Causality In Traffic Accident (Under Construction)

Repository for Traffic Accident Benchmark for Causality Recognition (ECCV 2020)

Overview

Data Preparation

Details of dataset construction

Benchmark

Cause and Effect Event Classification

We adopt Temporal Segment Networks (ECCV 2016) from the repository https://github.com/yjxiong/tsn-pytorch

The default arguments for code are set to train TSN with average consensus function.

python train_classifier.py --consensus_type average
python train_classifier.py --consensus_type linear

Temporal Cause and Effect Event Localization

We adopt three types of baseline methods in our benchmark.

Single-stage Action Detection

python train_localization.py --architecture_type forward-SST
python train_localization.py --architecture_type backward-SST
python train_localization.py --architecture_type bi-SST
python train_localization.py --architecture_type SSTCN-SST

Proposal-based Action Detection (Not supported yet)

python train_localization.py --architecture_type naive-conv-R-C3D
python train_localization.py --architecture_type SSTCN-R-C3D

Action Segmentation

python train_localization.py --architecture_type SSTCN-Segmentation
python train_localization.py --architecture_type MSTCN-Segmentation

Repository for Traffic Accident Benchmark for Causality Recognition (ECCV 2020)

Related tags

Overview

Causality In Traffic Accident (Under Construction)

Overview

Data Preparation

Benchmark

Cause and Effect Event Classification

Temporal Cause and Effect Event Localization

Owner

Tackgeun

The pytorch implementation of SOKD (BMVC2021).

Certified Patch Robustness via Smoothed Vision Transformers

Official PyTorch implementation of "Improving Face Recognition with Large AgeGaps by Learning to Distinguish Children" (BMVC 2021)

Code for the paper "Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds" (ICCV 2021)

PyTorch Implementation of Region Similarity Representation Learning (ReSim)

Assessing syntactic abilities of BERT

SatelliteNeRF - PyTorch-based Neural Radiance Fields adapted to satellite domain

Research code for Arxiv paper "Camera Motion Agnostic 3D Human Pose Estimation"

Parameter Efficient Deep Probabilistic Forecasting

PyTorch implementation for "Sharpness-aware Quantization for Deep Neural Networks".

Pytorch implementation of Rosca, Mihaela, et al. "Variational Approaches for Auto-Encoding Generative Adversarial Networks."

Python Library for learning (Structure and Parameter) and inference (Statistical and Causal) in Bayesian Networks.

Useful materials and tutorials for 110-1 NTU DBME5028 (Application of Deep Learning in Medical Imaging)

Flexible Networks for Learning Physical Dynamics of Deformable Objects (2021)

Code for the paper "Reinforced Active Learning for Image Segmentation"

A Python framework for conversational search

Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks.

Official PyTorch implementation of Spatial Dependency Networks.

This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.

Diverse Image Generation via Self-Conditioned GANs