Related papers: Predicting Relative Depth between Objects from Sem…

Human visual attention on three-dimensional objects emerges from the interplay between bottom-up geometric processing and top-down semantic recognition. Existing 3D saliency methods rely on hand-crafted geometric features or learning-based…

We present a method to estimate depth of a dynamic scene, containing arbitrary moving objects, from an ordinary video captured with a moving camera. We seek a geometrically and temporally consistent solution to this underconstrained…

Relative pose estimation provides a promising way for achieving object-agnostic pose estimation. Despite the success of existing 3D correspondence-based methods, the reliance on explicit feature matching suffers from small overlaps in…

The current trend in object detection and localization is to learn predictions with high capacity deep neural networks trained on a very large amount of annotated data and using a high amount of processing power. In this work, we propose a…

Monocular depth estimation, enabled by self-supervised learning, is a key technique for 3D perception in computer vision. However, it faces significant challenges in real-world scenarios, which encompass adverse weather variations, motion…

A more realistic object detection paradigm, Open-World Object Detection, has arisen increasing research interests in the community recently. A qualified open-world object detector can not only identify objects of known categories, but also…

Following the successful application of deep convolutional neural networks to 2d human pose estimation, the next logical problem to solve is 3d human pose estimation from monocular images. While previous solutions have shown some success,…

Geometric navigation is nowadays a well-established field of robotics and the research focus is shifting towards higher-level scene understanding, such as Semantic Mapping. When a robot needs to interact with its environment, it must be…

The relevance between a query and a document in search can be represented as matching degree between the two objects. Latent space models have been proven to be effective for the task, which are often trained with click-through data. One…

We address the problem of phrase grounding by lear ing a multi-level common semantic space shared by the textual and visual modalities. We exploit multiple levels of feature maps of a Deep Convolutional Neural Network, as well as…

We present a system for object recognition based on a semantic graph representation, which the system can learn from image examples. This graph is based on intrinsic properties of objects such as structure and geometry, so it is more robust…

Despite significant progress in monocular depth estimation in the wild, recent state-of-the-art methods cannot be used to recover accurate 3D scene shape due to an unknown depth shift induced by shift-invariant reconstruction losses used in…

Modern vision models have achieved strong object-recognition performance, yet it remains unclear whether their representations encode object-level semantic relatedness, the meaningful connection between object concepts that supports human…

Understanding 3D objects from images is fundamental to robotics and AR/VR applications. While recent work has made progress in category-level pose estimation, current representations fail to capture the fine-grained semantics needed for…

The human face constantly conveys information, both consciously and subconsciously. However, as basic as it is for humans to visually interpret this information, it is quite a big challenge for machines. Conventional semantic facial feature…

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…

Deep learning has achieved remarkable results in 3D shape analysis by learning global shape features from the pixel-level over multiple views. Previous methods, however, compute low-level features for entire views without considering…

Establishing dense semantic correspondences between object instances remains a challenging problem due to background clutter, significant scale and pose differences, and large intra-class variations. In this paper, we address weakly…

Deep features have been proven powerful in building accurate dense semantic correspondences in various previous works. However, the multi-scale and pyramidal hierarchy of convolutional neural networks has not been well studied to learn…

In this study, we address the challenge of 3D scene structure recovery from monocular depth estimation. While traditional depth estimation methods leverage labeled datasets to directly predict absolute depth, recent advancements advocate…