S3Aug: Segmentation, Sampling, and Shift for Action Recognition
Action recognition is a well-established area of research in computer vision. In this paper, we propose S3Aug, a video data augmenatation for action recognition. Unlike conventional video data augmentation methods that involve cutting and pasting regions from two videos, the proposed method generates new videos from a single training video through segmentation and label-to-image transformation. Furthermore, the proposed method modifies certain categories of label images by sampling to generate a variety of videos, and shifts intermediate features to enhance the temporal coherency between frames of the generate videos. Experimental results on the UCF101, HMDB51, and Mimetics datasets demonstrate the effectiveness of the proposed method, paricularlly for out-of-context videos of the Mimetics dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Action RecognitionData AugmentationSimilar Papers 제목 키워드 기반
Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos
Skeleton Action Recognition (SAR) involves identifying human actions using skeletal joint coordinates and their interconnections. While plain Transformers have been attempted for this task, they still fall short compared…
Action RecognitionAction Recognition In VideosMambaLearnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks
We propose learnable polyphase sampling (LPS), a pair of learnable down/upsampling layers that enable truly shift-invariant and equivariant convolutional networks. LPS can be trained end-to-end from data and generalizes …
image-classificationImage ClassificationSegmentationSemantic SegmentationUnderstanding Spatio-Temporal Relations in Human-Object Interaction using Pyramid Graph Convolutional Network
Human activities recognition is an important task for an intelligent robot, especially in the field of human-robot collaboration, it requires not only the label of sub-activities but also the temporal structure of the ac…
Action RecognitionAction SegmentationHuman-Object Interaction DetectionO-TALC: Steps Towards Combating Oversegmentation within Online Action Segmentation
Online temporal action segmentation shows a strong potential to facilitate many HRI tasks where extended human action sequences must be tracked and understood in real time. Traditional action segmentation approaches, how…
Action RecognitionAction SegmentationSegmentationSpatio-temporal Action Recognition+1Investigating Shift Equivalence of Convolutional Neural Networks in Industrial Defect Segmentation
In industrial defect segmentation tasks, while pixel accuracy and Intersection over Union (IoU) are commonly employed metrics to assess segmentation performance, the output consistency (also referred to equivalence) of t…
Data AugmentationSegmentation