Related papers: Higher-order Pooling of CNN Features via Kernel Li…
Deep learning models for video-based action recognition usually generate features for short clips (consisting of a few frames); such clip-level features are aggregated to video-level representations by computing statistics on these…
In this work, we present novel temporal encoding methods for action and activity classification by extending the unsupervised rank pooling temporal encoding method in two ways. First, we present "discriminative rank pooling" in which the…
Deep convolutional neural networks (CNNs) are nowadays achieving significant leaps in different pattern recognition tasks including action recognition. Current CNNs are increasingly deeper, data-hungrier and this makes their success…
Training Deep Convolutional Neural Networks (CNNs) is based on the notion of using multiple kernels and non-linearities in their subsequent activations to extract useful features. The kernels are used as general feature extractors without…
Representations that can compactly and effectively capture temporal evolution of semantic content are important to machine learning algorithms that operate on multi-variate time-series data. We investigate such representations motivated by…
Most popular deep learning based models for action recognition are designed to generate separate predictions within their short temporal windows, which are often aggregated by heuristic means to assign an action label to the full video…
Most popular deep models for action recognition split video sequences into short sub-sequences consisting of a few frames; frame-based features are then pooled for recognizing the activity. Usually, this pooling step discards the temporal…
Human actions in video sequences are characterized by the complex interplay between spatial features and their temporal dynamics. In this paper, we propose novel tensor representations for compactly capturing such higher-order relationships…
We aim at capturing high-order statistics of feature vectors formed by a neural network, and propose end-to-end second- and higher-order pooling to form a tensor descriptor. Tensor descriptors require a robust similarity measure due to low…
Representations that can compactly and effectively capture the temporal evolution of semantic content are important to computer vision and machine learning algorithms that operate on multi-variate time-series data. We investigate such…
During the last years, deep learning trackers achieved stimulating results while bringing interesting ideas to solve the tracking problem. This progress is mainly due to the use of learned deep features obtained by training deep…
Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as feature representation. However, the information in this layer may be too coarse to allow precise localization. On the contrary,…
Recent empirical work has shown that hierarchical convolutional kernels inspired by convolutional neural networks (CNNs) significantly improve the performance of kernel methods in image classification tasks. A widely accepted explanation…
Most of the current action recognition algorithms are based on deep networks which stack multiple convolutional, pooling and fully connected layers. While convolutional and fully connected operations have been widely studied in the…
We present a novel approach to neural response prediction that incorporates higher-order operations directly within convolutional neural networks (CNNs). Our model extends traditional 3D CNNs by embedding higher-order operations within the…
Most video based action recognition approaches create the video-level representation by temporally pooling the features extracted at each frame. The pooling methods that they adopt, however, usually completely or partially neglect the…
Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification. However, the development of high-quality deep models typically relies on a substantial amount…
Popular deep models for action recognition in videos generate independent predictions for short clips, which are then pooled heuristically to assign an action label to the full video segment. As not all frames may characterize the…
Graph Neural Networks achieve state-of-the-art performance on a plethora of graph classification tasks, especially due to pooling operators, which aggregate learned node embeddings hierarchically into a final graph representation. However,…
Most of human actions consist of complex temporal compositions of more simple actions. Action recognition tasks usually relies on complex handcrafted structures as features to represent the human action model. Convolutional Neural Nets…