Self-supervised video representation learning by uncovering spatio-temporal statistics

Self-supervised video representation learning by uncovering spatio-temporal statistics

This paper proposes a novel pretext task to address the self-supervised video representation learning problem. Specifically, given an unlabeled video clip, we compute a series of spatio-temporal statistical summaries, such as the spatial location and dominant direction of the largest motion, the spa...

Fuld beskrivelse

Bibliografiske detaljer
Main Authors:	Wang, J, Jiao, J, Bao, L, He, S, Liu, W, Liu, YH
Format:	Journal article
Sprog:	English
Udgivet:	IEEE 2021

Lignende værker

Improving self-supervision in video representation learning
af: Liu, Hualin
Udgivet: (2021)

Self-supervised contrastive video-speech representation learning for ultrasound
af: Jiao, J, et al.
Udgivet: (2020)

Self-supervised video representation learning
af: Han, T
Udgivet: (2022)

Self-supervised representation learning for ultrasound video
af: Jaio, J, et al.
Udgivet: (2020)

Self-supervised co-training for video representation learning
af: Han, T, et al.
Udgivet: (2020)

Deep Learning of Invariant Spatio−Temporal Features from Video
af: Chen, B, et al.
Udgivet: (2010)

Spatio-temporal registration of dynamic PET data
af: Jiao, J
Udgivet: (2014)

Solving inefficiency of self-supervised representation learning
af: Wang, G, et al.
Udgivet: (2022)

Structured video content analysis : learning spatio-temporal and multimodal structures
af: Song, Yale
Udgivet: (2014)

Learning spatio-temporal aggregation for fetal heart analysis in ultrasound video
af: Patra, A, et al.
Udgivet: (2017)

Blind video quality prediction by uncovering human video perceptual representation
af: Liao, Liang, et al.
Udgivet: (2024)

Video Reflection Removal Through Spatio-Temporal Optimization
af: Nandoriya, Ajay, et al.
Udgivet: (2021)

Uncovering temporal structure in neural data with statistical machine learning models
af: Higgins, C
Udgivet: (2019)

Learning sparse representation via spatio-temporal smoothing for human activity recognition
af: Peng, Haiyun
Udgivet: (2015)

Self-supervised video understanding
af: Lu, E
Udgivet: (2021)

Semantic-aware auto-encoders for self-supervised representation learning
af: Wang, G, et al.
Udgivet: (2022)

Deep learning methods for weakly supervised video temporal action localization
af: Adipraja Widjaja, Sergi
Udgivet: (2020)

Deep self-supervised representation learning for free-hand sketch
af: Xu, Peng, et al.
Udgivet: (2022)

Self-supervised learning of class embeddings from video
af: Wiles, O, et al.
Udgivet: (2020)

Self-supervised and cross-modal learning from videos
af: Koepke, AS
Udgivet: (2019)

Leveraging transfer learning for spatio-temporal human activity recognition from video sequences
af: Muneer Butt, Umair, et al.
Udgivet: (2023)

Self-supervised learning of structural representations of visual objects
af: Jakab, T
Udgivet: (2021)

Spatio-temporal representation of the pitch of complex tones in the auditory nerve and cochlear nucleus
af: Wang, Grace I
Udgivet: (2008)

Made to order: discovering monotonic temporal changes via self-supervised video ordering
af: Yang, C, et al.
Udgivet: (2024)

Spatio-temporal enhanced sparse feature selection for video saliency estimation
af: Luo, Ye, et al.
Udgivet: (2013)

Learning and understanding deep spatio-temporal representations from free-hand fetal ultrasound sweeps
af: Y Gao, et al.
Udgivet: (2019)

Self-supervised learning of audio-visual objects from video
af: Afouras, T, et al.
Udgivet: (2020)

Self-supervised learning of interpretable keypoints from unlabelled videos
af: Jakab, T, et al.
Udgivet: (2020)

Video anomaly search in crowded scenes via spatio-temporal motion context
af: Cong, Yang, et al.
Udgivet: (2013)

Video event detection : from subvolume localization to spatio-temporal path search
af: Tran, Du, et al.
Udgivet: (2014)

Middle-level representation for human activities recognition : the role of spatio-temporal relationships
af: Yuan, Fei, et al.
Udgivet: (2014)

Self-supervised learning of a facial attribute embedding from video
af: Wiles, O, et al.
Udgivet: (2018)

Self-supervised learning for multi-person pose estimation and tracking in videos
af: Tan, Jia Min
Udgivet: (2023)

Self-supervised and supervised contrastive learning
af: Tan, Alvin De Jun
Udgivet: (2023)

Self-supervised multi-task representation learning for sequential medical images
af: Dong, N, et al.
Udgivet: (2021)

Motion learning using spatio-temporal neural network
af: Yusoff, Nooraini, et al.
Udgivet: (2020)

On the spatio-temporal representativeness of observations
af: Schutgens, N, et al.
Udgivet: (2017)

Weakly-supervised learning for video understanding
af: Deng, Dingfan
Udgivet: (2023)

Spatio-temporal accuracy of ICA for FMRI
af: Beckmann, C, et al.
Udgivet: (2001)

Spatio-temporal dynamics of automatic processing of phonological information in visual words
af: Wang, Xiao-Dong, et al.
Udgivet: (2014)