Xinzhe-Ni

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

ActionCLIP

This is the official implement of paper "ActionCLIP: A New Paradigm for Action Recognition"

annotated_deep_learning_paper_implementations

🧑‍🏫 50! Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

info-nce-pytorch

PyTorch implementation of the InfoNCE loss for self-supervised learning.

kinetics-dataset

NCG

strm

[CVPR 2022] Official Pytorch Implementation for "Spatio-temporal Relation Modeling for Few-shot Action Recognition". SOTA Results for Few-shot Action Recognition

ToRA_xinzhe

trx

Temporal-Relational CrossTransformers (CVPR 2021)

Xinzhe-Ni/NCG

Xinzhe-Ni/ActionCLIP

This is the official implement of paper "ActionCLIP: A New Paradigm for Action Recognition"

Xinzhe-Ni/annotated_deep_learning_paper_implementations

🧑‍🏫 50! Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

Xinzhe-Ni/info-nce-pytorch

PyTorch implementation of the InfoNCE loss for self-supervised learning.

Xinzhe-Ni/kinetics-dataset

Xinzhe-Ni/strm

[CVPR 2022] Official Pytorch Implementation for "Spatio-temporal Relation Modeling for Few-shot Action Recognition". SOTA Results for Few-shot Action Recognition

Xinzhe-Ni/ToRA_xinzhe

Xinzhe-Ni/trx

Temporal-Relational CrossTransformers (CVPR 2021)