Related papers: Robust and Efficient Graph Correspondence Transfer…
In this paper, we tackle the problem of performing consistent and unified modifications across a set of related images. This task is particularly challenging because these images may vary significantly in pose, viewpoint, and spatial…
Graph-based models have achieved great success in person re-identification tasks recently, which compute the graph topology structure (affinities) among different people first and then pass the information across them to achieve stronger…
We propose a novel network that learns a part-aligned representation for person re-identification. It handles the body part misalignment problem, that is, body parts are misaligned across human detections due to pose/viewpoint change and…
Cloth-Changing person re-identification (CC-ReID) aims at matching the same person across different locations over a long-duration, e.g., over days, and therefore inevitably meets challenge of changing clothing. In this paper, we focus on…
Reconstructing 3D human shape and pose from monocular images is challenging despite the promising results achieved by the most recent learning-based methods. The commonly occurred misalignment comes from the facts that the mapping from…
We propose Co-op, a novel method for accurately and robustly estimating the 6DoF pose of objects unseen during training from a single RGB image. Our method requires only the CAD model of the target object and can precisely estimate its pose…
Establishing dense correspondence between two images is a fundamental computer vision problem, which is typically tackled by matching local feature descriptors. However, without global awareness, such local features are often insufficient…
Learning the distance metric between pairs of examples is of great importance for visual recognition, especially for person re-identification (Re-Id). Recently, the contrastive and triplet loss are proposed to enhance the discriminative…
Feature extraction and matching are two crucial components in person Re-Identification (ReID). The large pose deformations and the complex view variations exhibited by the captured person images significantly increase the difficulty of…
Gait recognition is emerging as a promising and innovative area within the field of computer vision, widely applied to remote person identification. Although existing gait recognition methods have achieved substantial success in controlled…
Due to unreliable geometric matching and content misalignment, most conventional pose transfer algorithms fail to generate fine-trained person images. In this paper, we propose a novel framework Spatial Content Alignment GAN (SCAGAN) which…
Person re-identification aims to identify a specific person at distinct times and locations. It is challenging because of occlusion, illumination, and viewpoint change in camera views. Recently, multi-shot person re-id task receives more…
In order to answer semantically-complicated questions about an image, a Visual Question Answering (VQA) model needs to fully understand the visual scene in the image, especially the interactive dynamics between different objects. We propose…
Person re-identification (re-ID) in the scenario with large spatial and temporal spans has not been fully explored. This is partially because that, existing benchmark datasets were mainly collected with limited spatial and temporal ranges,…
Scene coordinate regression has become an essential part of current camera re-localization methods. Different versions, such as regression forests and deep learning methods, have been successfully applied to estimate the corresponding…
A new method is proposed for human motion prediction by learning temporal and spatial dependencies. Recently, multiscale graphs have been developed to model the human body at higher abstraction levels, resulting in more stable motion…
Skeleton-based person re-identification (Re-ID) is an emerging open topic providing great value for safety-critical applications. Existing methods typically extract hand-crafted features or model skeleton dynamics from the trajectory of…
Deformable image registration estimates voxel-wise correspondences between images through spatial transformations, and plays a key role in medical imaging. While deep learning methods have significantly reduced runtime, efficiently handling…
Person re-identification (re-id), the process of matching pedestrian images across different camera views, is an important task in visual surveillance. Substantial development of re-id has recently been observed, and the majority of…
Person re-identification (Re-ID) via gait features within 3D skeleton sequences is a newly-emerging topic with several advantages. Existing solutions either rely on hand-crafted descriptors or supervised gait representation learning. This…