Related papers: Enhancing temporal segmentation by nonlocal self-s…

Fine-grained action detection is an important task with numerous applications in robotics and human-computer interaction. Existing methods typically utilize a two-stage approach including extraction of local spatio-temporal features…

We present TDNet, a temporally distributed network designed for fast and accurate video semantic segmentation. We observe that features extracted from a certain high-level layer of a deep CNN can be approximated by composing features…

When a deep neural network is trained on data with only image-level labeling, the regions activated in each image tend to identify only a small region of the target object. We propose a method of using videos automatically harvested from…

In low-level video analyses, effective representations are important to derive the correspondences between video frames. These representations have been learned in a self-supervised fashion from unlabeled images or videos, using carefully…

Real-time tool segmentation is an essential component in computer-assisted surgical systems. We propose a novel real-time automatic method based on Fully Convolutional Networks (FCN) and optical flow tracking. Our method exploits the…

Video monocular depth estimation is essential for applications such as autonomous driving, AR/VR, and robotics. Recent transformer-based single-image monocular depth estimation models perform well on single images but struggle with depth…

Semantic segmentation, which refers to pixel-wise classification of an image, is a fundamental topic in computer vision owing to its growing importance in robot vision and autonomous driving industries. It provides rich information about…

Instance segmentation is a challenging task aiming at classifying and segmenting all object instances of specific classes. While two-stage box-based methods achieve top performances in the image domain, they cannot easily extend their…

The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study. In the proposed approach, label prediction and network parameter learning are alternately iterated to meet the following…

Multimodal image fusion and semantic segmentation are critical for autonomous driving. Despite advancements, current models often struggle with segmenting densely packed elements due to a lack of comprehensive fusion features for guidance…

Traditionally, training neural networks to perform semantic segmentation required expensive human-made annotations. But more recently, advances in the field of unsupervised learning have made significant progress on this issue and towards…

In this paper, we introduce Coarse-Fine Networks, a two-stream architecture which benefits from different abstractions of temporal resolution to learn better video representations for long-term motion. Traditional Video models process…

We present a novel approach for unsupervised activity segmentation which uses video frame clustering as a pretext task and simultaneously performs representation learning and online clustering. This is in contrast with prior works where…

Multilevel strategies are an integral part of many image registration algorithms. These strategies are very well-known for avoiding undesirable local minima, providing an outstanding initial guess, and reducing overall computation time.…

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…

Monocular depth estimation involves predicting depth from a single RGB image and plays a crucial role in applications such as autonomous driving, robotic navigation, 3D reconstruction, etc. Recent advancements in learning-based methods have…

Event cameras offer significant advantages for low-light video enhancement, primarily due to their high dynamic range. Current research, however, is severely limited by the absence of large-scale, real-world, and spatio-temporally aligned…

How to effectively and efficiently deal with spatio-temporal event streams, where the events are generally sparse and non-uniform and have the microsecond temporal resolution, is of great value and has various real-life applications.…

Generating non-existing frames from a consecutive video sequence has been an interesting and challenging problem in the video processing field. Typical kernel-based interpolation methods predict pixels with a single convolution process that…

Semantic segmentation has been widely investigated in the community, in which the state of the art techniques are based on supervised models. Those models have reported unprecedented performance at the cost of requiring a large set of high…