paper-with-me

홈 › Papers

Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency

2022-04-06 · CVPR 2022 1 · Zhiwu Qing, Shiwei Zhang, Ziyuan Huang, Yi Xu, Xiang Wang, Mingqian Tang, Changxin Gao, Rong Jin, Nong Sang

Natural videos provide rich visual contents for self-supervised learning. Yet most existing approaches for learning spatio-temporal representations rely on manually trimmed videos, leading to limited diversity in visual patterns and limited performance gain. In this work, we aim to learn representations by leveraging more abundant information in untrimmed videos. To this end, we propose to learn a hierarchy of consistencies in videos, i.e., visual consistency and topical consistency, corresponding respectively to clip pairs that tend to be visually similar when separated by a short time span and share similar topics when separated by a long time span. Specifically, a hierarchical consistency learning framework HiCo is presented, where the visually consistent pairs are encouraged to have the same representation through contrastive learning, while the topically consistent pairs are coupled through a topical classifier that distinguishes whether they are topic related. Further, we impose a gradual sampling algorithm for proposed hierarchical consistency learning, and demonstrate its theoretical superiority. Empirically, we show that not only HiCo can generate stronger representations on untrimmed videos, it also improves the representation quality when applied to trimmed videos. This is in contrast to standard contrastive learning that fails to learn appropriate representations from untrimmed videos.

📄 PDF Abstract BibTeX arXiv:2204.03017

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningRepresentation LearningSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Exploring Relations in Untrimmed Videos for Self-Supervised Learning

2020-08-06 · Dezhao Luo, Bo Fang, Yu Zhou, Yucan Zhou 외

Existing video self-supervised learning methods mainly rely on trimmed videos for model training. However, trimmed datasets are manually annotated from untrimmed videos. In this sense, these methods are not really self-s…

Action RecognitionChange DetectionRetrievalSelf-Supervised Learning+1

Deep Learning-based Action Detection in Untrimmed Videos: A Survey

2021-09-30 · Elahe Vahdani, YingLi Tian

Understanding human behavior and activity facilitates advancement of numerous real-world applications, and is critical for video analysis. Despite the progress of action recognition algorithms in trimmed videos, the majo…

Action DetectionAction RecognitionActivity DetectionDeep Learning

Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision

2019-02-20 · Xiao-Yu Zhang, Haichao Shi, Changsheng Li, Kai Zheng 외

Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotation…

Action RecognitionAction Recognition In VideosTemporal Action Localization

Few-Shot Action Localization without Knowing Boundaries

2021-06-08 · Ting-Ting Xie, Christos Tzelepis, Fan Fu, Ioannis Patras

Learning to localize actions in long, cluttered, and untrimmed videos is a hard task, that in the literature has typically been addressed assuming the availability of large amounts of annotated training samples for each …

Action LocalizationFew-Shot Learning

What When and Where? Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions

2024-01-01 · CVPR 2024 1 · Brian Chen, Nina Shvetsova, Andrew Rouditchenko, Daniel Kondermann 외

Spatio-temporal grounding describes the task of localizing events in space and time e.g. in video data based on verbal descriptions only. Models for this task are usually trained with human-annotated sentences and bo…

Representation Learning