Action recognition with trajectory-pooled deep-convolutional descriptors
Explore this paper's citation graph
- Type
- preprint
- Published
- 2015-05-19
- Cited by
- 1,201
- References
- 47
- Access
- Open access
- OpenAlex
- https://openalex.org/W1944615693
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:4284367
Keywords
Discriminative model, Artificial intelligence, Computer science, Pooling, Normalization (sociology)
References
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Image Classification with the Fisher Vector: Theory and Practice
- Multi-view Super Vector for Action Recognition
- Evaluation of Local Spatio-temporal Features for Action Recognition
- Return of the Devil in the Details: Delving Deep into Convolutional Nets
- Large-Scale Video Classification with Convolutional Neural Networks
- On Space-Time Interest Points
- A Spatio-Temporal Descriptor Based on 3D-Gradients
- Action bank: A high-level representation of activity in video
- Latent Hierarchical Model of Temporal Structure for Complex Activity Classification
- Dense Trajectories and Motion Boundary Descriptors for Action Recognition
- Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
- Going deeper with convolutions
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- HMDB: A large video database for human motion recognition
- Motionlets: Mid-level 3D Parts for Human Motion Recognition
- Action Recognition with Actons
- Learning realistic human actions from movies
Cited by
- Stacked Denoising Tensor Auto-Encoder for Action Recognition With Spatiotemporal Corruptions
- Towards Good Practices for Very Deep Two-Stream ConvNets
- The Best of BothWorlds: Combining Data-Independent and Data-Driven Approaches for Action Recognition
- Efficient large-scale action recognition in videos using extreme learning machines
- Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice
- Temporal Variance Analysis for Action Recognition
- Exploring Fisher vector and deep networks for action spotting
- Object-Scene Convolutional Neural Networks for event recognition in images
- Deep Gaussian Conditional Random Field Network: A Model-Based Deep Network for Discriminative Denoising
- Temporal Pyramid Pooling-Based Convolutional Neural Network for Action Recognition
- Pooling the Convolutional Layers in Deep ConvNets for Action Recognition
- MoFAP: A Multi-level Representation for Action Recognition
- Better Exploiting OS-CNNs for Better Event Recognition in Images
- A Taxonomy of Deep Convolutional Neural Nets for Computer Vision
- Long-Term Temporal Convolutions for Action Recognition
- Encoding Feature Maps of CNNs for Action Recognition
- ChaLearn Looking at People 2015: Apparent Age and Cultural Event Recognition Datasets and Results
- Deep Spatial Pyramid Ensemble for Cultural Event Recognition
- Harnessing the Deep Net Object Models for Enhancing Human Action Recognition
- Handcrafted Local Features are Convolutional Neural Networks
Related papers
- A Fully Trainable Network with RNN-based Pooling
- MixSiam: A Mixture-based Approach to Self-supervised Representation Learning
- Group Softmax Loss with Discriminative Feature Grouping
- Improved Discriminative Model for View- Invariant Human Action Recognition
- Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation
- Few-Shot Learning with Discriminative Representation for Cyberattack Detection
- Learning deep discriminative features based on cosine loss function