Search
Search Results
-
Human re-identification by local maximal occurrence of color and scale-Invariant Channel integrated statistical pattern
Feature representation and metric learning are the two major components in human re-identification. An effective feature representation has to be...
-
Species-Agnostic Patterned Animal Re-identification by Aggregating Deep Local Features
Access to large image volumes through camera traps and crowdsourcing provides novel possibilities for animal monitoring and conservation. It calls...
-
Pattern-Expandable Image Copy Detection
Open-world visual recognition aims to empower models to identify objects in real-world settings, particularly when they encounter domains or...
-
Sequential Pattern Mining by Pattern-Growth: Principles and Extensions*
Sequential pattern mining is an important data mining problem with broad applications. However, it is also a challenging problem since the mining may...
-
Hierarchical U-net with re-parameterization technique for spatio-temporal weather forecasting
Due to the considerable computational demands of physics-based numerical weather prediction, especially when modeling fine-grained spatio-temporal...
-
Re-HGNM: a repeat aware hypergraph neural machine for session-based recommendation
Hypergraph neural network (HGNN) for session-based recommendation (SBR) is quite rare but has been rewarded with promising performance. However,...
-
Agile model-driven re-engineering
In this paper we describe an Agile model-driven engineering (MDE) approach, AMDRE, for the re-engineering of legacy systems. The objective is to...
-
RefinerHash: a new hashing-based re-ranking technique for image retrieval
Re-ranking is a task of refining an initially ranked list of images obtained from an image retrieval technique for a given query image, with the goal...
-
Pyramid-resolution person restoration for cross-resolution person re-identification
In this study, we present a simple yet effective pyramid-resolution person restoration method for cross-resolution person re-identification. Our...
-
Dual-attentive cascade clustering learning for visible-infrared person re-identification
Visible-infrared person re-identification (VI Re-ID) is challenging work due to huge inter-modality discrepancies and high similarity among...
-
Research on person re-identification based on multi-level attention model
Person Re-identification (ReID) is an important research direction in the field of pattern recognition, which aims to retrieve the same pedestrian in...
-
Weight Re-map** for Variational Quantum Algorithms
Inspired by the remarkable success of artificial neural networks across a broad spectrum of AI tasks, variational quantum circuits (VQCs) have...
-
Person re-identification using soft biometrics
Pedestrian characteristics like bags, gender, clothes, or short hair might affect in identifying people in video surveillance. Due to variation in...
-
Loose–tight cluster regularization for unsupervised person re-identification
Unsupervised person re-identification (Re-ID) is a critical and challenging task in computer vision. It aims to identify the same person across...
-
Learning discriminative local contexts for person re-identification in vehicle surveillance scenarios
In recent years, person re-identification (Re-ID) has been widely used in intelligent surveillance and security. However, Re-ID faces many challenges...
-
Joint training with local soft attention and dual cross-neighbor label smoothing for unsupervised person re-identification
Existing unsupervised person re-identification approaches fail to fully capture the fine-grained features of local regions, which can result in...
-
Staged encoder training for cross-camera person re-identification
As a cross-camera retrieval problem, person re-identification (ReID) suffers from image style variations caused by camera parameters, lighting and...
-
Unsupervised Person Re-identification Using Unified Domanial Learning
Recent deep learning-based person re-identification (RE-ID) approaches mainly adopt supervised learning, by which the network is trained with labels...
-
Injecting the score of the first-stage retriever as text improves BERT-based re-rankers
In this paper we propose a novel approach for combining first-stage lexical retrieval models and Transformer-based re-rankers: we inject the...
-
Aging Contrast: A Contrastive Learning Framework for Fish Re-identification Across Seasons and Years
The fields of biology, ecology, and fisheries management are witnessing a growing demand for distinguishing individual fish. In recent years, deep...