The Kinetics Human Action Video Dataset
Explore this paper's citation graph
Summary
The dataset is described, the statistics are described, how it was collected, and some baseline performance figures for neural network architectures trained and tested for human action classification on this dataset are given.
- Type
- preprint
- Published
- 2017-05-19
- Cited by
- 4,583
- References
- 28
- Access
- Open access
- OpenAlex
- https://openalex.org/W2619947201
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:27300853
Keywords
Action (physics), Kinetics, Computer science, Physics
References
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Learning Spatiotemporal Features with 3D Convolutional Networks
- Caltech-256 Object Category Dataset
- ActivityNet: A large-scale video benchmark for human activity understanding
- Long-term recurrent convolutional networks for visual recognition and description
- Large-Scale Video Classification with Convolutional Neural Networks
- Unbiased look at dataset bias
- The Pascal Visual Object Classes Challenge: A Retrospective
- Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words
- 2D Human Pose Estimation: New Benchmark and State of the Art Analysis
- ImageNet Large Scale Visual Recognition Challenge
- HMDB: A large video database for human motion recognition
- Learning realistic human actions from movies
- Two-Stream Convolutional Networks for Action Recognition in Videos
- Deep Residual Learning for Image Recognition
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Convolutional Two-Stream Network Fusion for Video Action Recognition
- Actions ~ Transformations
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
- Semantics derived automatically from language corpora contain human-like biases
Cited by
- ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events
- ActionFlowNet: Learning Motion Representation for Action Recognition
- Second-order Temporal Pooling for Action Recognition
- Discriminatively Learned Hierarchical Rank Pooling Networks
- AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
- Look, Listen and Learn
- Pillar Networks for action recognition
- Pillar Networks++: Distributed non-parametric deep and wide networks
- Revisiting the Effectiveness of Off-the-shelf Temporal Modeling Approaches for Large-scale Video Classification
- Multi-label Class-imbalanced Action Recognition in Hockey Videos via 3D Convolutional Neural Networks
- Attentional Pooling for Action Recognition
- Video Generation From Text
- ActivityNet Challenge 2017 Summary
- Multi-modal Aggregation for Video Classification
- Video Classification via Relational Feature Encoding Networks
- ViTS: Video Tagging System from Massive Web Multimedia Collections
- Grounded Objects and Interactions for Video Captioning
- Rethinking Spatiotemporal Feature Learning For Video Understanding
- From Lifestyle Vlogs to Everyday Interactions
Related papers
- ИСПОЛЬЗОВAНИЕ ПОТЕНЦИAЛA СОЦИAЛЬНЫХ ПAРТНЕРОВ В ПОДГОТОВКЕ БУДУЩИХ ПЕДAГОГОВ
- Using DataGrid Control to Realize DataBase of Querying in VB6.0
- Peripheral N- and C-terminal domains determine deactivation kinetics of HCN channels.
- Study and Two Types of Typical Usage of DataGrid Web Server Control
- PACWON: A parallelizing compiler for workstations on a network
- Bidirectional Sort and Choosing a Row to Update or Delete by Click Any Cell in DataGrid
- OpenCL-accelerated object classification in video streams using Spatial Pooler of Hierarchical Temporal Memory
- ESKVS: efficient and secure approach for keyframes-based video summarization framework