Papers › Busy-Quiet Video Disentangling for Video Classification

Busy-Quiet Video Disentangling for Video Classification

29 Mar 2021arXiv:2103.15584archive 2025-07-28

Guoxi Huang, Adrian G. Bors

In video data, busy motion details from moving regions are conveyed within a specific frequency bandwidth in the frequency domain. Meanwhile, the rest of the frequencies of video data are encoded with quiet information with substantial redundancy, which causes low processing efficiency in existing video models that take as input raw RGB frames. In this paper, we consider allocating intenser computation for the processing of the important busy information and less computation for that of the quiet information. We design a trainable Motion Band-Pass Module (MBPM) for separating busy information from quiet information in raw video data. By embedding the MBPM into a two-pathway CNN architecture, we define a Busy-Quiet Net (BQN). The efficiency of BQN is determined by avoiding redundancy in the feature space processed by the two pathways: one operating on Quiet features of low-resolution, while the other processes Busy features. The proposed BQN outperforms many recent video processing models on Something-Something V1, Kinetics400, UCF101 and HMDB51 datasets.

PaperPDFConference PDFCode

Code

guoxih/busy-quiet-net mentioned in papermentioned 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 ClassificationAction RecognitionAction Recognition In VideosClassificationGeneral ClassificationVideo Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 BQN (ResNet-50) Acc@1 77.3 #143 of 207 Archive leaderboard report
Action Classification Kinetics-400 BQN (ResNet-50) Acc@5 93.2 #143 of 207 Archive leaderboard report
Action Recognition HMDB-51 BQN Average accuracy of 3 splits 77.6 #31 of 77 Archive leaderboard report
Action Recognition Something-Something V1 BQNEn (ImageNet + K400 pretrained) Top 1 Accuracy 57.1 #17 of 74 Archive leaderboard report
Action Recognition Something-Something V1 BQNEn (ImageNet + K400 pretrained) Top 5 Accuracy 84.2 #17 of 74 Archive leaderboard report
Action Recognition UCF101 BQN 3-fold Accuracy 97.6 #18 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.

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