paper-with-me

Papers

Self-supervised Video Transformer

2021-12-02 · CVPR 2022 1 · Kanchana Ranasinghe, Muzammal Naseer, Salman Khan, Fahad Shahbaz Khan, Michael Ryoo

In this paper, we propose self-supervised training for video transformers using unlabeled video data. From a given video, we create local and global spatiotemporal views with varying spatial sizes and frame rates. Our self-supervised objective seeks to match the features of these different views representing the same video, to be invariant to spatiotemporal variations in actions. To the best of our knowledge, the proposed approach is the first to alleviate the dependency on negative samples or dedicated memory banks in Self-supervised Video Transformer (SVT). Further, owing to the flexibility of Transformer models, SVT supports slow-fast video processing within a single architecture using dynamically adjusted positional encoding and supports long-term relationship modeling along spatiotemporal dimensions. Our approach performs well on four action recognition benchmarks (Kinetics-400, UCF-101, HMDB-51, and SSv2) and converges faster with small batch sizes. Code: https://git.io/J1juJ

📄 PDF Abstract BibTeX arXiv:2112.01514

Code (1)

kahnchana/svt 공식 구현 pytorch

Tasks

Action ClassificationAction RecognitionAction Recognition In VideosSelf-Supervised Action Recognition Linear

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Self-supervised Video-centralised Transformer for Video Face Clustering

2022-03-24 · Yujiang Wang, Mingzhi Dong, Jie Shen, Yiming Luo 외

This paper presents a novel method for face clustering in videos using a video-centralised transformer. Previous works often employed contrastive learning to learn frame-level representation and used average pooling to a…

ClusteringContrastive LearningFace Clustering

SPARTAN: Self-supervised Spatiotemporal Transformers Approach to Group Activity Recognition

2023-03-06 · Naga VS Raviteja Chappa, Pha Nguyen, Alexander H Nelson, Han-Seok Seo 외

In this paper, we propose a new, simple, and effective Self-supervised Spatio-temporal Transformers (SPARTAN) approach to Group Activity Recognition (GAR) using unlabeled video data. Given a video, we create local and gl…

Activity RecognitionGroup Activity Recognition

Long-Short Temporal Contrastive Learning of Video Transformers

2021-06-17 · CVPR 2022 1 · Jue Wang, Gedas Bertasius, Du Tran, Lorenzo Torresani

Video transformers have recently emerged as a competitive alternative to 3D CNNs for video understanding. However, due to their large number of parameters and reduced inductive biases, these models require supervised pre…

Action RecognitionContrastive LearningVideo Understanding

Transformer-based Self-Supervised Fish Segmentation in Underwater Videos

2022-06-11 · Alzayat Saleh, Marcus Sheaves, Dean Jerry, Mostafa Rahimi Azghadi

Underwater fish segmentation to estimate fish body measurements is still largely unsolved due to the complex underwater environment. Relying on fully-supervised segmentation models requires collecting per-pixel labels, w…

Representation LearningSegmentationSelf-Supervised Learning

Self-Supervised Video Hashing via Bidirectional Transformers

2021-06-19 · CVPR 2021 1 · Shuyan Li, Xiu Li, Jiwen Lu, Jie zhou

Most existing unsupervised video hashing methods are built on unidirectional models with less reliable training objectives, which underuse the correlations among frames and the similarity structure between videos. To…

DecoderRetrievalVideo Retrieval