Attribute Recognition from Adaptive Parts
نویسندگان
چکیده
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 learning approach to overcome the limitation. It generates object parts from key points and perform attribute recognition accordingly, allowing adaptive spatial transform [10] of the parts. Both key point estimation and attribute recognition are learnt jointly in a multi-task setting. Extensive experiments on two datasets verify the efficacy of proposed end-to-end approach.
منابع مشابه
A Richly Annotated Dataset for Pedestrian Attribute Recognition
In this paper, we aim to improve the dataset foundation for pedestrian attribute recognition in real surveillance scenarios. Recognition of human attributes, such as gender, and clothes types, has great prospects in real applications. However, the development of suitable benchmark datasets for attribute recognition remains lagged behind. Existing human attribute datasets are collected from vari...
متن کاملHuman attribute recognition by refining attention heat map
Most existing methods of human attribute recognition are part-based, where features are extracted at human body parts corresponding to each human attribute and the part-based features are then fed to classifiers individually or together for recognizing human attributes. The performance of these methods is highly dependent on the accuracy of body-part detection, which is a well known challenging...
متن کاملReal Time Implementation of a License Plate Location Recognition System Based on Adaptive Morphology
License plate recognition (LPR) by using morphology has the advantage of resistance to brightness changes; high speed processing, and low complexity. However these approaches are sensitive to the distance of the plate from the camera and imaging angle. Various assumptions reported in other works might be unrealistic and cause major problems in practical experiences. In this paper we considered ...
متن کاملAn Optimized Part Based Gait Recognition using Multi- Objective Particle Swarm Optimization
Gait identification task becomes difficult due to the change of appearance by different cofactors (e.g., shoe, surface, carrying, view, and clothing). Some parts of gait are affected by cofactors and other parts remains unaffected. Most of the gait identification systems consider only most effective parts thereby omitting less effective parts. However some significant features for gait identifi...
متن کاملSeismic Data Forecasting: A Sequence Prediction or a Sequence Recognition Task
In this paper, we have tried to predict earthquake events in a cluster of seismic data on pacific ring of fire, using multivariate adaptive regression splines (MARS). The model is employed as either a predictor for a sequence prediction task, or a binary classifier for a sequence recognition problem, which could alternatively help to predict an event. Here, we explain that sequence prediction/r...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1607.01437 شماره
صفحات -
تاریخ انتشار 2016