Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

https://github.com/Alibaba-MIIL/STAM

Official implementation of "An Image is Worth 16x16 Words, What is a Video Worth?" (2021 paper)
https://github.com/Alibaba-MIIL/STAM

Last synced: 4 months ago
JSON representation

Official implementation of "An Image is Worth 16x16 Words, What is a Video Worth?" (2021 paper)

Lists

README 

        
# An Image is Worth 16x16 Words, What is a Video Worth?



[paper](https://arxiv.org/pdf/2103.13915.pdf) 



Official PyTorch Implementation



> Gilad Sharir, Asaf Noy, Lihi Zelnik-Manor


> DAMO Academy, Alibaba Group



**Abstract**



> Leading methods in the domain of action recognition try to

distill information from both the spatial and temporal dimensions of an input video. Methods that reach State of the

Art (SotA) accuracy, usually make use of 3D convolution

layers as a way to abstract the temporal information from

video frames. The use of such convolutions requires sampling short clips from the input video, where each clip is a

collection of closely sampled frames. Since each short clip

covers a small fraction of an input video, multiple clips are

sampled at inference in order to cover the whole temporal

length of the video. This leads to increased computational

load and is impractical for real-world applications. We address the computational bottleneck by significantly reducing

the number of frames required for inference. Our approach

relies on a temporal transformer that applies global attention over video frames, and thus better exploits the salient

information in each frame. Therefore our approach is very

input efficient, and can achieve SotA results (on Kinetics

dataset) with a fraction of the data (frames per video), computation and latency. Specifically on Kinetics-400, we reach

78.8 top-1 accuracy with ×30 less frames per video, and

×40 faster inference than the current leading method

>



## Update 2/5/2021:  Improved results

Due to improved training hyperparameters, and using KD training, we were able to improve

 STAM results on Kinetics400 (+ ~1.5%).  We are releasing the pretrained weights of the improved

  models (see Pretrained Models below). 



## Main Article Results



STAM models accuracy and GPU throughput on Kinetics400, compared to X3D. All measurements were

 done on Nvidia V100 GPU, with mixed precision. All models are trained on input resolution of 224.



 


  

    Models

    Top-1 Accuracy 
(%)

    Flops × views
(10^9)

    # Input Frames

    Runtime
(Videos/sec)

  

  

    X3D-M

    76.0

    6.2 × 30 

    480

    1.3

  

  

    X3D-L

    77.5

    24.8 × 30

    480

    0.46

  

  

    X3D-XL

    79.1

    48.4 × 30

    480

    N/A

  

  

    X3D-XXL

    80.4

    194 × 30

    480

    N/A

  

  

    TimeSformer-L

    80.7

    2380 × 3

     288 

    N/A

  

  

    ViViT-L

    81.3

    3992 × 12

    384

    N/A

  

  

    STAM-8

    77.5

    135 × 1

    8

    ---

  

  

    STAM-16

    79.3

    270 × 1

    16

    20.0

  

  

    STAM-32

    79.95

    540 × 1

    32

    ---

  

  

    STAM-64

    80.5

    1080 × 1

    64

    4.8

  

 



## Pretrained Models



We provide a collection of STAM models pre-trained on Kinetics400. 



| Model name  | checkpoint

| ------------ | :--------------: |

| STAM_8 | [link](https://miil-public-eu.oss-eu-central-1.aliyuncs.com/model-zoo/STAM/v2/stam_8.pth) |

| STAM_16 | [link](https://miil-public-eu.oss-eu-central-1.aliyuncs.com/model-zoo/STAM/v2/stam_16.pth) |

| STAM_32 | [link](https://miil-public-eu.oss-eu-central-1.aliyuncs.com/model-zoo/STAM/v2/stam_32.pth) |

| STAM_64 | [link](https://miil-public-eu.oss-eu-central-1.aliyuncs.com/model-zoo/STAM/v2/stam_64.pth) |



## Reproduce Article Scores

We provide code for reproducing the validation top-1 score of STAM

models on Kinetics400. First, download pretrained models from the links above.



Then, run the infer.py script. For example, for stam_16 (input size 224)

run:

```bash

python -m infer \

--val_dir=/path/to/kinetics_val_folder \

--model_path=/model/path/to/stam_16.pth \

--model_name=stam_16

--input_size=224

```



## Citations



```bibtex

@misc{sharir2021image,

    title   = {An Image is Worth 16x16 Words, What is a Video Worth?}, 

    author  = {Gilad Sharir and Asaf Noy and Lihi Zelnik-Manor},

    year    = {2021},

    eprint  = {2103.13915},

    archivePrefix = {arXiv},

    primaryClass = {cs.CV}

}

```



## Acknowledgements



We thank Tal Ridnik for discussions and comments.



Some components of this code implementation are adapted from the excellent

[repository of Ross Wightman](https://github.com/rwightman/pytorch-image-models). Check it out and give it a star while

you are at it.