Win-Fail Action Recognition

15 Feb 2021  ·  Paritosh Parmar, Brendan Morris ·

Current video/action understanding systems have demonstrated impressive performance on large recognition tasks. However, they might be limiting themselves to learning to recognize spatiotemporal patterns, rather than attempting to thoroughly understand the actions. To spur progress in the direction of a truer, deeper understanding of videos, we introduce the task of win-fail action recognition -- differentiating between successful and failed attempts at various activities. We introduce a first of its kind paired win-fail action understanding dataset with samples from the following domains: "General Stunts," "Internet Wins-Fails," "Trick Shots," and "Party Games." Unlike existing action recognition datasets, intra-class variation is high making the task challenging, yet feasible. We systematically analyze the characteristics of the win-fail task/dataset with prototypical action recognition networks and a novel video retrieval task. While current action recognition methods work well on our task/dataset, they still leave a large gap to achieve high performance. We hope to motivate more work towards the true understanding of actions/videos. Dataset will be available from https://github.com/ParitoshParmar/Win-Fail-Action-Recognition.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Action Recognition Win-Fail Action Understanding 2DCNN+TRN 2-Class Accuracy 75.74% # 1
Action Understanding Win-Fail Action Understanding 2DCNN+TRN 2-Class Accuracy 75.74 % # 1

Methods


No methods listed for this paper. Add relevant methods here