paper-with-me

Papers

Exploiting Spatio-Temporal Structure with Recurrent Winner-Take-All Networks

2016-10-31 · Eder Santana, Matthew Emigh, Pablo Zegers, Jose C. Principe

We propose a convolutional recurrent neural network, with Winner-Take-All dropout for high dimensional unsupervised feature learning in multi-dimensional time series. We apply the proposedmethod for object recognition with temporal context in videos and obtain better results than comparable methods in the literature, including the Deep Predictive Coding Networks previously proposed by Chalasani and Principe.Our contributions can be summarized as a scalable reinterpretation of the Deep Predictive Coding Networks trained end-to-end with backpropagation through time, an extension of the previously proposed Winner-Take-All Autoencoders to sequences in time, and a new technique for initializing and regularizing convolutional-recurrent neural networks.

📄 PDF Abstract BibTeX arXiv:1611.00050

Code (0)

등록된 구현이 없습니다.

Tasks

AllObject RecognitionTime SeriesTime Series Analysis

Similar Papers 제목 키워드 기반

WINNER: Weakly-Supervised hIerarchical decompositioN and aligNment for Spatio-tEmporal Video gRounding

2023-01-01 · CVPR 2023 1 · Mengze Li, Han Wang, Wenqiao Zhang, Jiaxu Miao 외

Spatio-temporal video grounding aims to localize the aligned visual tube corresponding to a language query. Existing techniques achieve such alignment by exploiting dense boundary and bounding box annotations, which can …

Contrastive LearningSpatio-Temporal Video GroundingVideo Grounding

Spartus: A 9.4 TOp/s FPGA-based LSTM Accelerator Exploiting Spatio-Temporal Sparsity

2021-08-04 · Chang Gao, Tobi Delbruck, Shih-Chii Liu

Long Short-Term Memory (LSTM) recurrent networks are frequently used for tasks involving time-sequential data such as speech recognition. Unlike previous LSTM accelerators that either exploit spatial weight sparsity or t…

speech-recognitionSpeech Recognition

A Temporally Disentangled Contrastive Diffusion Model for Spatiotemporal Imputation

2024-02-18 · Yakun Chen, Kaize Shi, Zhangkai Wu, Juan Chen 외

Spatiotemporal data analysis is pivotal across various domains, such as transportation, meteorology, and healthcare. The data collected in real-world scenarios are often incomplete due to device malfunctions and network …

Contrastive LearningImputationMissing Values

Structured Sequence Modeling with Graph Convolutional Recurrent Networks

2016-12-22 · Youngjoo Seo, Michaël Defferrard, Pierre Vandergheynst, Xavier Bresson

This paper introduces Graph Convolutional Recurrent Network (GCRN), a deep learning model able to predict structured sequences of data. Precisely, GCRN is a generalization of classical recurrent neural networks (RNN) to …

Language ModelingLanguage Modelling

Deep Learning Method for Cell-Wise Object Tracking, Velocity Estimation and Projection of Sensor Data over Time

2023-06-08 · Marco Braun, Moritz Luszek, Mirko Meuter, Dominic Spata 외

Current Deep Learning methods for environment segmentation and velocity estimation rely on Convolutional Recurrent Neural Networks to exploit spatio-temporal relationships within obtained sensor data. These approaches de…

Object Tracking