No article text was recorded for this version.
factorized 3D convolution
Version 1 of 1287 papers401 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Skeleton Aware Multi-modal Sign Language Recognition
- Blog: An Efficient 3D Convolutional Neural Network with Channel-wise, Spatial-grouped, and Temporal Convolutions
- Blog: Fast Spatio-Temporal Residual Network for Video Super-Resolution.
- Blog: RGB-D Based Action Recognition with Light-weight 3D Convolutional Networks
- Blog: Spatiotemporal Joint Filter Decomposition in 3D Convolutional Neural Networks
- Blog: Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
- Blog: Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification
- Blog: MVFNet: Multi-View Fusion Network for Efficient Video Recognition
- Blog: S3TC: Spiking Separated Spatial and Temporal Convolutions with Unsupervised STDP-based Learning for Action Recognition
- Blog: Parallel Separable 3D Convolution for Video and Volumetric Data Understanding
- Blog: Fast Spatio-Temporal Residual Network for Video Super-Resolution
- Blog: Light-Weight Hybrid Convolutional Network for Liver Tumor Segmentation
- Blog: An Efficient 3D CNN for Action/Object Segmentation in Video
- Blog: A Closer Look at Spatiotemporal Convolutions for Action Recognition
- Blog: Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification
- Blog: A Closer Look at Spatiotemporal Convolutions for Action Recognition
- Blog: Spatiotemporal Dilated Convolution with Uncertain Matching for Video-based Crowd Estimation
- Blog: Accelerating cardiac cine MRI beyond compressed sensing using DL-ESPIRiT
- Blog: Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation
- Blog: Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks
- Blog: Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks
- Blog: Temporal Feature Networks for CNN based Object Detection
- Blog: CINENet: deep learning-based 3D cardiac CINE MRI reconstruction with multi-coil complex-valued 4D spatio-temporal convolutions
- Blog: STH: Spatio-Temporal Hybrid Convolution for Efficient Action Recognition
- Blog: STEAD: Spatio-Temporal Efficient Anomaly Detection for Time and Compute Sensitive Applications
- Blog: Fusion of EEG feature extraction and CNN-MSTA transformer emotion recognition classification model
- Blog: Video Probabilistic Diffusion Models in Projected Latent Space
- Blog: MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps
- Blog: Neurodata Lab's approach to the Challenge on Computer Vision for Physiological Measurement
- Blog: ACTION-Net: Multipath Excitation for Action Recognition
- Blog: Explainable 3D Convolutional Neural Networks by Learning Temporal Transformations
- Blog: Resource Efficient 3D Convolutional Neural Networks
- Blog: Scene-aware Learning Network for Radar Object Detection
- Blog: H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Models
- Blog: RainUNet for Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts
- Blog: Spatiotemporal Contrastive Learning of Facial Expressions in Videos
- Blog: A Light Weight Model for Active Speaker Detection
- Blog: MVFNet: Multi-View Fusion Network for Efficient Video Recognition
- Blog: A Light Weight Model for Active Speaker Detection
- Blog: Fast Spatio-Temporal Residual Network for Video Super-Resolution
- Blog: Temporal Factorization of 3D Convolutional Kernels
- Blog: Automatic Evaluation Method for Functional Movement Screening Based on Multi-Scale Lightweight 3D Convolution and an Encoder–Decoder
- Blog: Decoupled Appearance and Motion Learning for Efficient Anomaly Detection in Surveillance Video
- Blog: Rethinking Spatiotemporal Feature Learning For Video Understanding
- Blog: Recent Progress in Appearance-based Action Recognition
- Blog: SS4D: Native 4D Generative Model via Structured Spacetime Latents
- Blog: Video Diffusion Models: A Survey
- Blog: TRecViT: A Recurrent Video Transformer
- Blog: Spatiotemporal Contrastive Learning of Facial Expressions in Videos
- Blog: Gesture and Sign Language Recognition with Temporal Residual Networks
- Blog: Two-Streams: Dark and Light Networks with Graph Convolution for Action Recognition from Dark Videos (Student Abstract)
- Blog: An Overview of Behavioral Recognition
- Blog: DUN-SRE: Deep Unrolling Network with Spatiotemporal Rotation Equivariance for Dynamic MRI Reconstruction
- Blog: Temporal Feature Networks for CNN based Object Detection
- Blog: Video Classification with Channel-Separated Convolutional Networks
- Blog: Mutually Reinforced Spatio-Temporal Convolutional Tube for Human Action Recognition
- Blog: TransNet: A Transfer Learning-Based Network for Human Action Recognition
- Blog: High Performance Gesture Recognition via Effective and Efficient Temporal Modeling
- Blog: Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling
- Blog: Improved 3D-ResNet sign language recognition algorithm with enhanced hand features
Showing 60 of 287 papers.
History & citation
Current · Permanent link
- Spatiotemporal Factorization for Efficient Video Networks merged into this direction (78% overlap)
- Efficient Spatiotemporal Learning via Convolutional Factorization merged into this direction (88% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_factorized_3d_convolution_97a62cf0,
title = {factorized 3D convolution},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/factorized-3d-convolution/rdr_97a62cf0abd94cf58e36e532e813640a},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_factorized_3d_convolution_97a62cf0_v1,
title = {factorized 3D convolution},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/factorized-3d-convolution/rdr_97a62cf0abd94cf58e36e532e813640a/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}