paper-with-me

Papers

Non-local Recurrent Neural Memory for Supervised Sequence Modeling

2019-08-26 · ICCV 2019 10 · Canmiao Fu, Wenjie Pei, Qiong Cao, Chaopeng Zhang, Yong Zhao, Xiaoyong Shen, Yu-Wing Tai

Typical methods for supervised sequence modeling are built upon the recurrent neural networks to capture temporal dependencies. One potential limitation of these methods is that they only model explicitly information interactions between adjacent time steps in a sequence, hence the high-order interactions between nonadjacent time steps are not fully exploited. It greatly limits the capability of modeling the long-range temporal dependencies since one-order interactions cannot be maintained for a long term due to information dilution and gradient vanishing. To tackle this limitation, we propose the Non-local Recurrent Neural Memory (NRNM) for supervised sequence modeling, which performs non-local operations to learn full-order interactions within a sliding temporal block and models global interactions between blocks in a gated recurrent manner. Consequently, our model is able to capture the long-range dependencies. Besides, the latent high-level features contained in high-order interactions can be distilled by our model. We demonstrate the merits of our NRNM on two different tasks: action recognition and sentiment analysis.

📄 PDF Abstract BibTeX arXiv:1908.09535

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionSentiment Analysis

Similar Papers 제목 키워드 기반

Learning Sequence Representations by Non-local Recurrent Neural Memory

2022-07-20 · Wenjie Pei, Xin Feng, Canmiao Fu, Qiong Cao 외

The key challenge of sequence representation learning is to capture the long-range temporal dependencies. Typical methods for supervised sequence representation learning are built upon recurrent neural networks to captur…

Representation Learning

Recurrent Memory Transformer

2022-07-14 · Aydar Bulatov, Yuri Kuratov, Mikhail S. Burtsev

Transformer-based models show their effectiveness across multiple domains and tasks. The self-attention allows to combine information from all sequence elements into context-aware representations. However, global and loc…

Language ModelingLanguage Modelling

mGRADE: Minimal Recurrent Gating Meets Delay Convolutions for Lightweight Sequence Modeling

2025-07-02 · Tristan Torchet, Christian Metzner, Karthik Charan Raghunathan, Jimmy Weber 외 arxiv

Multi-timescale sequence modeling relies on capturing both local fast dynamics and global slow context; yet, maintaining these capabilities under the strict memory constraints common to edge devices remains an open chall…

Audio Classification

Pretraining Recurrent Networks without Recurrence

2026-06-04 · Akarsh Kumar, Phillip Isola arxiv

Training recurrent neural networks (RNNs) requires assigning credit across long sequences of computations. Standard backpropagation through time (BPTT) addresses this problem poorly: it is sequential in time, limiting pa…

SinkRec: Mitigating Semantic State Sink in Long Sequence Recommendation with Memory-Conditioned Gated Delta Networks

2026-06-03 · Zhuang Zhuang, Zhipeng Wei, Ji Dai, Jie Chen 외 arxiv

Linear attention provides an efficient backbone for long-sequence recommendation by avoiding the quadratic cost of standard Transformers, but its compressed recurrent state can be dominated by repetitive behavior pattern…