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

Recognition of surgical activity is an essential component to develop context-aware decision support for the operating room. In this work, we tackle the recognition of fine-grained activities, modeled as action triplets <instrument, verb, target> representing the tool activity. To this end, we introduce a new laparoscopic dataset, CholecT40, consisting of 40 videos from the public dataset Cholec80 in which all frames have been annotated using 128 triplet classes. Furthermore, we present an approach to recognize these triplets directly from the video data. It relies on a module called Class Activation Guide (CAG), which uses the instrument activation maps to guide the verb and target recognition. To model the recognition of multiple triplets in the same frame, we also propose a trainable 3D Interaction Space, which captures the associations between the triplet components. Finally, we demonstrate the significance of these contributions via several ablation studies and comparisons to baselines on CholecT40.

PDF Abstract

Datasets


Introduced in the Paper:

CholecT40

Used in the Paper:

HICO-DET Cholec80 CholecT50 CholecT45
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Action Triplet Recognition CholecT40 Tripnet mAP 18.95 # 1
Action Triplet Recognition CholecT50 Tripnet (TensorFlow v1) Mean AP 20.0 # 6
Action Triplet Recognition CholecT50 (Challenge) Tripnet (TensorFlow v1) mAP 23.4 # 18

Methods