FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2960198392> ?p ?o ?g. }

• W2960198392 abstract "Surgical tool presence detection and surgical phase recognition are two fundamental yet challenging tasks in surgical video analysis and also very essential components in various applications in modern operating rooms. While these two analysis tasks are highly correlated in clinical practice as the surgical process is well-defined, most previous methods tackled them separately, without making full use of their relatedness. In this paper, we present a novel method by developing a multi-task recurrent convolutional network with correlation loss (MTRCNet-CL) to exploit their relatedness to simultaneously boost the performance of both tasks. Specifically, our proposed MTRCNet-CL model has an end-to-end architecture with two branches, which share earlier feature encoders to extract general visual features while holding respective higher layers targeting for specific tasks. Given that temporal information is crucial for phase recognition, long-short term memory (LSTM) is explored to model the sequential dependencies in the phase recognition branch. More importantly, a novel and effective correlation loss is designed to model the relatedness between tool presence and phase identification of each video frame, by minimizing the divergence of predictions from the two branches. Mutually leveraging both low-level feature sharing and high-level prediction correlating, our MTRCNet-CL method can encourage the interactions between the two tasks to a large extent, and hence can bring about benefits to each other. Extensive experiments on a large surgical video dataset (Cholec80) demonstrate outstanding performance of our proposed method, consistently exceeding the state-of-the-art methods by a large margin (e.g., 89.1% v.s. 81.0% for the mAP in tool presence detection and 87.4% v.s. 84.5% for F1 score in phase recognition). The code can be found on our project website." @default.
• W2960198392 created "2019-07-23" @default.
• W2960198392 creator A5013847639 @default.
• W2960198392 creator A5022499603 @default.
• W2960198392 creator A5022856212 @default.
• W2960198392 creator A5031202827 @default.
• W2960198392 creator A5032708386 @default.
• W2960198392 creator A5050163233 @default.
• W2960198392 creator A5090516040 @default.
• W2960198392 date "2019-07-13" @default.
• W2960198392 modified "2023-09-24" @default.
• W2960198392 title "Multi-Task Recurrent Convolutional Network with Correlation Loss for Surgical Video Analysis" @default.
• W2960198392 cites W101951079 @default.
• W2960198392 cites W1507561440 @default.
• W2960198392 cites W1572533718 @default.
• W2960198392 cites W1803870300 @default.
• W2960198392 cites W1947481528 @default.
• W2960198392 cites W1989228528 @default.
• W2960198392 cites W1989912492 @default.
• W2960198392 cites W1998162403 @default.
• W2960198392 cites W2016545368 @default.
• W2960198392 cites W2018421200 @default.
• W2960198392 cites W2025241052 @default.
• W2960198392 cites W2041742273 @default.
• W2960198392 cites W2054866636 @default.
• W2960198392 cites W2107466310 @default.
• W2960198392 cites W2166302203 @default.
• W2960198392 cites W2179331991 @default.
• W2960198392 cites W2194775991 @default.
• W2960198392 cites W2266464013 @default.
• W2960198392 cites W2308279915 @default.
• W2960198392 cites W2322020277 @default.
• W2960198392 cites W2419249022 @default.
• W2960198392 cites W2519007024 @default.
• W2960198392 cites W2534834437 @default.
• W2960198392 cites W2568518337 @default.
• W2960198392 cites W2585890928 @default.
• W2960198392 cites W2599689342 @default.
• W2960198392 cites W2604690505 @default.
• W2960198392 cites W2621477274 @default.
• W2960198392 cites W2689531869 @default.
• W2960198392 cites W2747257024 @default.
• W2960198392 cites W2755397839 @default.
• W2960198392 cites W2755513326 @default.
• W2960198392 cites W2777273430 @default.
• W2960198392 cites W2779943048 @default.
• W2960198392 cites W2781390193 @default.
• W2960198392 cites W2788528628 @default.
• W2960198392 cites W2795040403 @default.
• W2960198392 cites W2804845319 @default.
• W2960198392 cites W2884036902 @default.
• W2960198392 cites W2927739223 @default.
• W2960198392 cites W2963240734 @default.
• W2960198392 cites W2963500702 @default.
• W2960198392 cites W2964066956 @default.
• W2960198392 cites W3098609708 @default.
• W2960198392 cites W3098904667 @default.
• W2960198392 cites W2599653512 @default.
• W2960198392 doi "https://doi.org/10.48550/arxiv.1907.06099" @default.
• W2960198392 hasPublicationYear "2019" @default.
• W2960198392 type Work @default.
• W2960198392 sameAs 2960198392 @default.
• W2960198392 citedByCount "0" @default.
• W2960198392 crossrefType "posted-content" @default.
• W2960198392 hasAuthorship W2960198392A5013847639 @default.
• W2960198392 hasAuthorship W2960198392A5022499603 @default.
• W2960198392 hasAuthorship W2960198392A5022856212 @default.
• W2960198392 hasAuthorship W2960198392A5031202827 @default.
• W2960198392 hasAuthorship W2960198392A5032708386 @default.
• W2960198392 hasAuthorship W2960198392A5050163233 @default.
• W2960198392 hasAuthorship W2960198392A5090516040 @default.
• W2960198392 hasBestOaLocation W29601983921 @default.
• W2960198392 hasConcept C111919701 @default.
• W2960198392 hasConcept C117220453 @default.
• W2960198392 hasConcept C118505674 @default.
• W2960198392 hasConcept C119857082 @default.
• W2960198392 hasConcept C126042441 @default.
• W2960198392 hasConcept C138885662 @default.
• W2960198392 hasConcept C153180895 @default.
• W2960198392 hasConcept C154945302 @default.
• W2960198392 hasConcept C162324750 @default.
• W2960198392 hasConcept C165696696 @default.
• W2960198392 hasConcept C187736073 @default.
• W2960198392 hasConcept C2524010 @default.
• W2960198392 hasConcept C2776401178 @default.
• W2960198392 hasConcept C2780451532 @default.
• W2960198392 hasConcept C33923547 @default.
• W2960198392 hasConcept C38652104 @default.
• W2960198392 hasConcept C41008148 @default.
• W2960198392 hasConcept C41895202 @default.
• W2960198392 hasConcept C76155785 @default.
• W2960198392 hasConcept C774472 @default.
• W2960198392 hasConcept C81363708 @default.
• W2960198392 hasConcept C98045186 @default.
• W2960198392 hasConceptScore W2960198392C111919701 @default.
• W2960198392 hasConceptScore W2960198392C117220453 @default.
• W2960198392 hasConceptScore W2960198392C118505674 @default.
• W2960198392 hasConceptScore W2960198392C119857082 @default.
• W2960198392 hasConceptScore W2960198392C126042441 @default.
• W2960198392 hasConceptScore W2960198392C138885662 @default.

• next