-play reinforcement learning and search to imperfect-information games.

awesome-rl-nlp

Curated Reinforcement Learning Resources for Natural Language Processing

probing-vits

Probing the representations of Vision Transformers.

ns-vqa

Neural-symbolic visual question answering

SGAE

OSSO

From a body shape, infer the anatomic skeleton.

Voice-synthesis

This repository is an implementation of Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis (SV2TTS) with a vocoder that works in real-time. SV2TTS is a three-stage deep learning framework that allows to create a numerical representation of a voice from a few seconds of audio, and to use it to condition a text-to-speech model trained to generalize to new voices.

NPYViewer

Load and view .npy files containing 2D and 1D NumPy arrays.

Text-Independent-Speaker-Verification

Text Independent Speaker Verification Using GE2E Loss

CICERO

The purpose of this repository is to introduce new dialogue-level commonsense inference datasets and tasks. We chose dialogues as the data source because dialogues are known to be complex and rich in commonsense.

awesome-multi-agent

A curated list of awesome multi-agent learning papers

Medical-Dialogue

REGRAD

the code for generating REGRAD dataset

human-rl

Code for human intervention reinforcement learning

EthicsShaping

[AAAI 2018] Implementation of the Ethics Shaping approach proposed in "A low-cost ethics shaping approach for designing reinforcement learning agents"

zsarcap

TICC-MCP

An online solver for Trust-Intent-Capability-Calibration POMDP (TICC-POMDP)

mirror

Differentiable Deep Social Projection for AssistiveHuman-Robot Communication (RSS 2022)

MUMBAI

Multi-Person, Multimodal Board Game Affect and Interaction Analysis Dataset

Voice-Cloning

This repository is an implementation of Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis (SV2TTS) with a vocoder that works in real-time.