Papers › An Efficient 3D CNN for Action/Object Segmentation in Video

An Efficient 3D CNN for Action/Object Segmentation in Video

21 Jul 2019arXiv:1907.08895archive 2025-07-28

Rui Hou, Chen Chen, Rahul Sukthankar, Mubarak Shah

Convolutional Neural Network (CNN) based image segmentation has made great progress in recent years. However, video object segmentation remains a challenging task due to its high computational complexity. Most of the previous methods employ a two-stream CNN framework to handle spatial and motion features separately. In this paper, we propose an end-to-end encoder-decoder style 3D CNN to aggregate spatial and temporal information simultaneously for video object segmentation. To efficiently process video, we propose 3D separable convolution for the pyramid pooling module and decoder, which dramatically reduces the number of operations while maintaining the performance. Moreover, we also extend our framework to video action segmentation by adding an extra classifier to predict the action label for actors in videos. Extensive experiments on several video datasets demonstrate the superior performance of the proposed approach for action and object segmentation compared to the state-of-the-art.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

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 SegmentationDecoderImage SegmentationObjectSegmentationSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo Semantic SegmentationVisual Object Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation DAVIS 2016 Hou et al. F-measure (Decay) 4.9 #64 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 Hou et al. F-measure (Mean) 77.2 #64 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 Hou et al. F-measure (Recall) 84.7 #64 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 Hou et al. J&F 77.75 #64 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 Hou et al. Jaccard (Decay) 2.3 #64 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 Hou et al. Jaccard (Mean) 78.3 #64 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 Hou et al. Jaccard (Recall) 91.1 #64 of 78 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 PoolingBatch NormalizationConvolutionPyramid Pooling ModuleReLU

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