DTCN IJCAI - Sequential prediction learning framework and algorithm

Overview

DTCN

This is the implementation of our paper "Sequential Prediction of Social Media Popularity with Deep Temporal Context Networks".

Dataset

To successfully test performance, we created TPIC Dataset, a temporal popularity image collection dataset.

Overview

Our DTCN contains three main components, from embedding, learning to predicting. With a joint embedding network, we obtain a unified deep representation of multi-modal user-post data in a common embedding space. Then, based on the embedded data sequence over time, temporal context learning attempts to recurrently learn two adaptive temporal contexts for sequential popularity. Finally, a novel temporal attention is designed to predict new popularity (the popularity of a new user-post pair) with temporal coherence across multiple time-scales.

DTCN framework

Environment

The code is pure python. Keras is chosen to be the deep learning library here. Environment is configured by Anaconda. The environment file is saved as "environment.yml".

  • Ubuntu 16.04
  • Python 2.7
  • Cuda 10.0
  • cudnn 7.6.5

Setup

conda env create -f environment.yml

Prequisition

  • Clone the repository to your local machine
  • Acquire relevant dataset
  • Extract the image feature with ResNet (2048 dims)
  • Run script by seeing example.

Usage

DATA_HOME=test_data/TRIM_DATA
KERAS_BACKEND=theano \
THEANO_FLAGS='mode=FAST_RUN,device=cuda0,nvcc.fastmath=True,optimizer=fast_run' \
python main.py \
-feature_path $DATA_HOME/USER_20W_SORTED_BY_TIME.txt \
-meta_path $DATA_HOME/ResNet_20W_2048_SORTED_BY_TIME.txt \
-label_path $DATA_HOME/LABEL_20W_SORTED_BY_TIME.txt \
-algorithm SHARED_DTCN \
-nb_epoch 1000 \
-start_cross_validation 2 \
-total_cross_validation 3 \
-identifier_path $DATA_HOME/USERID_20W_SORTED_BY_TIME.txt \
-timestamps_path $DATA_HOME/TIMESTAMP_20W_SORTED_BY_TIME.txt \
-visual_mlp_enabled y \
-timestep 10 \
-time_align y \
-time_dis_con continue \
-time_context_length 18 \
-time_unit_metric hour \
-discrete_time_start_offset 2 \
-discrete_time_unit 4 \
-train_set_partial 9 \
-merge_mode concat \
-dual_time_align n \
-time_weight_mode time_flag \
-dual_lstm n

Citation

@inproceedings{Wu2017DTCN,
  title={Sequential Prediction of Social Media Popularity with Deep Temporal Context Networks},
  author={Wu, Bo and Cheng, Wen-Huang and Zhang, Yongdong and Qiushi, Huang and Jintao, Li and Mei, Tao},
  booktitle={IJCAI},
  year={2017},
  location = {Melbourne, Australia}}

Please concat us ([email protected]) if you have further questions or cooporations

FlingBot: The Unreasonable Effectiveness of Dynamic Manipulations for Cloth Unfolding

This repository contains code for training and evaluating FlingBot in both simulation and real-world settings on a dual-UR5 robot arm setup for Ubuntu 18.04

Columbia Artificial Intelligence and Robotics Lab 70 Dec 06, 2022
πŸ“š A collection of all the Deep Learning Metrics that I came across which are not accuracy/loss.

πŸ“š A collection of all the Deep Learning Metrics that I came across which are not accuracy/loss.

Rahul Vigneswaran 1 Jan 17, 2022
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation

TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation Zhaoyun Yin, Pichao Wang, Fan Wang, Xianzhe Xu, Hanling Zhang, Hao Li

DamoCV 25 Dec 16, 2022
NumPy둜 κ΅¬ν˜„ν•œ λ”₯λŸ¬λ‹ λΌμ΄λΈŒλŸ¬λ¦¬μž…λ‹ˆλ‹€. (μžλ™ λ―ΈλΆ„ 지원)

