Related papers: Beyond Temporal Pooling: Recurrence and Temporal C…
Image and video classification research has made great progress through the development of handcrafted local features and learning based features. These two architectures were proposed roughly at the same time and have flourished at…
Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of…
How can we tell whether a video has been sped up or slowed down? How can we generate videos at different speeds? Although videos have been central to modern computer vision research, little attention has been paid to perceiving and…
Many methods for learning from video sequences involve temporally processing 2D CNN features from the individual frames or directly utilizing 3D convolutions within high-performing 2D CNN architectures. The focus typically remains on how to…
Video-based person re-identification aims to match pedestrians from video sequences across non-overlapping camera views. The key factor for video person re-identification is to effectively exploit both spatial and temporal clues from video…
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,…
Video action recognition has made significant strides, but challenges remain in effectively using both spatial and temporal information. While existing methods often focus on either spatial features (e.g., object appearance) or temporal…
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…
Despite the steady progress in video analysis led by the adoption of convolutional neural networks (CNNs), the relative improvement has been less drastic as that in 2D static image classification. Three main challenges exist including…
Change detection is one of the central problems in earth observation and was extensively investigated over recent decades. In this paper, we propose a novel recurrent convolutional neural network (ReCNN) architecture, which is trained to…
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…
Temporally locating and classifying action segments in long untrimmed videos is of particular interest to many applications like surveillance and robotics. While traditional approaches follow a two-step pipeline, by generating frame-wise…
Video-based person re-identification (ReID) is a challenging problem, where some video tracks of people across non-overlapping cameras are available for matching. Feature aggregation from a video track is a key step for video-based person…
Although current face manipulation techniques achieve impressive performance regarding quality and controllability, they are struggling to generate temporal coherent face videos. In this work, we explore to take full advantage of the…
While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this work has focused on images. In a similar spirit, we view…
Understanding temporal dynamics of video is an essential aspect of learning better video representations. Recently, transformer-based architectural designs have been extensively explored for video tasks due to their capability to capture…
Temporal modeling is crucial for video super-resolution. Most of the video super-resolution methods adopt the optical flow or deformable convolution for explicitly motion compensation. However, such temporal modeling techniques increase the…
We present a new action recognition deep neural network which adaptively learns the best action velocities in addition to the classification. While deep neural networks have reached maturity for image understanding tasks, we are still…
This paper focuses on tackling the problem of temporal language localization in videos, which aims to identify the start and end points of a moment described by a natural language sentence in an untrimmed video. However, it is non-trivial…
Several recent approaches showed how the representations learned by Convolutional Neural Networks can be repurposed for novel tasks. Most commonly it has been shown that the activation features of the last fully connected layers (fc7 or…