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

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

11 Apr 2022arXiv:2204.05235archive 2025-07-28

Chinedu Innocent Nwoye, Nicolas Padoy

In addition to generating data and annotations, devising sensible data splitting strategies and evaluation metrics is essential for the creation of a benchmark dataset. This practice ensures consensus on the usage of the data, homogeneous assessment, and uniform comparison of research methods on the dataset. This study focuses on CholecT50, which is a 50 video surgical dataset that formalizes surgical activities as triplets of <instrument, verb, target>. In this paper, we introduce the standard splits for the CholecT50 and CholecT45 datasets and show how they compare with existing use of the dataset. CholecT45 is the first public release of 45 videos of CholecT50 dataset. We also develop a metrics library, ivtmetrics, for model evaluation on surgical triplets. Furthermore, we conduct a benchmark study by reproducing baseline methods in the most predominantly used deep learning frameworks (PyTorch and TensorFlow) to evaluate them using the proposed data splits and metrics and release them publicly to support future research. The proposed data splits and evaluation metrics will enable global tracking of research progress on the dataset and facilitate optimal model selection for further deployment.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

camma-public/attention-tripnet officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
camma-public/tripnet officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
camma-public/ivtmetrics officialmentioned in paperBSD-2-Clause report
CAMMA-public/cholect45 officialmentioned on GitHubpytorchNOASSERTION report
camma-public/rendezvous mentioned in papermentioned on GitHubpytorchNOASSERTION report
CAMMA-public/cholect50 mentioned on GitHubpytorchNOASSERTION report
camma-public/mcit-ig mentioned on GitHubpytorchNOASSERTION report
camma-public/rendezvous-in-time mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action Triplet RecognitionBenchmarkingModel Selection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Triplet Recognition CholecT45 Rendezvous mAP 29.4±2.8 #1 of 3 Archive leaderboard report
Action Triplet Recognition CholecT45 Attention Tripnet mAP 27.2±2.7 #2 of 3 Archive leaderboard report
Action Triplet Recognition CholecT45 Tripnet mAP 24.4±4.7 #3 of 3 Archive leaderboard report
Action Triplet Recognition CholecT45 (cross-val) Rendezvous mAP 29.4±2.8 #3 of 5 Archive leaderboard report
Action Triplet Recognition CholecT45 (cross-val) Attention Tripnet mAP 27.2±2.7 #4 of 5 Archive leaderboard report
Action Triplet Recognition CholecT45 (cross-val) Tripnet mAP 24.4±4.7 #5 of 5 Archive leaderboard report
Action Triplet Recognition CholecT50 Rendezvous (PyTorch) Mean AP 29.5 #2 of 6 Archive leaderboard report
Action Triplet Recognition CholecT50 Attention Tripnet (PyTorch) Mean AP 23.3 #4 of 6 Archive leaderboard report
Action Triplet Recognition CholecT50 Tripnet (PyTorch) Mean AP 21.6 #5 of 6 Archive leaderboard report
Action Triplet Recognition CholecT50 (Challenge) Rendezvous (PyTorch) mAP 32.8 #6 of 27 Archive leaderboard report
Action Triplet Recognition CholecT50 (Challenge) Attention Tripnet (PyTorch) mAP 27.7 #12 of 27 Archive leaderboard report
Action Triplet Recognition CholecT50 (Challenge) Tripnet (PyTorch) mAP 27.4 #13 of 27 Archive leaderboard report
Action Triplet Recognition CholecT50 (cross-val) Rendezvous mAP 29.4±2.5 #2 of 4 Archive leaderboard report
Action Triplet Recognition CholecT50 (cross-val) Attention Tripnet mAP 27.2±2.9 #3 of 4 Archive leaderboard report
Action Triplet Recognition CholecT50 (cross-val) Tripnet mAP 25.3±2.4 #4 of 4 Archive leaderboard report
Action Triplet Recognition CholecT50(cross-val) Rendezvous mAP 29.4±2.5 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections