Search Results for author:
Found 7 papers, 2 papers with code
Location-free Human Pose Estimation
We reformulate the regression-based HPE from the perspective of classification.
Alleviating Human-level Shift : A Robust Domain Adaptation Method for Multi-person Pose Estimation
Therefore, we propose a novel domain adaptation method for multi-person pose estimation to conduct the human-level topological structure alignment and fine-grained feature alignment.
Multi-Person Pose Estimation with Enhanced Feature Aggregation and Selection
More specifically, a Feature Aggregation and Selection Module (FASM), which constructs hierarchical multi-scale feature aggregation and makes the aggregated features discriminative, is proposed to get more accurate fine-grained representation, leading to more precise joint locations.
Object Discovery From a Single Unlabeled Image by Mining Frequent Itemset With Multi-scale Features
To tackle this problem, we propose a simple but effective pattern mining-based method, called Object Location Mining (OLM), which exploits the advantages of data mining and feature representation of pre-trained convolutional neural networks (CNNs).
Unsupervised Part Mining for Fine-grained Image Classification
To tackle this issue, we propose a fully unsupervised part mining (UPM) approach to localize the discriminative parts without even image-level annotations, which largely improves the fine-grained classification performance.
Effects of Image Degradations to CNN-based Image Classification
In this paper, we empirically study this problem for four kinds of degraded images -- hazy images, underwater images, motion-blurred images and fish-eye images.
Does Haze Removal Help CNN-based Image Classification?
Typically, the goal of image dehazing is to produce clearer images from which human vision can better identify the object and structural details present in the images.
