Action Classification
227 papers with code • 24 benchmarks • 30 datasets
Image source: The Kinetics Human Action Video Dataset
Benchmarks
These leaderboards are used to track progress in Action Classification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Action Classification models and implementationsDatasets
UCF101
Kinetics
HMDB51
ActivityNet
Kinetics 400
Charades
THUMOS14
Something-Something V2
YouCook2
Kinetics-600
Latest papers
Joint Skeletal and Semantic Embedding Loss for Micro-gesture Classification
In this paper, we briefly introduce the solution of our team HFUT-VUT for the Micros-gesture Classification in the MiGA challenge at IJCAI 2023.
What Can Simple Arithmetic Operations Do for Temporal Modeling?
whwu95/ATM
•
•
ICCV 2023
We conduct comprehensive ablation studies on the instantiation of ATMs and demonstrate that this module provides powerful temporal modeling capability at a low computational cost.
Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers
Both PAAT and PAAB surpass their respective backbone Transformers by up to 9. 8% in real-world action recognition and 21. 8% in multi-view robotic video alignment.
HomE: Homography-Equivariant Video Representation Learning
In this work, we propose a novel method for representation learning of multi-view videos, where we explicitly model the representation space to maintain Homography Equivariance (HomE).
Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
Modern hierarchical vision transformers have added several vision-specific components in the pursuit of supervised classification performance.
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
In this work, we explore a scalable way for building a general representation model toward unlimited modalities.
Implicit Temporal Modeling with Learnable Alignment for Video Recognition
francis-rings/ila
•
•
ICCV 2023
While modeling temporal information within straight through tube is widely adopted in literature, we find that simple frame alignment already provides enough essence without temporal attention.
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
OpenGVLab/VideoMAEv2
•
•
CVPR 2023
Finally, we successfully train a video ViT model with a billion parameters, which achieves a new state-of-the-art performance on the datasets of Kinetics (90. 0% on K400 and 89. 9% on K600) and Something-Something (68. 7% on V1 and 77. 0% on V2).
Unmasked Teacher: Towards Training-Efficient Video Foundation Models
opengvlab/unmasked_teacher
•
•
ICCV 2023
Previous VFMs rely on Image Foundation Models (IFMs), which face challenges in transferring to the video domain.
The effectiveness of MAE pre-pretraining for billion-scale pretraining
facebookresearch/maws
•
•
ICCV 2023
While MAE has only been shown to scale with the size of models, we find that it scales with the size of the training dataset as well.
