Fight Recognition from Still Images in the Wild @ WACVW2022, Real-world Surveillance Workshop

Related tags

Deep LearningSMFI
Overview

Fight Detection from Still Images in the Wild

Detecting fights from still images is an important task required to limit the distribution of social media images with fight content, in order to prevent the negative effects of such violent media items. For this reason, in this study we addressed the problem of fight detection from still images collected from web and social media. We explored how well one can detect fights from just a single still image.

In this context, a new image dataset on the fight recognition from still images task is collected named Social Media Fight Images (SMFI) dataset. The dataset samples gathered from social media (Twitter and Google) and NTU-CCTV Fights 1 dataset. Since the main concern is recognizing fight actions in the wild, real-world scenarios are included in the dataset where a mass amount of them are spontaneous recordings of fight actions. Using different keywords while crawling the data, the regional diversity is also maintained since the social media uploadings are mostly regional where users share the content in their own language. Some example images from the dataset are given below:

samples

Both fight and non-fight samples are collected from the same domain where the non-fight samples are also content likely to be shared on social media. Hard non-fight samples are also included in the dataset which displays the actions that might be misinterpreted as fight such as hugging, throwing ball, dancing and more. This prevents the dataset bias, so that the trained models focuses on the actions and the performers on the scene instead of benefiting other characteristics such as motion blur. The distribution of the dataset samples among each class and source is given below:

Twitter Google NTU CCTV-Fights Total
Fight 2247 162 330 2739
Non-fight 2642 146 164 2952
Total 4889 308 494 5691

Due to the copyright issues the dataset images are not shared directly and the links to the images / videos are shared. As the dataset samples might be deleted in time by the users or the authorities, the size of the dataset is subject to change.

Dataset Format

The dataset samples are shared through a CSV file where the columns are as follows:

  • Image ID: Unique ID assigned to each image.
  • Class: class of the image as fight / nofight
  • Source: The source of the images or videos as twitter_img / twitter_video / google / ntu-cctv
  • URL: The link for the images / videos.
    • For Twitter and Google data, image and video URLs are shared.
    • For the NTU CCTV-Fights data, the path to the original video is shared.
  • Frame number: If the image is extracted from a video, this column indicates the number of frame within the video.
    • For Twitter videos, the frame number is the number of frame (0-9) out of 10 uniformly sampled frames from each video.
    • For NTU CCTV-Fight videos, the frame number is the number of frame (0-N) out of all frames (N) extracted from each video.

In order to retrieve the dataset, you should first download the NTU CCTV-Fights here.

Citation

TBA

References

1 Mauricio Perez, Alex C. Kot, Anderson Rocha, “Detection of Real-world Fights in Surveillance Videos”, in IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019

Owner
Şeymanur Aktı
Şeymanur Aktı
Code for the paper "MASTER: Multi-Aspect Non-local Network for Scene Text Recognition" (Pattern Recognition 2021)

MASTER-PyTorch PyTorch reimplementation of "MASTER: Multi-Aspect Non-local Network for Scene Text Recognition" (Pattern Recognition 2021). This projec

Wenwen Yu 255 Dec 29, 2022
A library for efficient similarity search and clustering of dense vectors.

Faiss Faiss is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any

Meta Research 18.8k Jan 08, 2023
CATE: Computation-aware Neural Architecture Encoding with Transformers

CATE: Computation-aware Neural Architecture Encoding with Transformers Code for paper: CATE: Computation-aware Neural Architecture Encoding with Trans

16 Dec 27, 2022
Code for "Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space"

Sparse Steerable Convolution (SS-Conv) Code for "Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and

25 Dec 21, 2022
Language Models for the legal domain in Spanish done @ BSC-TEMU within the "Plan de las Tecnologías del Lenguaje" (Plan-TL).

