paper-with-me

Papers

Self-supervised Temporal Learning

2021-01-01 · Hao Shao, Yu Liu, Hongsheng Li

Self-supervised learning (SSL) has shown its powerful ability in discriminative representations for various visual, audio, and video applications. However, most recent works still focus on the different paradigms of spatial-level SSL on video representations. How to self-supervised learn the inherent representation on the temporal dimension is still unrevealed. In this work we propose self-supervised temporal learning (SSTL), aiming at learning spatial-temporal-invariance. Inspired by spatial-based contrastive SSL, we show that significant improvement can be achieved by a proposed temporal-based contrastive learning approach, which includes three novel and efficient modules: temporal augmentations, temporal memory bank and SSTL loss. The temporal augmentations include three operators -- temporal crop, temporal dropout, and temporal jitter. Besides the contrastive paradigm, we observe the temporal contents vary between each layer of the temporal pyramid. The SSTL extends the upper-bound of the current SSL approaches by $\sim$6% on the famous video classification tasks and surprisingly improves the current state-of-the-art approaches by $\sim$100% on some famous video retrieval tasks. The code of SSTL is released with this draft, hoping to nourish the progress of the booming self-supervised learning community.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningRetrievalSelf-Supervised LearningVideo ClassificationVideo Retrieval

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Self-Supervised Learning for Semi-Supervised Temporal Action Proposal

2021-04-07 · CVPR 2021 1 · Xiang Wang, Shiwei Zhang, Zhiwu Qing, Yuanjie Shao 외

Self-supervised learning presents a remarkable performance to utilize unlabeled data for various video tasks. In this paper, we focus on applying the power of self-supervised methods to improve semi-supervised action pro…

RelationSelf-Supervised LearningSemi-Supervised Action DetectionTemporal Action Localization

Two Stream Self-Supervised Learning for Action Recognition

2018-06-16 · Ahmed Taha, Moustafa Meshry, Xitong Yang, Yi-Ting Chen 외

We present a self-supervised approach using spatio-temporal signals between video frames for action recognition. A two-stream architecture is leveraged to tangle spatial and temporal representation learning. Our task is …

Action RecognitionRepresentation LearningSelf-Supervised LearningTemporal Action Localization+1

Can Temporal Information Help with Contrastive Self-Supervised Learning?

2020-11-25 · Yutong Bai, Haoqi Fan, Ishan Misra, Ganesh Venkatesh 외

Leveraging temporal information has been regarded as essential for developing video understanding models. However, how to properly incorporate temporal information into the recent successful instance discrimination based…

Data AugmentationRepresentation LearningSelf-Supervised LearningVideo Understanding

PhySU-Net: Long Temporal Context Transformer for rPPG with Self-Supervised Pre-training

2024-02-19 · Marko Savic, Guoying Zhao

Remote photoplethysmography (rPPG) is a promising technology that consists of contactless measuring of cardiac activity from facial videos. Most recent approaches utilize convolutional networks with limited temporal mode…

Self-supervised Learning for Semi-supervised Temporal Language Grounding

2021-09-23 · Fan Luo, Shaoxiang Chen, Jingjing Chen, Zuxuan Wu 외

Given a text description, Temporal Language Grounding (TLG) aims to localize temporal boundaries of the segments that contain the specified semantics in an untrimmed video. TLG is inherently a challenging task, as it req…

Contrastive LearningPseudo LabelSelf-Supervised LearningSentence