Video Classification
132 papers with code • 8 benchmarks • 12 datasets
Video Classification is the task of producing a label that is relevant to the video given its frames. A good video level classifier is one that not only provides accurate frame labels, but also best describes the entire video given the features and the annotations of the various frames in the video. For example, a video might contain a tree in some frame, but the label that is central to the video might be something else (e.g., “hiking”). The granularity of the labels that are needed to describe the frames and the video depends on the task. Typical tasks include assigning one or more global labels to the video, and assigning one or more labels for each frame inside the video.
Benchmarks
These leaderboards are used to track progress in Video Classification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Video Classification models and implementationsDatasets
Kinetics
Charades
Something-Something V2
YouTube-8M
Something-Something V1
Charades-Ego
Home Action Genome
Multimodal PISA
MetaVD
Most implemented papers
Non-local Neural Networks
facebookresearch/video-nonlocal-net
•
•
CVPR 2018
Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time.
Group Normalization
ppwwyyxx/GroupNorm-reproduce
•
•
ECCV 2018
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
Is Space-Time Attention All You Need for Video Understanding?
facebookresearch/TimeSformer
•
•
We present a convolution-free approach to video classification built exclusively on self-attention over space and time.
Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks
One of the challenges in modeling cognitive events from electroencephalogram (EEG) data is finding representations that are invariant to inter- and intra-subject differences, as well as to inherent noise associated with such data.
Video Swin Transformer
SwinTransformer/Video-Swin-Transformer
•
•
CVPR 2022
The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks.
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.
Temporal Segment Networks for Action Recognition in Videos
yjxiong/temporal-segment-networks
•
•
Furthermore, based on the temporal segment networks, we won the video classification track at the ActivityNet challenge 2016 among 24 teams, which demonstrates the effectiveness of TSN and the proposed good practices.
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.
Two-Stream Convolutional Networks for Action Recognition in Videos
Our architecture is trained and evaluated on the standard video actions benchmarks of UCF-101 and HMDB-51, where it is competitive with the state of the art.
YouTube-8M: A Large-Scale Video Classification Benchmark
Despite the size of the dataset, some of our models train to convergence in less than a day on a single machine using TensorFlow.