Spanish legal domain Language Model ⚖️ This repository contains the page for two main resources for the Spanish legal domain: A RoBERTa model: https:/

Plan de Tecnologías del Lenguaje - Gobierno de España 12 Nov 14, 2022
Consistency Regularization for Adversarial Robustness

Consistency Regularization for Adversarial Robustness Official PyTorch implementation of Consistency Regularization for Adversarial Robustness by Jiho

40 Dec 17, 2022
Bayesian Deep Learning and Deep Reinforcement Learning for Object Shape Error Response and Correction of Manufacturing Systems

Bayesian Deep Learning for Manufacturing 2.0 (dlmfg) Object Shape Error Response (OSER) Digital Lifecycle Management - In Process Quality Improvement

Sumit Sinha 30 Oct 31, 2022
Automated Hyperparameter Optimization Competition

QQ浏览器2021AI算法大赛 - 自动超参数优化竞赛 ACM CIKM 2021 AnalyticCup 在信息流推荐业务场景中普遍存在模型或策略效果依赖于“超参数”的问题,而“超参数"的设定往往依赖人工经验调参,不仅效率低下维护成本高,而且难以实现更优效果。因此,本次赛题以超参数优化为主题,从真

20 Dec 09, 2021
Python Library for learning (Structure and Parameter) and inference (Statistical and Causal) in Bayesian Networks.

pgmpy pgmpy is a python library for working with Probabilistic Graphical Models. Documentation and list of algorithms supported is at our official sit

pgmpy 2.2k Jan 03, 2023
This is a Tensorflow implementation of Learning to See in the Dark in CVPR 2018

Learning-to-See-in-the-Dark This is a Tensorflow implementation of Learning to See in the Dark in CVPR 2018, by Chen Chen, Qifeng Chen, Jia Xu, and Vl

5.3k Jan 01, 2023
Structured Data Gradient Pruning (SDGP)

Structured Data Gradient Pruning (SDGP) Weight pruning is a technique to make Deep Neural Network (DNN) inference more computationally efficient by re

Bradley McDanel 10 Nov 11, 2022
Official implementation of the paper 'Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution' in CVPR 2022

LDL Paper | Supplementary Material Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution Jie Liang*, Hu

150 Dec 26, 2022
Pytorch implementation of four neural network based domain adaptation techniques: DeepCORAL, DDC, CDAN and CDAN+E. Evaluated on benchmark dataset Office31.

Deep-Unsupervised-Domain-Adaptation Pytorch implementation of four neural network based domain adaptation techniques: DeepCORAL, DDC, CDAN and CDAN+E.

Alan Grijalva 49 Dec 20, 2022
The official implementation of Theme Transformer

Theme Transformer This is the official implementation of Theme Transformer. Checkout our demo and paper : Demo | arXiv Environment: using python versi

Ian Shih 85 Dec 08, 2022
PyStan, a Python interface to Stan, a platform for statistical modeling. Documentation: https://pystan.readthedocs.io

PyStan NOTE: This documentation describes a BETA release of PyStan 3. PyStan is a Python interface to Stan, a package for Bayesian inference. Stan® is

Stan 229 Dec 29, 2022
use tensorflow 2.0 to tell a dog and cat from a specified picture

dog_or_cat use tensorflow 2.0 to tell a dog and cat from a specified picture This is one of the classic experiments for the introduction of deep learn

你这个代码我看不懂 1 Oct 22, 2021
Tensorflow implementation of "Learning Deep Features for Discriminative Localization"

Weakly_detector Tensorflow implementation of "Learning Deep Features for Discriminative Localization" B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and

Taeksoo Kim 363 Jun 29, 2022
[ICRA 2022] An opensource framework for cooperative detection. Official implementation for OPV2V.

OpenCOOD OpenCOOD is an Open COOperative Detection framework for autonomous driving. It is also the official implementation of the ICRA 2022 paper OPV

Runsheng Xu 322 Dec 23, 2022
tsai is an open-source deep learning package built on top of Pytorch & fastai focused on state-of-the-art techniques for time series classification, regression and forecasting.

Time series Timeseries Deep Learning Pytorch fastai - State-of-the-art Deep Learning with Time Series and Sequences in Pytorch / fastai

timeseriesAI 2.8k Jan 08, 2023
modelvshuman is a Python library to benchmark the gap between human and machine vision

modelvshuman is a Python library to benchmark the gap between human and machine vision. Using this library, both PyTorch and TensorFlow models can be evaluated on 17 out-of-distribution datasets with

Bethge Lab 244 Jan 03, 2023