ruohaoguo/pavsodr
Official Implementation of "Instance-Level Panoramic Audio-Visual Saliency Detection and Ranking" [ACM MM 2024].
This project helps video analysts and content creators automatically identify the most captivating objects in 360-degree panoramic videos that have sound. You input a panoramic video with audio, and it outputs segmented visual regions corresponding to individual salient objects, along with a ranking of how much each object attracts attention. This is ideal for anyone working with immersive video content who needs to understand viewer focus.
No commits in the last 6 months.
Use this if you need to pinpoint and rank specific attention-grabbing objects within a 360-degree video, especially when sound plays a role.
Not ideal if you are working with standard (non-panoramic) videos or if your primary interest is in general scene understanding rather than specific object saliency.
Stars
11
Forks
—
Language
Python
License
MIT
Category
Last pushed
Jul 28, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ruohaoguo/pavsodr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
BR-IDL/PaddleViT
:robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+
pathak22/unsupervised-video
[CVPR 2017] Unsupervised deep learning using unlabelled videos on the web
IBM/CrossViT
Official implementation of CrossViT. https://arxiv.org/abs/2103.14899
NVlabs/GCVit
[ICML 2023] Official PyTorch implementation of Global Context Vision Transformers
ViTAE-Transformer/ViTDet
Unofficial implementation for [ECCV'22] "Exploring Plain Vision Transformer Backbones for Object...