Related papers: Attentional Separation-and-Aggregation Network for…
Recent weakly-supervised methods for scene flow estimation from LiDAR point clouds are limited to explicit reasoning on object-level. These methods perform multiple iterative optimizations for each rigid object, which makes them vulnerable…
Recently, adversarial erasing for weakly-supervised object attention has been deeply studied due to its capability in localizing integral object regions. However, such a strategy raises one key problem that attention regions will gradually…
We present GLNet, a self-supervised framework for learning depth, optical flow, camera pose and intrinsic parameters from monocular video - addressing the difficulty of acquiring realistic ground-truth for such tasks. We propose three…
High-quality 4D light field representation with efficient angular feature modeling is crucial for scene perception, as it can provide discriminative spatial-angular cues to identify moving targets. However, recent developments still…
Automatic human action recognition is indispensable for almost artificial intelligent systems such as video surveillance, human-computer interfaces, video retrieval, etc. Despite a lot of progress, recognizing actions in an unknown video is…
Learning depth and camera ego-motion from raw unlabeled RGB video streams is seeing exciting progress through self-supervision from strong geometric cues. To leverage not only appearance but also scene geometry, we propose a novel…
Although existing monocular depth estimation methods have made great progress, predicting an accurate absolute depth map from a single image is still challenging due to the limited modeling capacity of networks and the scale ambiguity…
Linguistic knowledge is of great benefit to scene text recognition. However, how to effectively model linguistic rules in end-to-end deep networks remains a research challenge. In this paper, we argue that the limited capacity of language…
We introduce a convolutional neural network model for unsupervised learning of depth and ego-motion from cylindrical panoramic video. Panoramic depth estimation is an important technology for applications such as virtual reality, 3D…
Egocentric video grounding is a crucial task for embodied intelligence applications, distinct from exocentric video moment localization. Existing methods primarily focus on the distributional differences between egocentric and exocentric…
Learning object segmentation in image and video datasets without human supervision is a challenging problem. Humans easily identify moving salient objects in videos using the gestalt principle of common fate, which suggests that what moves…
Progress has been achieved recently in object detection given advancements in deep learning. Nevertheless, such tools typically require a large amount of training data and significant manual effort to label objects. This limits their…
Scene text recognition has attracted particular research interest because it is a very challenging problem and has various applications. The most cutting-edge methods are attentional encoder-decoder frameworks that learn the alignment…
Existing works address the problem of generating high frame-rate sharp videos by separately learning the frame deblurring and frame interpolation modules. Most of these approaches have a strong prior assumption that all the input frames are…
This paper addresses the challenge of perceiving complete object shapes through visual perception. While prior studies have demonstrated encouraging outcomes in segmenting the visible parts of objects within a scene, amodal segmentation, in…
3D convolutional neural networks have achieved promising results for video tasks in computer vision, including video saliency prediction that is explored in this paper. However, 3D convolution encodes visual representation merely on fixed…
In this paper, we provide an improved version of UnDEMoN model for depth and ego motion estimation from monocular images. The improvement is achieved by combining the standard bi-linear sampler with a deep network based image sampling model…
Sports videos pose complex challenges, including cluttered backgrounds, camera angle changes, small action-representing objects, and imbalanced action class distribution. Existing methods for detecting actions in sports videos heavily rely…
We introduce a novel network, called CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task from a holistic view. We emphasize the importance of inherent correlation among video frames and…
We introduce MGNet, a multi-task framework for monocular geometric scene understanding. We define monocular geometric scene understanding as the combination of two known tasks: Panoptic segmentation and self-supervised monocular depth…