Related papers: Rethinking Motion Representation: Residual Frames …
Deep learning has been demonstrated to achieve excellent results for image classification and object detection. However, the impact of deep learning on video analysis (e.g. action detection and recognition) has been limited due to…
Image segmentation is an important step in most visual tasks. While convolutional neural networks have shown to perform well on single image segmentation, to our knowledge, no study has been been done on leveraging recurrent gated…
The paucity of videos in current action classification datasets (UCF-101 and HMDB-51) has made it difficult to identify good video architectures, as most methods obtain similar performance on existing small-scale benchmarks. This paper…
Visual attributes play an essential role in real applications based on image retrieval. For instance, the extraction of attributes from images allows an eCommerce search engine to produce retrieval results with higher precision. The…
Video processing and analysis have become an urgent task since a huge amount of videos (e.g., Youtube, Hulu) are uploaded online every day. The extraction of representative key frames from videos is very important in video processing and…
Facial expression spotting is the preliminary step for micro- and macro-expression analysis. The task of reliably spotting such expressions in video sequences is currently unsolved. The current best systems depend upon optical flow methods…
In this paper, we introduce a global video representation to video-based person re-identification (re-ID) that aggregates local 3D features across the entire video extent. Most of the existing methods rely on 2D convolutional networks…
Deep convolutional networks are widely used in video action recognition. 3D convolutions are one prominent approach to deal with the additional time dimension. While 3D convolutions typically lead to higher accuracies, the inner workings of…
In this paper, we consider the task of unsupervised object discovery in videos. Previous works have shown promising results via processing optical flows to segment objects. However, taking flow as input brings about two drawbacks. First,…
Currently, spatiotemporal features are embraced by most deep learning approaches for human action detection in videos, however, they neglect the important features in frequency domain. In this work, we propose an end-to-end network that…
Traditional 3D convolutions are computationally expensive, memory intensive, and due to large number of parameters, they often tend to overfit. On the other hand, 2D CNNs are less computationally expensive and less memory intensive than 3D…
Different from salient object detection methods for still images, a key challenging for video saliency detection is how to extract and combine spatial and temporal features. In this paper, we present a novel and effective approach for…
Recent advances in deep learning have significantly improved performance of video prediction. However, state-of-the-art methods still suffer from blurriness and distortions in their future predictions, especially when there are large…
Typical human actions last several seconds and exhibit characteristic spatio-temporal structure. Recent methods attempt to capture this structure and learn action representations with convolutional neural networks. Such representations,…
After the incredible success of deep learning in the computer vision domain, there has been much interest in applying Convolutional Network (ConvNet) features in robotic fields such as visual navigation and SLAM. Unfortunately, there are…
Training of Convolutional Neural Networks (CNNs) on long video sequences is computationally expensive due to the substantial memory requirements and the massive number of parameters that deep architectures demand. Early fusion of video…
Violence and abnormal behavior detection research have known an increase of interest in recent years, due mainly to a rise in crimes in large cities worldwide. In this work, we propose a deep learning architecture for violence detection…
Existing action recognition methods typically sample a few frames to represent each video to avoid the enormous computation, which often limits the recognition performance. To tackle this problem, we propose Ample and Focal Network (AFNet),…
Convolutional Neural Networks (CNNs) filter the input data using spatial convolution operators with compact stencils. Commonly, the convolution operators couple features from all channels, which leads to immense computational cost in the…
We address the problem of action detection in videos. Driven by the latest progress in object detection from 2D images, we build action models using rich feature hierarchies derived from shape and kinematic cues. We incorporate appearance…