相关论文: AdaScan: Adaptive Scan Pooling in Deep Convolution…
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…
We propose a function-based temporal pooling method that captures the latent structure of the video sequence data - e.g. how frame-level features evolve over time in a video. We show how the parameters of a function that has been fit to 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…
Encouraged by the success of Convolutional Neural Networks (CNNs) in image classification, recently much effort is spent on applying CNNs to video based action recognition problems. One challenge is that video contains a varying number of…
Most 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…
We introduce the concept of "dynamic image", a novel compact representation of videos useful for video analysis, particularly in combination with convolutional neural networks (CNNs). A dynamic image encodes temporal data such as RGB or…
Pooling layers are essential building blocks of convolutional neural networks (CNNs), to reduce computational overhead and increase the receptive fields of proceeding convolutional operations. Their goal is to produce downsampled volumes…
Deep ConvNets have shown its good performance in image classification tasks. However it still remains as a problem in deep video representation for action recognition. The problem comes from two aspects: on one hand, current video ConvNets…
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…
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 neural networks have recently achieved competitive accuracy for human activity recognition. However, there is room for improvement, especially in modeling long-term temporal importance and determining the activity relevance of…
Detecting complex events in a large video collection crawled from video websites is a challenging task. When applying directly good image-based feature representation, e.g., HOG, SIFT, to videos, we have to face the problem of how to pool…
We propose a novel pooling strategy that learns how to adaptively rank deep convolutional features for selecting more informative representations. To this end, we exploit discriminative analysis to project the features onto a space spanned…
Visual features are of vital importance for human action understanding in videos. This paper presents a new video representation, called trajectory-pooled deep-convolutional descriptor (TDD), which shares the merits of both hand-crafted…
The recent advances in Deep Convolutional Neural Networks (DCNNs) have shown extremely good results for video human action classification, however, action detection is still a challenging problem. The current action detection approaches…
Action recognition from videos, i.e., classifying a video into one of the pre-defined action types, has been a popular topic in the communities of artificial intelligence, multimedia, and signal processing. However, existing methods usually…
Video action recognition, which is topical in computer vision and video analysis, aims to allocate a short video clip to a pre-defined category such as brushing hair or climbing stairs. Recent works focus on action recognition with deep…
In Neural Processing Letters 50,3 (2019) a machine learning approach to blind video quality assessment was proposed. It is based on temporal pooling of features of video frames, taken from the last pooling layer of deep convolutional neural…
Recent studies have demonstrated the power of recurrent neural networks for machine translation, image captioning and speech recognition. For the task of capturing temporal structure in video, however, there still remain numerous open…
We introduce Eigen Evolution Pooling, an efficient method to aggregate a sequence of feature vectors. Eigen evolution pooling is designed to produce compact feature representations for a sequence of feature vectors, while maximally…