2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information
Login Paper Search My Schedule Paper Index Help

My ICASSP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDIVMSP-33.2
Paper Title MULTI-DIRECTIONAL CONVOLUTION NETWORKS WITH SPATIAL-TEMPORAL FEATURE PYRAMID MODULE FOR ACTION RECOGNITION
Authors Bohong Yang, Zijian Wang, Wu Ran, Hong Lu, Fudan University, China; Yi-Ping Phoebe Chen, La Trobe University, China
SessionIVMSP-33: Action Recognition
LocationGather.Town
Session Time:Friday, 11 June, 14:00 - 14:45
Presentation Time:Friday, 11 June, 14:00 - 14:45
Presentation Poster
Topic Image, Video, and Multidimensional Signal Processing: [IVSMR] Image & Video Sensing, Modeling, and Representation
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Recent attempts show that factorizing 3D convolutional filters into separate spatial and temporal components brings impressive improvement in action recognition. However, traditional temporal convolution operating along the temporal dimension will aggregate unrelated features, since the feature maps of fast-moving objects have shifted spatial positions. In this paper, we propose a novel and effective Multi-Directional Convolution (MDConv), which extracts features along different spatial-temporal orientations. Especially, MDConv has the same FLOPs and parameters as the traditional 1D temporal convolution. Also, we propose the Spatial-Temporal Features Pyramid Module (STFPM) to fuse spatial semantics in different scales in a light-weight way. Our extensive experiments show that the models which integrate with MDConv achieve better accuracy on several large-scale action recognition benchmarks such as Kinetics, AVA and SomethingSomething V1&V2 datasets.