Video Recognition
55 papers with code • 0 benchmarks • 4 datasets
Benchmarks
MIDV-2019
BosphorusSign22k
Greatest papers with code
MoViNets: Mobile Video Networks for Efficient Video Recognition
tensorflow/models
•
•
CVPR 2021
We present Mobile Video Networks (MoViNets), a family of computation and memory efficient video networks that can operate on streaming video for online inference.
Ranked #1 on
Action Recognition
on EPIC-KITCHENS-100
Multiscale Vision Transformers
We evaluate this fundamental architectural prior for modeling the dense nature of visual signals for a variety of video recognition tasks where it outperforms concurrent vision transformers that rely on large scale external pre-training and are 5-10x more costly in computation and parameters.
Ranked #2 on
Action Recognition
on AVA v2.2
X3D: Expanding Architectures for Efficient Video Recognition
facebookresearch/SlowFast
•
•
CVPR 2020
This paper presents X3D, a family of efficient video networks that progressively expand a tiny 2D image classification architecture along multiple network axes, in space, time, width and depth.
Ranked #24 on
Action Classification
on Kinetics-400
Audiovisual SlowFast Networks for Video Recognition
We present Audiovisual SlowFast Networks, an architecture for integrated audiovisual perception.
SlowFast Networks for Video Recognition
facebookresearch/SlowFast
•
•
ICCV 2019
We present SlowFast networks for video recognition.
Ranked #1 on
Action Recognition
on AVA v2.1
Micro-Batch Training with Batch-Channel Normalization and Weight Standardization
lab-ml/nn
•
•
Batch Normalization (BN) has become an out-of-box technique to improve deep network training.
Ranked #35 on
Instance Segmentation
on COCO minival
Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?
kenshohara/3D-ResNets-PyTorch
•
•
Therefore, in the present paper, we conduct exploration study in order to improve spatiotemporal 3D CNNs as follows: (i) Recently proposed large-scale video datasets help improve spatiotemporal 3D CNNs in terms of video classification accuracy.
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
Similarly, the output feature maps of a convolution layer can also be seen as a mixture of information at different frequencies.
Ranked #69 on
Action Classification
on Kinetics-400
Omni-sourced Webly-supervised Learning for Video Recognition
open-mmlab/mmaction
•
•
ECCV 2020
Then a joint-training strategy is proposed to deal with the domain gaps between multiple data sources and formats in webly-supervised learning.
Ranked #2 on
Action Recognition
on UCF101
(using extra training data)
Sequence Level Semantics Aggregation for Video Object Detection
open-mmlab/mmtracking
•
•
ICCV 2019
In this work, we argue that aggregating features in the full-sequence level will lead to more discriminative and robust features for video object detection.
Ranked #3 on
Video Object Detection
on ImageNet VID
