Stars
A family of compressed models obtained via pruning and knowledge distillation
AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
SuperCLUE-Math6：新一代中文原生多轮多步数学推理数据集的探索之旅
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
Code for CVPR 2022 paper "NomMer: Nominate Synergistic Context in Vision Transformer for Visual Recognition"
Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
[Pedestron] Generalizable Pedestrian Detection: The Elephant In The Room. @ CVPR2021
extract features by maximizing mutual information
local non-uniformity correction for mutual information estimation
Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image (CVPR 2019)
Learning Rich Features from RGB-D Images for Object Detection and Segmentation
CVPR 2019 Translate-to-Recognize Networks for RGB-D Scene Recognition
Image augmentation for machine learning experiments.
Code to use the nturgb+d dataset for action recognition
Exploiting Multi-Layer Features Using a CNN-RNN Approach for RGB-D Object Recognition (ECCV 2018 workshops)
Original implementation of the paper "Recurrent Convolutional Fusion for RGB-D Object Recognition": https://arxiv.org/pdf/1806.01673.pdf
Models and examples built with TensorFlow