Papers › Bubblenet: A Disperse Recurrent Structure To Recognize Activities

Bubblenet: A Disperse Recurrent Structure To Recognize Activities

30 Oct 2020archive 2025-07-28

Igor L. O. Bastos, Victor H. C. Melo, William R. Schwartz

This paper presents an approach to perform human activity recognition in videos through the employment of a deep recurrent network, taking as inputs appearance and optical flow information. Our method proposes a novel architecture named BubbleNET, which is based on a recurrent layer dispersed into several modules (referred to as bubbles) along with an attention mechanism based on squeeze-and-excitation strategy, responsible to modulate each bubble contribution. Thereby, we intend to gather information from fundamentally correlated segments of the input data, creating a signature of components that characterize each activity. Our experiments, conducted on widely employed activity recognition datasets, support the existence of these signatures, evidenced by maps of bubble activations for every class of the datasets. To compare the approach to literature methods, mean accuracy is taken into account, for which BubbleNET obtained 97.62%, 91.70% and 82.60% on UCF-101, YUP++ and HMDB-51 datasets, respectively, being placed among state-of-the-art methods.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Action RecognitionActivity RecognitionActivity Recognition In VideosHuman Activity RecognitionOptical Flow Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition HMDB-51 BubbleNET Average accuracy of 3 splits 82.60 #14 of 77 Archive leaderboard report
Action Recognition UCF101 BubbleNET 3-fold Accuracy 97.62 #16 of 91 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.

Methods

Average PoolingConvolutionDense ConnectionsReLUSigmoid ActivationSqueeze-and-Excitation Block

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