Papers › Learning spatio-temporal representations with temporal squeeze pooling

Learning spatio-temporal representations with temporal squeeze pooling

11 Feb 2020arXiv:2002.04685archive 2025-07-28

Guoxi Huang, Adrian G. Bors

In this paper, we propose a new video representation learning method, named Temporal Squeeze (TS) pooling, which can extract the essential movement information from a long sequence of video frames and map it into a set of few images, named Squeezed Images. By embedding the Temporal Squeeze pooling as a layer into off-the-shelf Convolution Neural Networks (CNN), we design a new video classification model, named Temporal Squeeze Network (TeSNet). The resulting Squeezed Images contain the essential movement information from the video frames, corresponding to the optimization of the video classification task. We evaluate our architecture on two video classification benchmarks, and the results achieved are compared to the state-of-the-art.

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 RecognitionClassificationGeneral ClassificationRepresentation LearningVideo Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition HMDB-51 TesNet (ImageNet pretrained) Average accuracy of 3 splits 71.5 #51 of 77 Archive leaderboard report
Action Recognition UCF101 TesNet (ImageNet pretrained) 3-fold Accuracy 95.2 #46 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

Convolution

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