paper-with-me

Papers

Two Stream Self-Supervised Learning for Action Recognition

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

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 formulated as both a sequence verification and spatio-temporal alignment tasks. The former task requires motion temporal structure understanding while the latter couples the learned motion with the spatial representation. The self-supervised pre-trained weights effectiveness is validated on the action recognition task. Quantitative evaluation shows the self-supervised approach competence on three datasets: HMDB51, UCF101, and Honda driving dataset (HDD). Further investigations to boost performance and generalize validity are still required.

📄 PDF Abstract BibTeX arXiv:1806.07383

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionRepresentation LearningSelf-Supervised LearningTemporal Action LocalizationVocal Bursts Valence Prediction

Similar Papers 제목 키워드 기반

Preserve Pre-trained Knowledge: Transfer Learning With Self-Distillation For Action Recognition

2022-05-01 · Yang Zhou, Zhanhao He, Keyu Lu, Guanhong Wang 외

Video-based action recognition is one of the most popular topics in computer vision. With recent advances of selfsupervised video representation learning approaches, action recognition usually follows a two-stage trainin…

Action RecognitionRepresentation LearningTransfer Learning

Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition

2023-07-15 · Mengyuan Liu, Hong Liu, Tianyu Guo

Considering the instance-level discriminative ability, contrastive learning methods, including MoCo and SimCLR, have been adapted from the original image representation learning task to solve the self-supervised skeleton…

Action RecognitionContrastive LearningEnsemble LearningPseudo Label+6

Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition

2024-09-23 · IEEE Transactions on Human-Machine Systems 2024 9 · Liu, Mengyuan; Liu, Hong; Guo, Tianyu

Considering the instance-level discriminative ability, contrastive learning methods, including MoCo and SimCLR, have been adapted from the original image representation learning task to solve the self-supervised skeleton…

Action RecognitionContrastive LearningEnsemble LearningPseudo Label+5

SS-VAERR: Self-Supervised Apparent Emotional Reaction Recognition from Video

2022-10-20 · Marija Jegorova, Stavros Petridis, Maja Pantic

This work focuses on the apparent emotional reaction recognition (AERR) from the video-only input, conducted in a self-supervised fashion. The network is first pre-trained on different self-supervised pretext tasks and l…

Self-Supervised Learning

Self-Supervised Learning via multi-Transformation Classification for Action Recognition

2021-02-20 · Duc Quang Vu, Ngan T. H. Le, Jia-Ching Wang

Self-supervised tasks have been utilized to build useful representations that can be used in downstream tasks when the annotation is unavailable. In this paper, we introduce a self-supervised video representation learnin…

Action RecognitionClassificationGeneral ClassificationRepresentation Learning+2