NPF-200: A multi-modal eye fixation dataset and method for non-photorealistic videos
Non-photorealistic videos are in demand with the wave of the metaverse, but lack of sufficient research studies. This work aims to take a step forward to understand how humans perceive nonphotorealistic videos with eye fixation (i.e., saliency detection), which is critical for enhancing media produc...
Saved in:
Main Authors: | , , , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8384 https://ink.library.smu.edu.sg/context/sis_research/article/9387/viewcontent/NPF_200_pvoa_cc_by.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-9387 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-93872023-12-20T03:18:33Z NPF-200: A multi-modal eye fixation dataset and method for non-photorealistic videos YANG, Ziyu REN, Sucheng WU, Zongwei ZHAO, Nanxuan WANG, Junle QIN, Jing HE, Shengfeng Non-photorealistic videos are in demand with the wave of the metaverse, but lack of sufficient research studies. This work aims to take a step forward to understand how humans perceive nonphotorealistic videos with eye fixation (i.e., saliency detection), which is critical for enhancing media production, artistic design, and game user experience. To fill in the gap of missing a suitable dataset for this research line, we present NPF-200, the first largescale multi-modal dataset of purely non-photorealistic videos with eye fixations. Our dataset has three characteristics: 1) it contains soundtracks that are essential according to vision and psychological studies; 2) it includes diverse semantic content and videos are of high-quality; 3) it has rich motions across and within videos. We conduct a series of analyses to gain deeper insights into this task and compare several state-of-the-art methods to explore the gap between natural images and non-photorealistic data. Additionally, as the human attention system tends to extract visual and audio features with different frequencies, we propose a universal frequency-aware multi-modal non-photorealistic saliency detection model called NPSNet, demonstrating the state-of-the-art performance of our task. The results uncover strengths and weaknesses of multi-modal network design and multi-domain training, opening up promising directions for future works. Our dataset and code can be found at https://github.com/Yangziyu/NPF200. 2023-11-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8384 info:doi/10.1145/3581783.3611839 https://ink.library.smu.edu.sg/context/sis_research/article/9387/viewcontent/NPF_200_pvoa_cc_by.pdf http://creativecommons.org/licenses/by/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Non-photorealistic videos Eye fixation Multi-modal frequency Graphics and Human Computer Interfaces Numerical Analysis and Scientific Computing |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Non-photorealistic videos Eye fixation Multi-modal frequency Graphics and Human Computer Interfaces Numerical Analysis and Scientific Computing |
spellingShingle |
Non-photorealistic videos Eye fixation Multi-modal frequency Graphics and Human Computer Interfaces Numerical Analysis and Scientific Computing YANG, Ziyu REN, Sucheng WU, Zongwei ZHAO, Nanxuan WANG, Junle QIN, Jing HE, Shengfeng NPF-200: A multi-modal eye fixation dataset and method for non-photorealistic videos |
description |
Non-photorealistic videos are in demand with the wave of the metaverse, but lack of sufficient research studies. This work aims to take a step forward to understand how humans perceive nonphotorealistic videos with eye fixation (i.e., saliency detection), which is critical for enhancing media production, artistic design, and game user experience. To fill in the gap of missing a suitable dataset for this research line, we present NPF-200, the first largescale multi-modal dataset of purely non-photorealistic videos with eye fixations. Our dataset has three characteristics: 1) it contains soundtracks that are essential according to vision and psychological studies; 2) it includes diverse semantic content and videos are of high-quality; 3) it has rich motions across and within videos. We conduct a series of analyses to gain deeper insights into this task and compare several state-of-the-art methods to explore the gap between natural images and non-photorealistic data. Additionally, as the human attention system tends to extract visual and audio features with different frequencies, we propose a universal frequency-aware multi-modal non-photorealistic saliency detection model called NPSNet, demonstrating the state-of-the-art performance of our task. The results uncover strengths and weaknesses of multi-modal network design and multi-domain training, opening up promising directions for future works. Our dataset and code can be found at https://github.com/Yangziyu/NPF200. |
format |
text |
author |
YANG, Ziyu REN, Sucheng WU, Zongwei ZHAO, Nanxuan WANG, Junle QIN, Jing HE, Shengfeng |
author_facet |
YANG, Ziyu REN, Sucheng WU, Zongwei ZHAO, Nanxuan WANG, Junle QIN, Jing HE, Shengfeng |
author_sort |
YANG, Ziyu |
title |
NPF-200: A multi-modal eye fixation dataset and method for non-photorealistic videos |
title_short |
NPF-200: A multi-modal eye fixation dataset and method for non-photorealistic videos |
title_full |
NPF-200: A multi-modal eye fixation dataset and method for non-photorealistic videos |
title_fullStr |
NPF-200: A multi-modal eye fixation dataset and method for non-photorealistic videos |
title_full_unstemmed |
NPF-200: A multi-modal eye fixation dataset and method for non-photorealistic videos |
title_sort |
npf-200: a multi-modal eye fixation dataset and method for non-photorealistic videos |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2023 |
url |
https://ink.library.smu.edu.sg/sis_research/8384 https://ink.library.smu.edu.sg/context/sis_research/article/9387/viewcontent/NPF_200_pvoa_cc_by.pdf |
_version_ |
1787136847763210240 |