相关论文: AAformer: Auto-Aligned Transformer for Person Re-I…

This is a short technical report introducing the solution of the Team TCParser for Short-video Face Parsing Track of The 3rd Person in Context (PIC) Workshop and Challenge at CVPR 2021. In this paper, we introduce a strong backbone which is…

Transformer has achieved great success in computer vision, while how to split patches in an image remains a problem. Existing methods usually use a fixed-size patch embedding which might destroy the semantics of objects. To address this…

Amodal Instance Segmentation (AIS) aims to segment the region of both visible and possible occluded parts of an object instance. While Mask R-CNN-based AIS approaches have shown promising results, they are unable to model high-level…

Deep part-based methods in recent literature have revealed the great potential of learning local part-level representation for pedestrian image in the task of person re-identification. However, global features that capture discriminative…

Previous part-based attribute recognition approaches perform part detection and attribute recognition in separate steps. The parts are not optimized for attribute recognition and therefore could be sub-optimal. We present an end-to-end deep…

Multi-class cell nuclei detection is a fundamental prerequisite in the diagnosis of histopathology. It is critical to efficiently locate and identify cells with diverse morphology and distributions in digital pathological images. Most…

Accurate segmentation of critical anatomical structures is at the core of medical image analysis. The main bottleneck lies in gathering the requisite expert-labeled image annotations in a scalable manner. Methods that permit to produce…

Reversibility in artificial neural networks allows us to retrieve the input given an output. We present feature alignment, a method for approximating reversibility in arbitrary neural networks. We train a network by minimizing the distance…

A recent approach for object detection and human pose estimation is to regress bounding boxes or human keypoints from a central point on the object or person. While this center-point regression is simple and efficient, we argue that the…

Although facial landmark detection (FLD) has gained significant progress, existing FLD methods still suffer from performance drops on partially non-visible faces, such as faces with occlusions or under extreme lighting conditions or poses.…

Occluded person re-identification (ReID) aims to match occluded person images to holistic ones across dis-joint cameras. In this paper, we propose a novel framework by learning high-order relation and topology information for discriminative…

Given a pedestrian image as a query, the purpose of person re-identification is to identify the correct match from a large collection of gallery images depicting the same person captured by disjoint camera views. The critical challenge is…

Person search aims to simultaneously localize and identify a query person from realistic, uncropped images, which can be regarded as the unified task of pedestrian detection and person re-identification (re-id). Most existing works employ…

In video person re-identification (Re-ID), the network must consistently extract features of the target person from successive frames. Existing methods tend to focus only on how to use temporal information, which often leads to networks…

This research proposes a novel adjustable algorithm for reconstructing 3D body shapes from front and side silhouettes. Most recent silhouette-based approaches use a deep neural network trained by silhouettes and key points to estimate the…

Deformation component analysis is a fundamental problem in geometry processing and shape understanding. Existing approaches mainly extract deformation components in local regions at a similar scale while deformations of real-world objects…

In person re-identification (re-ID), the key task is feature representation, which is used to compute distance or similarity in prediction. Person re-ID achieves great improvement when deep learning methods are introduced to tackle this…

Recent efforts have shown promising results for person re-identification by designing part-based architectures to allow a neural network to learn discriminative representations from semantically coherent parts. Some efforts use soft…

Human interaction recognition is very important in many applications. One crucial cue in recognizing an interaction is the interactive body parts. In this work, we propose a novel Interaction Graph Transformer (IGFormer) network for…

The person re-identification (Re-ID) task requires to robustly extract feature representations for person images. Recently, part-based representation models have been widely studied for extracting the more compact and robust feature…