paper-with-me

홈 › Papers

Do Less and Achieve More: Training CNNs for Action Recognition Utilizing Action Images from the Web

2015-12-22 · Shugao Ma, Sarah Adel Bargal, Jianming Zhang, Leonid Sigal, Stan Sclaroff

Recently, attempts have been made to collect millions of videos to train CNN models for action recognition in videos. However, curating such large-scale video datasets requires immense human labor, and training CNNs on millions of videos demands huge computational resources. In contrast, collecting action images from the Web is much easier and training on images requires much less computation. In addition, labeled web images tend to contain discriminative action poses, which highlight discriminative portions of a video's temporal progression. We explore the question of whether we can utilize web action images to train better CNN models for action recognition in videos. We collect 23.8K manually filtered images from the Web that depict the 101 actions in the UCF101 action video dataset. We show that by utilizing web action images along with videos in training, significant performance boosts of CNN models can be achieved. We then investigate the scalability of the process by leveraging crawled web images (unfiltered) for UCF101 and ActivityNet. We replace 16.2M video frames by 393K unfiltered images and get comparable performance.

📄 PDF Abstract BibTeX arXiv:1512.07155

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionAction Recognition In VideosTemporal Action Localization

Similar Papers 제목 키워드 기반

Exploring Adversarial Examples and Adversarial Robustness of Convolutional Neural Networks by Mutual Information

2022-07-12 · Jiebao Zhang, Wenhua Qian, Rencan Nie, Jinde Cao 외

A counter-intuitive property of convolutional neural networks (CNNs) is their inherent susceptibility to adversarial examples, which severely hinders the application of CNNs in security-critical fields. Adversarial examp…

Adversarial Robustness

Caffeinated FPGAs: FPGA Framework For Convolutional Neural Networks

2016-09-30 · Roberto DiCecco, Griffin Lacey, Jasmina Vasiljevic, Paul Chow 외

Convolutional Neural Networks (CNNs) have gained significant traction in the field of machine learning, particularly due to their high accuracy in visual recognition. Recent works have pushed the performance of GPU imple…

General ClassificationGPU

A breakthrough in Speech emotion recognition using Deep Retinal Convolution Neural Networks

2017-07-12 · Yafeng Niu, Dongsheng Zou, Yadong Niu, Zhongshi He 외

Speech emotion recognition (SER) is to study the formation and change of speaker's emotional state from the speech signal perspective, so as to make the interaction between human and computer more intelligent. SER is a c…

Data AugmentationEmotion RecognitionSpeech Emotion Recognition

Are Transformers More Robust Than CNNs?

2021-11-10 · NeurIPS 2021 12 · Yutong Bai, Jieru Mei, Alan Yuille, Cihang Xie

Transformer emerges as a powerful tool for visual recognition. In addition to demonstrating competitive performance on a broad range of visual benchmarks, recent works also argue that Transformers are much more robust th…

Adversarial Robustness

Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition

2020-07-22 · Sudhakar Kumawat, Manisha Verma, Yuta Nakashima, Shanmuganathan Raman

Conventional 3D convolutional neural networks (CNNs) are computationally expensive, memory intensive, prone to overfitting, and most importantly, there is a need to improve their feature learning capabilities. To address…

Action RecognitionTemporal Action Localization