SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.07736 · 2020

HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
JonathonLuiten/TrackEval pwc_unofficial 4 of 10
FunctionStatusWhere it lives
create_coco_mask Ran JonathonLuiten/TrackEval/trackeval/baselines/baseline_utils.py
code served (permissive licence) · get_code("e4a9dbe96206f1e6")
init_config Ran JonathonLuiten/TrackEval/trackeval/utils.py
code served (permissive licence) · get_code("0ce058e665602da2")
threshold Ran JonathonLuiten/TrackEval/trackeval/baselines/baseline_utils.py
code served (permissive licence) · get_code("407ecabd804b59d8")
update_config Ran JonathonLuiten/TrackEval/trackeval/utils.py
code served (permissive licence) · get_code("5ef3f617efb9ddc4")
geometric_mean Not yet run JonathonLuiten/TrackEval/trackeval/plotting.py
code served (permissive licence) · get_code("06d2be4ac9d0e95b")
jaccard Not yet run JonathonLuiten/TrackEval/trackeval/plotting.py
code served (permissive licence) · get_code("00c662d6d9709fe4")
load_multiple_tracker_summaries Not yet run JonathonLuiten/TrackEval/trackeval/plotting.py
code served (permissive licence) · get_code("e9f7b2829ca9731b")
load_seq Not yet run JonathonLuiten/TrackEval/trackeval/baselines/baseline_utils.py
code served (permissive licence) · get_code("3aceddbf375bf009")
time Not yet run JonathonLuiten/TrackEval/trackeval/_timing.py
code served (permissive licence) · get_code("df1bd31f4da1bed6")
validate_metrics_list Not yet run JonathonLuiten/TrackEval/trackeval/utils.py
code served (permissive licence) · get_code("9792bf1150d36891")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Multi-Object Tracking (MOT) has been notoriously difficult to evaluate. Previous metrics overemphasize the importance of either detection or association. To address this, we present a novel MOT evaluation metric, HOTA (Higher Order Tracking Accuracy), which explicitly balances the effect of performing accurate detection, association and localization into a single unified metric for comparing trackers. HOTA decomposes into a family of sub-metrics which are able to evaluate each of five basic error types separately, which enables clear analysis of tracking performance. We evaluate the effectiveness of HOTA on the MOTChallenge benchmark, and show that it is able to capture important aspects of MOT performance not previously taken into account by established metrics. Furthermore, we show HOTA scores better align with human visual evaluation of tracking performance.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2009.07736")
get_code_for_paper("2009.07736")
have("2009.07736")

Connect an agent — have() is free.