SMILE: Infusing Spatial and Motion Semantics in Masked Video Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Thoker, Fida Mohammad, Jiang, Letian, Zhao, Chen, Ghanem, Bernard
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917972921024512
author Thoker, Fida Mohammad
Jiang, Letian
Zhao, Chen
Ghanem, Bernard
author_facet Thoker, Fida Mohammad
Jiang, Letian
Zhao, Chen
Ghanem, Bernard
contents Masked video modeling, such as VideoMAE, is an effective paradigm for video self-supervised learning (SSL). However, they are primarily based on reconstructing pixel-level details on natural videos which have substantial temporal redundancy, limiting their capability for semantic representation and sufficient encoding of motion dynamics. To address these issues, this paper introduces a novel SSL approach for video representation learning, dubbed as SMILE, by infusing both spatial and motion semantics. In SMILE, we leverage image-language pretrained models, such as CLIP, to guide the learning process with their high-level spatial semantics. We enhance the representation of motion by introducing synthetic motion patterns in the training data, allowing the model to capture more complex and dynamic content. Furthermore, using SMILE, we establish a new self-supervised video learning paradigm capable of learning strong video representations without requiring any natural video data. We have carried out extensive experiments on 7 datasets with various downstream scenarios. SMILE surpasses current state-of-the-art SSL methods, showcasing its effectiveness in learning more discriminative and generalizable video representations. Code is available: https://github.com/fmthoker/SMILE
format Preprint
id arxiv_https___arxiv_org_abs_2504_00527
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SMILE: Infusing Spatial and Motion Semantics in Masked Video Learning
Thoker, Fida Mohammad
Jiang, Letian
Zhao, Chen
Ghanem, Bernard
Computer Vision and Pattern Recognition
Masked video modeling, such as VideoMAE, is an effective paradigm for video self-supervised learning (SSL). However, they are primarily based on reconstructing pixel-level details on natural videos which have substantial temporal redundancy, limiting their capability for semantic representation and sufficient encoding of motion dynamics. To address these issues, this paper introduces a novel SSL approach for video representation learning, dubbed as SMILE, by infusing both spatial and motion semantics. In SMILE, we leverage image-language pretrained models, such as CLIP, to guide the learning process with their high-level spatial semantics. We enhance the representation of motion by introducing synthetic motion patterns in the training data, allowing the model to capture more complex and dynamic content. Furthermore, using SMILE, we establish a new self-supervised video learning paradigm capable of learning strong video representations without requiring any natural video data. We have carried out extensive experiments on 7 datasets with various downstream scenarios. SMILE surpasses current state-of-the-art SSL methods, showcasing its effectiveness in learning more discriminative and generalizable video representations. Code is available: https://github.com/fmthoker/SMILE
title SMILE: Infusing Spatial and Motion Semantics in Masked Video Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.00527