Related papers: Self-supervised Geometric Features Discovery via I…

Object Re-Identification (ReID) is pivotal in computer vision, witnessing an escalating demand for adept multimodal representation learning. Current models, although promising, reveal scalability limitations with increasing modalities as…

Object-centric understanding is fundamental to human vision and required for complex reasoning. Traditional methods define slot-based bottlenecks to learn object properties explicitly, while recent self-supervised vision models like DINO…

In recommender systems, models mostly use a combination of embedding layers and multilayer feedforward neural networks. The high-dimensional sparse original features are downscaled in the embedding layer and then fed into the fully…

3D object representation learning is a fundamental challenge in computer vision to infer about the 3D world. Recent advances in deep learning have shown their efficiency in 3D object recognition, among which view-based methods have…

Re-identification (ReID) is to identify the same instance across different cameras. Existing ReID methods mostly utilize alignment-based or attention-based strategies to generate effective feature representations. However, most of these…

Vehicle re-identification (ReID) in a large-scale camera network is important in public safety, traffic control, and security. However, due to the appearance ambiguities of vehicle, the previous appearance-based ReID methods often fail to…

Vessel segmentation is an essential task in many clinical applications. Although supervised methods have achieved state-of-art performance, acquiring expert annotation is laborious and mostly limited for two-dimensional datasets with a…

Unsupervised person re-identification (ReID) aims to train a feature extractor for identity retrieval without exploiting identity labels. Due to the blind trust in imperfect clustering results, the learning is inevitably misled by…

Existing methods for video-based person re-identification (ReID) mainly learn the appearance feature of a given pedestrian via a feature extractor and a feature aggregator. However, the appearance models would fail when different…

In this paper, we propose a self-supervised learningmethod for multi-object pose estimation. 3D object under-standing from 2D image is a challenging task that infers ad-ditional dimension from reduced-dimensional information.In particular,…

Object parts serve as crucial intermediate representations in various downstream tasks, but part-level representation learning still has not received as much attention as other vision tasks. Previous research has established that Vision…

The performance of person re-identification (Re-ID) has been seriously effected by the large cross-view appearance variations caused by mutual occlusions and background clutters. Hence learning a feature representation that can adaptively…

In comparison with person re-identification (ReID), which has been widely studied in the research community, vehicle ReID has received less attention. Vehicle ReID is challenging due to 1) high intra-class variability (caused by the…

Self-supervised representation learning techniques utilize large datasets without semantic annotations to learn meaningful, universal features that can be conveniently transferred to solve a wide variety of downstream supervised tasks. In…

The vehicle re-identification (ReID) plays a critical role in the perception system of autonomous driving, which attracts more and more attention in recent years. However, to our best knowledge, there is no existing complete solution for…

Vehicle re-identification (V-reID) has become significantly popular in the community due to its applications and research significance. In particular, the V-reID is an important problem that still faces numerous open challenges. This paper…

Feed-forward surround-view autonomous driving scene reconstruction offers fast, generalizable inference ability, which faces the core challenge of ensuring generalization while elevating novel view quality. Due to the surround-view with…

We present self-supervised geometric perception (SGP), the first general framework to learn a feature descriptor for correspondence matching without any ground-truth geometric model labels (e.g., camera poses, rigid transformations). Our…

Current lane detection methods are struggling with the invisibility lane issue caused by heavy shadows, severe road mark degradation, and serious vehicle occlusion. As a result, discriminative lane features can be barely learned by the…

This paper introduces a novel approach to leverage features learned from both supervised and self-supervised paradigms, to improve image classification tasks, specifically for vehicle classification. Two state-of-the-art self-supervised…