☆ 4.7 Article

An Improved Inter-Intra Contrastive Learning Framework on Self-Supervised Video Representation

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2022)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Engineering, Electrical & Electronic

Task-Specific Loss for Robust Instance Segmentation With Noisy Class Labels

Longrong Yang et al.

Summary: A novel method is proposed in this paper to address the issues of annotation confusion and misleading in instance segmentation. Different loss functions are used for different sub-tasks to provide correct gradient guidance, and contrastive self-supervised loss is applied to update features. Extensive experiments demonstrate the effectiveness of this method in various noisy class label scenarios.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2023)

添加到收藏夹

Article Engineering, Electrical & Electronic

Deep Self-Supervised Representation Learning for Free-Hand Sketch

Peng Xu et al.

Summary: This paper addresses the problem of self-supervised representation learning for free-hand sketches, introducing specific pretext tasks and a dual-branch architecture designed for sketches. Experimental results on a large-scale sketch dataset demonstrate that the proposed approach outperforms state-of-the-art unsupervised representation learning methods, narrowing the performance gap with supervised representation learning.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Graph-Based CNNs With Self-Supervised Module for 3D Hand Pose Estimation From Monocular RGB

Shaoxiang Guo et al.

Summary: The paper explores the prediction of 3D hand poses from a single RGB image, utilizing multiple feature maps, graph-based convolutional neural networks, and self-supervised modules to improve the accuracy of hand pose estimation.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Mining Better Samples for Contrastive Learning of Temporal Correspondence

Sangryul Jeon et al.

Summary: A novel framework for contrastive learning of pixel-level representation using only unlabeled video is proposed, which collects well-defined positive and negative correspondences by measuring confidences and adjusting hardness during training. The method suppresses the adverse impact of ambiguous matches and prevents trivial solutions by incorporating three different criteria and a curriculum for adaptive hardness of negative samples. State-of-the-art performance is achieved over the latest approaches on several video label propagation tasks with this method.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Rethinking Motion Representation: Residual Frames With 3D ConvNets

Li Tao et al.

Summary: This paper proposes a method of utilizing residual frames in 3D ConvNets to extract motion features, which significantly improves action recognition performance compared to traditional stacked RGB frames.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Attribute-Identity Embedding and Self-Supervised Learning for Scalable Person Re-Identification

Huafeng Li et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2020)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Evolving Losses for Unsupervised Video Representation Learning

A. J. Piergiovanni et al.

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

Parking Space Status Inference Upon a Deep CNN and Multi-Task Contrastive Network With Spatial Transform

Hoang Tran Vu et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2019)

添加到收藏夹

Article Engineering, Electrical & Electronic

Semantic Cues Enhanced Multimodality Multistream CNN for Action Recognition

Zhigang Tu et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning

Chuang Gan et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

添加到收藏夹

Article Engineering, Electrical & Electronic

Two-Stream Dictionary Learning Architecture for Action Recognition

Ke Xu et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

The something something video database for learning and evaluating visual common sense

Raghav Goyal et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Self-Supervised Video Representation Learning With Odd-One-Out Networks

Basura Fernando et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset

Joao Carreira et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Unsupervised Representation Learning by Sorting Sequences

Hsin-Ying Lee et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Webly-Supervised Video Recognition by Mutually Voting for Relevant Web Images and Web Video Frames

Chuang Gan et al.

COMPUTER VISION - ECCV 2016, PT III (2016)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Learning Spatiotemporal Features with 3D Convolutional Networks

Du Tran et al.

2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2015)

添加到收藏夹

Article Multidisciplinary Sciences

Reducing the dimensionality of data with neural networks

G. E. Hinton et al.

SCIENCE (2006)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.