相关论文: Weakly-supervised Part-Attention and Mentored Netw…
Vehicle Re-identification (Re-ID) aims to retrieve the most similar image to a given query from images captured by non-overlapping cameras. Extending vehicle Re-ID from image-only queries to text-based queries enables retrieval in…
Weakly supervised image segmentation trained with image-level labels usually suffers from inaccurate coverage of object areas during the generation of the pseudo groundtruth. This is because the object activation maps are trained with the…
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…
Fine-grained object categorization aims for distinguishing objects of subordinate categories that belong to the same entry-level object category. The task is challenging due to the facts that (1) training images with ground-truth labels are…
Semi-supervised learning is a challenging problem which aims to construct a model by learning from a limited number of labeled examples. Numerous methods have been proposed to tackle this problem, with most focusing on utilizing the…
Existing view-based methods excel at recognizing 3D objects from predefined viewpoints, but their exploration of recognition under arbitrary views is limited. This is a challenging and realistic setting because each object has different…
Holistic person re-identification (ReID) has received extensive study in the past few years and achieves impressive progress. However, persons are often occluded by obstacles or other persons in practical scenarios, which makes partial…
Road crack detection is essential for intelligent infrastructure maintenance in smart cities. To reduce reliance on costly pixel-level annotations, we propose WP-CrackNet, an end-to-end weakly-supervised method that trains with only…
State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results and hardly work on unseen classes without fine-tuning. Few-shot segmentation is thus proposed to tackle this problem by learning a model…
Video Moment Retrieval (VMR) is a task to localize the temporal moment in untrimmed video specified by natural language query. For VMR, several methods that require full supervision for training have been proposed. Unfortunately, acquiring…
We present an approach to matching images of objects in fine-grained datasets without using part annotations, with an application to the challenging problem of weakly supervised single-view reconstruction. This is in contrast to prior works…
Jointly utilizing global and local features to improve model accuracy is becoming a popular approach for the person re-identification (ReID) problem, because previous works using global features alone have very limited capacity at…
Vehicle re-identification (reID) often requires recognize a target vehicle in large datasets captured from multi-cameras. It plays an important role in the automatic analysis of the increasing urban surveillance videos, which has become a…
Extracting robust feature representation is critical for object re-identification to accurately identify objects across non-overlapping cameras. Although having a strong representation ability, the Vision Transformer (ViT) tends to overfit…
Most person re-identification methods, being supervised techniques, suffer from the burden of massive annotation requirement. Unsupervised methods overcome this need for labeled data, but perform poorly compared to the supervised…
Vehicle Re-Identification (Re-ID) aims to identify the same vehicle across different cameras, hence plays an important role in modern traffic management systems. The technical challenges require the algorithms must be robust in different…
Vehicle re-identification (ReID) endeavors to associate vehicle images collected from a distributed network of cameras spanning diverse traffic environments. This task assumes paramount importance within the spectrum of vehicle-centric…
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…
Camouflaged object detection (COD) from a single image is a challenging task due to the high similarity between objects and their surroundings. Existing fully supervised methods require labor-intensive pixel-level annotations, making weakly…
In supervised learning, traditional image masking faces two key issues: (i) discarded pixels are underutilized, leading to a loss of valuable contextual information; (ii) masking may remove small or critical features, especially in…