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
[CVPR 2021] Forecasting the panoptic segmentation of future video frames

Panoptic Segmentation Forecasting Colin Graber, Grace Tsai, Michael Firman, Gabriel Brostow, Alexander Schwing - CVPR 2021 [Link to paper] We propose

Niantic Labs 44 Nov 29, 2022
A general framework for inferring CNNs efficiently. Reduce the inference latency of MobileNet-V3 by 1.3x on an iPhone XS Max without sacrificing accuracy.

GFNet-Pytorch (NeurIPS 2020) This repo contains the official code and pre-trained models for the glance and focus network (GFNet). Glance and Focus: a

Rainforest Wang 169 Oct 28, 2022
FAST-RIR: FAST NEURAL DIFFUSE ROOM IMPULSE RESPONSE GENERATOR

This is the official implementation of our neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given acoustic environment.

Anton Jeran Ratnarajah 89 Dec 22, 2022
Data and codes for ACL 2021 paper: Towards Emotional Support Dialog Systems

Emotional-Support-Conversation Copyright © 2021 CoAI Group, Tsinghua University. All rights reserved. Data and codes are for academic research use onl

126 Dec 21, 2022
Re-implememtation of MAE (Masked Autoencoders Are Scalable Vision Learners) using PyTorch.

mae-repo PyTorch re-implememtation of "masked autoencoders are scalable vision learners". In this repo, it heavily borrows codes from codebase https:/

Peng Qiao 1 Dec 14, 2021
External Attention Network

Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks paper : https://arxiv.org/abs/2105.02358 Jittor code will come soon

MenghaoGuo 357 Dec 11, 2022
This repository accompanies our paper “Do Prompt-Based Models Really Understand the Meaning of Their Prompts?”

This repository accompanies our paper “Do Prompt-Based Models Really Understand the Meaning of Their Prompts?” Usage To replicate our results in Secti

Albert Webson 64 Dec 11, 2022
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

Generative Models Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow. Also present here are RBM and Helmholtz Machine. Note: Gen

Agustinus Kristiadi 7k Jan 02, 2023
Pytorch implementation of "Get To The Point: Summarization with Pointer-Generator Networks"

About this repository This repo contains an Pytorch implementation for the ACL 2017 paper Get To The Point: Summarization with Pointer-Generator Netwo

wxDai 7 Oct 14, 2022
Runtime type annotations for the shape, dtype etc. of PyTorch Tensors.

torchtyping Type annotations for a tensor's shape, dtype, names, ... Turn this: def batch_outer_product(x: torch.Tensor, y: torch.Tensor) - torch.Ten

Patrick Kidger 1.2k Jan 03, 2023
Udacity Suse Cloud Native Foundations Scholarship Course Walkthrough

SUSE Cloud Native Foundations Scholarship Udacity is collaborating with SUSE, a global leader in true open source solutions, to empower developers and

Shivansh Srivastava 34 Oct 18, 2022
Canonical Capsules: Unsupervised Capsules in Canonical Pose (NeurIPS 2021)

Canonical Capsules: Unsupervised Capsules in Canonical Pose (NeurIPS 2021) Introduction This is the official repository for the PyTorch implementation

165 Dec 07, 2022
List some popular DeepFake models e.g. DeepFake, FaceSwap-MarekKowal, IPGAN, FaceShifter, FaceSwap-Nirkin, FSGAN, SimSwap, CihaNet, etc.

deepfake-models List some popular DeepFake models e.g. DeepFake, CihaNet, SimSwap, FaceSwap-MarekKowal, IPGAN, FaceShifter, FaceSwap-Nirkin, FSGAN, Si

Mingcan Xiang 100 Dec 17, 2022
This is the official code of our paper "Diversity-based Trajectory and Goal Selection with Hindsight Experience Relay" (PRICAI 2021)

Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay This is the official implementation of our paper "Diversity-based Traje

Tianhong Dai 6 Jul 18, 2022
Reimplement of SimSwap training code

SimSwap-train Reimplement of SimSwap training code Instructions 1.Environment Preparation (1)Refer to the README document of SIMSWAP to configure the

seeprettyface.com 111 Dec 31, 2022
Auditing Black-Box Prediction Models for Data Minimization Compliance

Data-Minimization-Auditor An auditing tool for model-instability based data minimization that is introduced in "Auditing Black-Box Prediction Models f

Bashir Rastegarpanah 2 Mar 24, 2022
Pytorch-Swin-Unet-V2 - a modified version of Swin Unet based on Swin Transfomer V2

Swin Unet V2 Swin Unet V2 is a modified version of Swin Unet arxiv based on Swin

Chenxu Peng 26 Dec 03, 2022
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

Peter Lin 6.5k Jan 04, 2023
PyTorch Live is an easy to use library of tools for creating on-device ML demos on Android and iOS.

PyTorch Live is an easy to use library of tools for creating on-device ML demos on Android and iOS. With Live, you can build a working mobile app ML demo in minutes.

559 Jan 01, 2023
TensorFlow-based implementation of "ICNet for Real-Time Semantic Segmentation on High-Resolution Images".

ICNet_tensorflow This repo provides a TensorFlow-based implementation of paper "ICNet for Real-Time Semantic Segmentation on High-Resolution Images,"

HsuanKung Yang 406 Nov 27, 2022