Action Triplet Recognition

8 papers with code • 6 benchmarks • 4 datasets

Recognising action as a triplet of subject verb and object. Example HOI = Human Object Interaction, Surgical IVT = Instrument Verb Target, etc.


Use these libraries to find Action Triplet Recognition models and implementations

Most implemented papers

Benchmarking Deep Reinforcement Learning for Continuous Control

rllab/rllab 22 Apr 2016

Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning.

Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos

camma-public/tripnet 7 Sep 2021

To achieve this task, we introduce our new model, the Rendezvous (RDV), which recognizes triplets directly from surgical videos by leveraging attention at two different levels.

Data Splits and Metrics for Method Benchmarking on Surgical Action Triplet Datasets

CAMMA-public/cholect45 11 Apr 2022

We also develop a metrics library, ivtmetrics, for model evaluation on surgical triplets.

CholecTriplet2021: A benchmark challenge for surgical action triplet recognition

CAMMA-public/cholectriplet2021 10 Apr 2022

In this paper, we present the challenge setup and assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge.

Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets

camma-public/tripnet 10 Jul 2020

Recognition of surgical activity is an essential component to develop context-aware decision support for the operating room.

CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection

CAMMA-public/cholect50 13 Feb 2023

This paper presents the CholecTriplet2022 challenge, which extends surgical action triplet modeling from recognition to detection.

Dissecting Self-Supervised Learning Methods for Surgical Computer Vision

camma-public/selfsupsurg 1 Jul 2022

Correct transfer of these methods to surgery, as described and conducted in this work, leads to substantial performance gains over generic uses of SSL - up to 7. 4% on phase recognition and 20% on tool presence detection - as well as state-of-the-art semi-supervised phase recognition approaches by up to 14%.

Rendezvous in Time: An Attention-based Temporal Fusion approach for Surgical Triplet Recognition

camma-public/rendezvous-in-time 30 Nov 2022

Focusing more on the verbs, our RiT explores the connectedness of current and past frames to learn temporal attention-based features for enhanced triplet recognition.