Related papers: Improving Semantic Segmentation through Spatio-Tem…
This work addresses multi-class segmentation of indoor scenes with RGB-D inputs. While this area of research has gained much attention recently, most works still rely on hand-crafted features. In contrast, we apply a multiscale…
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…
State-of-the-art deep neural networks demonstrate outstanding performance in semantic segmentation. However, their performance is tied to the domain represented by the training data. Open world scenarios cause inaccurate predictions which…
Self-supervised learning has drawn attention through its effectiveness in learning in-domain representations with no ground-truth annotations; in particular, it is shown that properly designed pretext tasks (e.g., contrastive prediction…
We consider the problem of transferring a temporal action segmentation system initially designed for exocentric (fixed) cameras to an egocentric scenario, where wearable cameras capture video data. The conventional supervised approach…
Event cameras are neuromorphically inspired sensors that sparsely and asynchronously report brightness changes. Their unique characteristics of high temporal resolution, high dynamic range, and low power consumption make them well-suited…
We propose a novel approach to the action segmentation task for long, untrimmed videos, based on solving an optimal transport problem. By encoding a temporal consistency prior into a Gromov-Wasserstein problem, we are able to decode a…
Enabling computational systems with the ability to localize actions in video-based content has manifold applications. Traditionally, such a problem is approached in a fully-supervised setting where video-clips with complete frame-by-frame…
Video segmentation -- partitioning video frames into multiple segments or objects -- plays a critical role in a broad range of practical applications, from enhancing visual effects in movie, to understanding scenes in autonomous driving, to…
We propose a stereo vision-based approach for tracking the camera ego-motion and 3D semantic objects in dynamic autonomous driving scenarios. Instead of directly regressing the 3D bounding box using end-to-end approaches, we propose to use…
Action recognition is currently one of the top-challenging research fields in computer vision. Convolutional Neural Networks (CNNs) have significantly boosted its performance but rely on fixed-size spatio-temporal windows of analysis,…
Rapid progress in terrain-aware autonomous ground navigation has been driven by advances in supervised semantic segmentation. However, these methods rely on costly data collection and labor-intensive ground truth labeling to train deep…
Stereo matching is one of the widely used techniques for inferring depth from stereo images owing to its robustness and speed. It has become one of the major topics of research since it finds its applications in autonomous driving, robotic…
Semantic video segmentation is a key challenge for various applications. This paper presents a new model named Noisy-LSTM, which is trainable in an end-to-end manner, with convolutional LSTMs (ConvLSTMs) to leverage the temporal coherency…
Semantic segmentation is a well-addressed topic in the computer vision literature, but the design of fast and accurate video processing networks remains challenging. In addition, to run on embedded hardware, computer vision models often…
Stereo matching provides depth estimation from binocular images for downstream applications. These applications mostly take video streams as input and require temporally consistent depth maps. However, existing methods mainly focus on the…
Learning meaningful visual representations in an embedding space can facilitate generalization in downstream tasks such as action segmentation and imitation. In this paper, we learn a motion-centric representation of surgical video…
Self-supervised monocular depth estimation has emerged as a promising method because it does not require groundtruth depth maps during training. As an alternative for the groundtruth depth map, the photometric loss enables to provide…
The performance of supervised deep learning methods for medical image segmentation is often limited by the scarcity of labeled data. As a promising research direction, semi-supervised learning addresses this dilemma by leveraging unlabeled…
This paper presents a deep learning framework for medical video segmentation. Convolution neural network (CNN) and transformer-based methods have achieved great milestones in medical image segmentation tasks due to their incredible semantic…