Inicio  /  Applied Sciences  /  Vol: 10 Par: 6 (2020)  /  Artículo
ARTÍCULO
TITULO

Instance Hard Triplet Loss for In-video Person Re-identification

Xing Fan    
Wei Jiang    
Hao Luo    
Weijie Mao and Hongyan Yu    

Resumen

Traditional Person Re-identification (ReID) methods mainly focus on cross-camera scenarios, while identifying a person in the same video/camera from adjacent subsequent frames is also an important question, for example, in human tracking and pose tracking. We try to address this unexplored in-video ReID problem with a new large-scale video-based ReID dataset called PoseTrack-ReID with full images available and a new network structure called ReID-Head, which can extract multi-person features efficiently in real time and can be integrated with both one-stage and two-stage human or pose detectors. A new loss function is also required to solve this new in-video problem. Hence, a triplet-based loss function with an online hard example mining designed to distinguish persons in the same video/group is proposed, called instance hard triplet loss, which can be applied in both cross-camera ReID and in-video ReID. Compared with the widely-used batch hard triplet loss, our proposed loss achieves competitive performance and saves more than 30% of the training time. We also propose an automatic reciprocal identity association method, so we can train our model in an unsupervised way, which further extends the potential applications of in-video ReID. The PoseTrack-ReID dataset and code will be publicly released.

Palabras claves

 Artículos similares

       
 
Aaron Barbosa, Elijah Pelofske, Georg Hahn and Hristo N. Djidjev    
Quantum annealers, such as the device built by D-Wave Systems, Inc., offer a way to compute solutions of NP-hard problems that can be expressed in Ising or quadratic unconstrained binary optimization (QUBO) form. Although such solutions are typically of ... ver más
Revista: Algorithms

 
Serafino Cicerone and Gabriele Di Stefano    
The mixture of data in real life exhibits structure or connection property in nature. Typical data include biological data, communication network data, image data, etc. Graphs provide a natural way to represent and analyze these types of data and their r... ver más
Revista: Algorithms

 
Luca Tonti and Alessandro Patti    
Collision between rigid three-dimensional objects is a very common modelling problem in a wide spectrum of scientific disciplines, including Computer Science and Physics. It spans from realistic animation of polyhedral shapes for computer vision to the d... ver más
Revista: Algorithms

 
Mike Nkongolo, Jacobus Philippus van Deventer and Sydney Mambwe Kasongo    
This research attempts to introduce the production methodology of an anomaly detection dataset using ten desirable requirements. Subsequently, the article presents the produced dataset named UGRansome, created with up-to-date and modern network traffic (... ver más
Revista: Information

 
Oleg A. Logachev,Sergey N. Fedorov     Pág. 33 - 38
The classic blockchain design implies the mining procedure, which is essentially reflected in the following: to add a new block to the chain, a user has to solve an instance of some moderately hard computational problem (Proof-of-Workframe... ver más