The “Something Something” Video Database for Learning and Evaluating Visual Common Sense
Raghav Goyal,Samira Ebrahimi Kahou,Vincent Michalski,Joanna Materzynska,Susanne Westphal,Heuna Kim,Valentin Haenel,Ingo Fruend,Peter N. Yianilos,Moritz Mueller-Freitag,Florian Hoppe,Christian Thurau,Ingo Bax,Roland Memisevic +13 more
- pp 5843-5851
TLDR
This work describes the ongoing collection of the “something-something” database of video prediction tasks whose solutions require a common sense understanding of the depicted situation, and describes the challenges in crowd-sourcing this data at scale.Abstract:
Neural networks trained on datasets such as ImageNet have led to major advances in visual object classification. One obstacle that prevents networks from reasoning more deeply about complex scenes and situations, and from integrating visual knowledge with natural language, like humans do, is their lack of common sense knowledge about the physical world. Videos, unlike still images, contain a wealth of detailed information about the physical world. However, most labelled video datasets represent high-level concepts rather than detailed physical aspects about actions and scenes. In this work, we describe our ongoing collection of the “something-something” database of video prediction tasks whose solutions require a common sense understanding of the depicted situation. The database currently contains more than 100,000 videos across 174 classes, which are defined as caption-templates. We also describe the challenges in crowd-sourcing this data at scale.read more
Citations
More filters
Posted Content
Only Time Can Tell: Discovering Temporal Data for Temporal Modeling
TL;DR: This paper identifies action classes where temporal information is actually necessary to recognize them and call these "temporal classes", and proposes a methodology based on a simple and effective human annotation experiment that leads to better generalization in unseen classes, demonstrating the need for more temporal data.
Posted Content
V4D:4D Convolutional Neural Networks for Video-level Representation Learning
TL;DR: This paper designs a new 4D residual block able to capture inter-clip interactions, which could enhance the representation power of the original clip-level 3D CNNs, and introduces the training and inference methods for the proposed V4D.
Proceedings ArticleDOI
Video Action Recognition Via Neural Architecture Searching
TL;DR: This paper makes the first attempt to let algorithm automatically design neural networks for video action recognition tasks using a spatio-temporal network developed in a differentiable space modeled by a directed acyclic graph.
Proceedings ArticleDOI
Dynamic Motion Representation for Human Action Recognition
TL;DR: The experimental results show that training a convolutional neural network with the dynamic motion representation outperforms state-of-the-art action recognition models and is obtainable on HMDB, JHMDB, UCF-101, and AVA datasets.
Proceedings ArticleDOI
Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework
TL;DR: In this article, a self-supervised method is proposed to learn feature representations from videos. But the method is limited to video retrieval and video recognition tasks, and it is not suitable for video classification.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.