Deep Learning Library only using NumPy λ³Έ λ ˆν¬μ§€ν† λ¦¬λŠ” NumPy 만으둜 κ΅¬ν˜„ν•œ λ”₯λŸ¬λ‹ λΌμ΄λΈŒλŸ¬λ¦¬μž…λ‹ˆλ‹€. μžλ™ 미뢄이 κ΅¬ν˜„λ˜μ–΄ μžˆμŠ΅λ‹ˆλ‹€. μžλ™ λ―ΈλΆ„ μžλ™ 미뢄은 미뢄을 μžλ™μœΌλ‘œ κ³„μ‚°ν•΄μ£ΌλŠ” κΈ°λŠ₯μž…λ‹ˆλ‹€. μ•„λž˜ μ½”λ“œλŠ” μžλ™ 미뢄을 ν™œμš©ν•΄ μ—­μ „νŒŒ

쑰쀀희 17 Aug 16, 2022
Neural implicit reconstruction experiments for the Vector Neuron paper

Neural Implicit Reconstruction with Vector Neurons This repository contains code for the neural implicit reconstruction experiments in the paper Vecto

Congyue Deng 35 Jan 02, 2023
Multi-Stage Episodic Control for Strategic Exploration in Text Games

XTX: eXploit - Then - eXplore Requirements First clone this repo using git clone https://github.com/princeton-nlp/XTX.git Please create two conda envi

Princeton Natural Language Processing 9 May 24, 2022
Official PyTorch Implementation of "AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting".

AgentFormer This repo contains the official implementation of our paper: AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecast

Ye Yuan 161 Dec 23, 2022
PyTorch for Semantic Segmentation

PyTorch for Semantic Segmentation This repository contains some models for semantic segmentation and the pipeline of training and testing models, impl

Zijun Deng 1.7k Jan 06, 2023
Barbershop: GAN-based Image Compositing using Segmentation Masks (SIGGRAPH Asia 2021)

Barbershop: GAN-based Image Compositing using Segmentation Masks Barbershop: GAN-based Image Compositing using Segmentation Masks Peihao Zhu, Rameen A

Peihao Zhu 928 Dec 30, 2022
A large-scale video dataset for the training and evaluation of 3D human pose estimation models

ASPset-510 ASPset-510 (Australian Sports Pose Dataset) is a large-scale video dataset for the training and evaluation of 3D human pose estimation mode

Aiden Nibali 36 Oct 30, 2022
An Easy-to-use, Modular and Prolongable package of deep-learning based Named Entity Recognition Models.

DeepNER An Easy-to-use, Modular and Prolongable package of deep-learning based Named Entity Recognition Models. This repository contains complex Deep

Derrick 9 May 30, 2022
Vpw analyzer - A visual J1850 VPW analyzer written in Python

VPW Analyzer A visual J1850 VPW analyzer written in Python Requires Tkinter, Pan

7 May 01, 2022
A very impractical 3D rendering engine that runs in the python terminal.

Terminal-3D-Render A very impractical 3D rendering engine that runs in the python terminal. do NOT try to run this program using the standard python I

23 Dec 31, 2022
Tools for investing in Python

InvestOps Original repository on GitHub Original author is Magnus Erik Hvass Pedersen Introduction This is a Python package with simple and effective

24 Nov 26, 2022
mbrl-lib is a toolbox for facilitating development of Model-Based Reinforcement Learning algorithms.

mbrl-lib is a toolbox for facilitating development of Model-Based Reinforcement Learning algorithms. It provides easily interchangeable modeling and planning components, and a set of utility function

Facebook Research 724 Jan 04, 2023
MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images

MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images This repository contains the implementation of our paper MetaAvatar: Learni

sfwang 96 Dec 13, 2022
Official implementation for CVPR 2021 paper: Adaptive Class Suppression Loss for Long-Tail Object Detection

Adaptive Class Suppression Loss for Long-Tail Object Detection This repo is the official implementation for CVPR 2021 paper: Adaptive Class Suppressio

CASIA-IVA-Lab 67 Dec 04, 2022
CMT: Convolutional Neural Networks Meet Vision Transformers

CMT: Convolutional Neural Networks Meet Vision Transformers [arxiv] 1. Introduction This repo is the CMT model which impelement with pytorch, no refer

FlyEgle 83 Dec 30, 2022
Training vision models with full-batch gradient descent and regularization

Stochastic Training is Not Necessary for Generalization -- Training competitive vision models without stochasticity This repository implements trainin

Jonas Geiping 32 Jan 06, 2023