Yu (Brian) Yao's repositories
Detection-of-Traffic-Anomaly
This is the repo for our Detection of Traffic Anomaly (DoTA) dataset.
tad-IROS2019
Code of the Unsupervised Traffic Accident Detection paper in Pytorch.
fvl-ICRA2019
Official code for future vehicle localization paper implemented in Keras
DeepLearning-500-questions
深度学习500问,以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述,以帮助自己及有需要的读者。 全书分为18个章节,50余万字。由于水平有限,书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作,联系scutjy2015@163.com 版权所有,违权必究 Tan 2018.06
maskrcnn-benchmark
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
Anomaly_Prediction
Pytorch implementation of anomaly prediction.
bidireaction-trajectory-prediction
The code for Bi-directional Trajectory Prediction (BiTraP).
DiT
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
flownet2-pytorch
Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
jetson-detectors
Contains examples and documentation on how to setup your remote development environment from your Windows host to a Jetson device
jetson-inference
Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
PIE_annotations
Annotations for Pedestrian Intention Estimation (PIE) dataset
PIEPredict
PIE: A Large-Scale Dataset and Models for Pedestrian Intention Estimation and Trajectory Prediction
segmentation_models.pytorch
Segmentation models with pretrained backbones. PyTorch.
TFSegmentation
RTSeg: Real-time Semantic Segmentation Comparative Study
Trajectron-plus-plus
Code accompanying "Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data" by Tim Salzmann*, Boris Ivanovic*, Punarjay Chakravarty, and Marco Pavone (* denotes equal contribution).
transfusion-pytorch
Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI
Video-LLaVA
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
VideoLLaMA2
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs