paper-with-me

Papers

GLSFormer : Gated - Long, Short Sequence Transformer for Step Recognition in Surgical Videos

2023-07-20 · Nisarg A. Shah, Shameema Sikder, S. Swaroop Vedula, Vishal M. Patel

Automated surgical step recognition is an important task that can significantly improve patient safety and decision-making during surgeries. Existing state-of-the-art methods for surgical step recognition either rely on separate, multi-stage modeling of spatial and temporal information or operate on short-range temporal resolution when learned jointly. However, the benefits of joint modeling of spatio-temporal features and long-range information are not taken in account. In this paper, we propose a vision transformer-based approach to jointly learn spatio-temporal features directly from sequence of frame-level patches. Our method incorporates a gated-temporal attention mechanism that intelligently combines short-term and long-term spatio-temporal feature representations. We extensively evaluate our approach on two cataract surgery video datasets, namely Cataract-101 and D99, and demonstrate superior performance compared to various state-of-the-art methods. These results validate the suitability of our proposed approach for automated surgical step recognition. Our code is released at: https://github.com/nisargshah1999/GLSFormer

📄 PDF Abstract BibTeX arXiv:2307.11081

Code (1)

nisargshah1999/glsformer 공식 구현 pytorch

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Fusion Matters: Length-Aware Analysis of Positional-Encoding Fusion in Transformers

2026-01-09 · Mohamed Amine Hallam, Kuo-Kun Tseng arxiv

Transformers require positional encodings to represent sequence order, yet most prior work focuses on designing new positional encodings rather than examining how positional information is fused with token embeddings. In…

Text Classification

Classification Models for Partially Ordered Sequences

2021-01-31 · Stephanie Ger, Diego Klabjan, Jean Utke

Many models such as Long Short Term Memory (LSTMs), Gated Recurrent Units (GRUs) and transformers have been developed to classify time series data with the assumption that events in a sequence are ordered. On the other h…

ClassificationGeneral ClassificationTime SeriesTime Series Analysis

Hierarchically Gated Recurrent Neural Network for Sequence Modeling

2023-09-21 · NeurIPS 2023 11

Transformers have surpassed RNNs in popularity due to their superior abilities in parallel training and long-term dependency modeling. Recently, there has been a renewed interest in using linear RNNs for efficient sequen…

Transformer Quality in Linear Time

2022-02-21 · Weizhe Hua, Zihang Dai, Hanxiao Liu, Quoc V. Le

We revisit the design choices in Transformers, and propose methods to address their weaknesses in handling long sequences. First, we propose a simple layer named gated attention unit, which allows the use of a weaker sin…

8kLanguage ModelingLanguage ModellingMasked Language Modeling

Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling

2026-04-27 · Parsa Ashrafi Fashi, Utkarsh Saxena, Mehdi Rezagholizadeh, Aref Jafari 외 arxiv

Hybrid sequence models that combine efficient Transformer components with linear sequence modeling blocks are a promising alternative to pure Transformers, but most are still pretrained from scratch and therefore fail to…

Common Sense Reasoning