Related papers: Self-supervised Geometric Features Discovery via I…
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…
Recent advances in person re-identification have demonstrated enhanced discriminability, especially with supervised learning or transfer learning. However, since the data requirements---including the degree of data curations---are becoming…
Set-based person re-identification (SReID) is a matching problem that aims to verify whether two sets are of the same identity (ID). Existing SReID models typically generate a feature representation per image and aggregate them to represent…
Person re-identification (reID) aims to match person images to retrieve the ones with the same identity. This is a challenging task, as the images to be matched are generally semantically misaligned due to the diversity of human poses and…
Vision Transformers (ViTs) have excelled in vehicle re-identification (ReID) tasks. However, non-square aspect ratios of image or video input might significantly affect the re-identification performance. To address this issue, we propose a…
Vehicle re-identification helps in distinguishing between images of the same and other vehicles. It is a challenging process because of significant intra-instance differences between identical vehicles from different views and subtle…
Low-level 3D representations, such as point clouds, meshes, NeRFs and 3D Gaussians, are commonly used for modeling 3D objects and scenes. However, cognitive studies indicate that human perception operates at higher levels and interprets 3D…
Transformers are more and more popular in computer vision, which treat an image as a sequence of patches and learn robust global features from the sequence. However, pure transformers are not entirely suitable for vehicle re-identification…
A key challenge of learning a visual representation for the 3D high fidelity geometry of dressed humans lies in the limited availability of the ground truth data (e.g., 3D scanned models), which results in the performance degradation of 3D…
As a fundamental yet challenging problem in intelligent transportation systems, point cloud registration attracts vast attention and has been attained with various deep learning-based algorithms. The unsupervised registration algorithms…
While metric learning is important for Person re-identification (RE-ID), a significant problem in visual surveillance for cross-view pedestrian matching, existing metric models for RE-ID are mostly based on supervised learning that requires…
Vehicle Re-identification (re-id) over surveillance camera network with non-overlapping field of view is an exciting and challenging task in intelligent transportation systems (ITS). Due to its versatile applicability in metropolitan…
Progress in self-supervised learning has brought strong general image representation learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks such as unsupervised image segmentation have not benefited from…
Recently, large-scale vision-language pre-trained models like CLIP have shown impressive performance in image re-identification (ReID). In this work, we explore whether self-supervision can aid in the use of CLIP for image ReID tasks.…
Extracting effective and discriminative features is very important for addressing the challenging person re-identification (re-ID) task. Prevailing deep convolutional neural networks (CNNs) usually use high-level features for identifying…
Robust local feature representations are essential for spatial intelligence tasks such as robot navigation and augmented reality. Establishing reliable correspondences requires descriptors that provide both high discriminative power and…
Person re-identification (ReID) is a challenging task due to arbitrary human pose variations, background clutters, etc. It has been studied extensively in recent years, but the multifarious local and global features are still not fully…
Person re-identification (re-id) aims to match pedestrians observed by disjoint camera views. It attracts increasing attention in computer vision due to its importance to surveillance system. To combat the major challenge of cross-view…
Most invariance-based self-supervised methods rely on single object-centric images (e.g., ImageNet images) for pretraining, learning features that invariant to geometric transformation. However, when images are not object-centric, the…
Self-supervised multi-object trackers have tremendous potential as they enable learning from raw domain-specific data. However, their re-identification accuracy still falls short compared to their supervised counterparts. We hypothesize…