相关论文: Order-aware Convolutional Pooling for Video Based …

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…

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…

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…

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…

We propose a novel method for temporally pooling frames in a video for the task of human action recognition. The method is motivated by the observation that there are only a small number of frames which, together, contain sufficient…

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…

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…

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…

Consider a set of n images of a scene with dynamic objects captured with a static or a handheld camera. Let the temporal order in which these images are captured be unknown. There can be n! possibilities for the temporal order in which…

This analysis explores the temporal sequencing of objects in a movie trailer. Temporal sequencing of objects in a movie trailer (e.g., a long shot of an object vs intermittent short shots) can convey information about the type of movie,…

Most action recognition methods base on a) a late aggregation of frame level CNN features using average pooling, max pooling, or RNN, among others, or b) spatio-temporal aggregation via 3D convolutions. The first assume independence among…

In this paper, a novel video classification method is presented that aims to recognize different categories of third-person videos efficiently. Our motivation is to achieve a light model that could be trained with insufficient training…

In this paper, we present a new feature representation for first-person videos. In first-person video understanding (e.g., activity recognition), it is very important to capture both entire scene dynamics (i.e., egomotion) and salient local…

In video-based person re-identification, both the spatial and temporal features are known to provide orthogonal cues to effective representations. Such representations are currently typically obtained by aggregating the frame-level features…

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…

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…

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…

This thesis focuses on video understanding for human action and interaction recognition. We start by identifying the main challenges related to action recognition from videos and review how they have been addressed by current methods. Based…

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…

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…