paper-with-me

홈 › Papers

Spatio-Temporal FAST 3D Convolutions for Human Action Recognition

2019-09-30 · Alexandros Stergiou, Ronald Poppe

Effective processing of video input is essential for the recognition of temporally varying events such as human actions. Motivated by the often distinctive temporal characteristics of actions in either horizontal or vertical direction, we introduce a novel convolution block for CNN architectures with video input. Our proposed Fractioned Adjacent Spatial and Temporal (FAST) 3D convolutions are a natural decomposition of a regular 3D convolution. Each convolution block consist of three sequential convolution operations: a 2D spatial convolution followed by spatio-temporal convolutions in the horizontal and vertical direction, respectively. Additionally, we introduce a FAST variant that treats horizontal and vertical motion in parallel. Experiments on benchmark action recognition datasets UCF-101 and HMDB-51 with ResNet architectures demonstrate consistent increased performance of FAST 3D convolution blocks over traditional 3D convolutions. The lower validation loss indicates better generalization, especially for deeper networks. We also evaluate the performance of CNN architectures with similar memory requirements, based either on Two-stream networks or with 3D convolution blocks. DenseNet-121 with FAST 3D convolutions was shown to perform best, giving further evidence of the merits of the decoupled spatio-temporal convolutions.

📄 PDF Abstract BibTeX arXiv:1909.13474

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionTemporal Action Localization

Methods 이 논문이 사용한 방법론

3D Convolution A 3D Convolution is a type of convolution where the kernel slides in 3 dimensions as opposed to 2 dimensions with 2D…
Average Pooling 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Similar Papers 제목 키워드 기반

Timeception for Complex Action Recognition

2018-12-04 · CVPR 2019 6 · Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders

This paper focuses on the temporal aspect for recognizing human activities in videos; an important visual cue that has long been undervalued. We revisit the conventional definition of activity and restrict it to Complex …

Action ClassificationAction RecognitionLong-video Activity RecognitionVideo Classification

Temporal Convolutional Networks for Action Segmentation and Detection

2016-11-16 · CVPR 2017 7 · Colin Lea, Michael D. Flynn, Rene Vidal, Austin Reiter 외

The ability to identify and temporally segment fine-grained human actions throughout a video is crucial for robotics, surveillance, education, and beyond. Typical approaches decouple this problem by first extracting loca…

Action SegmentationDecoderSkeleton Based Action Recognition

Fast Spatio-Temporal Residual Network for Video Super-Resolution

2019-04-05 · CVPR 2019 6 · Sheng Li, Fengxiang He, Bo Du, Lefei Zhang 외

Recently, deep learning based video super-resolution (SR) methods have achieved promising performance. To simultaneously exploit the spatial and temporal information of videos, employing 3-dimensional (3D) convolutions i…

Super-ResolutionVideo Super-Resolution

Fast Fourier Inception Networks for Occluded Video Prediction

2023-06-17 · Ping Li, Chenhan Zhang, Xianghua Xu

Video prediction is a pixel-level task that generates future frames by employing the historical frames. There often exist continuous complex motions, such as object overlapping and scene occlusion in video, which poses g…

PredictionVideo Prediction

TAN: Temporal Aggregation Network for Dense Multi-label Action Recognition

2018-12-14 · Xiyang Dai, Bharat Singh, Joe Yue-Hei Ng, Larry S. Davis

We present Temporal Aggregation Network (TAN) which decomposes 3D convolutions into spatial and temporal aggregation blocks. By stacking spatial and temporal convolutions repeatedly, TAN forms a deep hierarchical represe…

Action RecognitionTemporal Action Localization