ARID: A New Dataset for Recognizing Action in the Dark
- URL: http://arxiv.org/abs/2006.03876v4
- Date: Fri, 19 Aug 2022 05:41:15 GMT
- Title: ARID: A New Dataset for Recognizing Action in the Dark
- Authors: Yuecong Xu, Jianfei Yang, Haozhi Cao, Kezhi Mao, Jianxiong Yin and
Simon See
- Abstract summary: This paper explores the task of action recognition in dark videos.
It consists of over 3,780 video clips with 11 action categories.
To the best of our knowledge, it is the first dataset focused on human actions in dark videos.
- Score: 19.010874017607247
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: The task of action recognition in dark videos is useful in various scenarios,
e.g., night surveillance and self-driving at night. Though progress has been
made in the action recognition task for videos in normal illumination, few have
studied action recognition in the dark. This is partly due to the lack of
sufficient datasets for such a task. In this paper, we explored the task of
action recognition in dark videos. We bridge the gap of the lack of data for
this task by collecting a new dataset: the Action Recognition in the Dark
(ARID) dataset. It consists of over 3,780 video clips with 11 action
categories. To the best of our knowledge, it is the first dataset focused on
human actions in dark videos. To gain further understandings of our ARID
dataset, we analyze the ARID dataset in detail and exhibited its necessity over
synthetic dark videos. Additionally, we benchmarked the performance of several
current action recognition models on our dataset and explored potential methods
for increasing their performances. Our results show that current action
recognition models and frame enhancement methods may not be effective solutions
for the task of action recognition in dark videos.
Related papers
- Egocentric RGB+Depth Action Recognition in Industry-Like Settings [50.38638300332429]
Our work focuses on recognizing actions from egocentric RGB and Depth modalities in an industry-like environment.
Our framework is based on the 3D Video SWIN Transformer to encode both RGB and Depth modalities effectively.
Our method also secured first place at the multimodal action recognition challenge at ICIAP 2023.
arXiv Detail & Related papers (2023-09-25T08:56:22Z) - IndGIC: Supervised Action Recognition under Low Illumination [0.0]
We propose action recognition method using deep multi-input network.
Ind-GIC is proposed to enhance poor-illumination video, generating one gamma for one frame to increase enhancement performance.
Experimental results show that our model achieves high accuracy in on ARID dataset.
arXiv Detail & Related papers (2023-08-29T14:41:10Z) - Adversarial Domain Adaptation for Action Recognition Around the Clock [0.7614628596146599]
This paper presents a domain adaptation-based action recognition approach.
It uses adversarial learning in cross-domain settings to learn cross-domain action recognition.
It achieves SOTA performance on InFAR and XD145 actions datasets.
arXiv Detail & Related papers (2022-10-25T01:08:27Z) - ActAR: Actor-Driven Pose Embeddings for Video Action Recognition [12.043574473965318]
Human action recognition (HAR) in videos is one of the core tasks of video understanding.
We propose a new method that simultaneously learns to recognize efficiently human actions in the infrared spectrum.
arXiv Detail & Related papers (2022-04-19T05:12:24Z) - Video Action Detection: Analysing Limitations and Challenges [70.01260415234127]
We analyze existing datasets on video action detection and discuss their limitations.
We perform a biasness study which analyzes a key property differentiating videos from static images: the temporal aspect.
Such extreme experiments show existence of biases which have managed to creep into existing methods inspite of careful modeling.
arXiv Detail & Related papers (2022-04-17T00:42:14Z) - A Comprehensive Study of Deep Video Action Recognition [35.7068977497202]
Video action recognition is one of the representative tasks for video understanding.
We provide a comprehensive survey of over 200 existing papers on deep learning for video action recognition.
arXiv Detail & Related papers (2020-12-11T18:54:08Z) - Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition [86.31412529187243]
Few-shot video recognition aims at learning new actions with only very few labeled samples.
We propose a depth guided Adaptive Meta-Fusion Network for few-shot video recognition which is termed as AMeFu-Net.
arXiv Detail & Related papers (2020-10-20T03:06:20Z) - Toward Accurate Person-level Action Recognition in Videos of Crowded
Scenes [131.9067467127761]
We focus on improving the action recognition by fully-utilizing the information of scenes and collecting new data.
Specifically, we adopt a strong human detector to detect spatial location of each frame.
We then apply action recognition models to learn thetemporal information from video frames on both the HIE dataset and new data with diverse scenes from the internet.
arXiv Detail & Related papers (2020-10-16T13:08:50Z) - TinyVIRAT: Low-resolution Video Action Recognition [70.37277191524755]
In real-world surveillance environments, the actions in videos are captured at a wide range of resolutions.
We introduce a benchmark dataset, TinyVIRAT, which contains natural low-resolution activities.
We propose a novel method for recognizing tiny actions in videos which utilizes a progressive generative approach.
arXiv Detail & Related papers (2020-07-14T21:09:18Z) - ZSTAD: Zero-Shot Temporal Activity Detection [107.63759089583382]
We propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training can still be detected.
We design an end-to-end deep network based on R-C3D as the architecture for this solution.
Experiments on both the THUMOS14 and the Charades datasets show promising performance in terms of detecting unseen activities.
arXiv Detail & Related papers (2020-03-12T02:40:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.