Weakly supervised object localization and detection: A survey
As an emerging and challenging problem in the computer vision community, weakly
supervised object localization and detection plays an important role for developing new …
supervised object localization and detection plays an important role for developing new …
Consistency-based semi-supervised learning for object detection
Making a precise annotation in a large dataset is crucial to the performance of object
detection. While the object detection task requires a huge number of annotated samples to …
detection. While the object detection task requires a huge number of annotated samples to …
Attention-based dropout layer for weakly supervised object localization
Abstract Weakly Supervised Object Localization (WSOL) techniques learn the object
location only using image-level labels, without location annotations. A common limitation for …
location only using image-level labels, without location annotations. A common limitation for …
Coco-stuff: Thing and stuff classes in context
Semantic classes can be either things (objects with a well-defined shape, eg car, person) or
stuff (amorphous background regions, eg grass, sky). While lots of classification and …
stuff (amorphous background regions, eg grass, sky). While lots of classification and …
Pcl: Proposal cluster learning for weakly supervised object detection
Weakly Supervised Object Detection (WSOD), using only image-level annotations to train
object detectors, is of growing importance in object recognition. In this paper, we propose a …
object detectors, is of growing importance in object recognition. In this paper, we propose a …
Interactive self-training with mean teachers for semi-supervised object detection
The goal of semi-supervised object detection is to learn a detection model using only a few
labeled data and large amounts of unlabeled data, thereby reducing the cost of data …
labeled data and large amounts of unlabeled data, thereby reducing the cost of data …
Autoloc: Weakly-supervised temporal action localization in untrimmed videos
Abstract Temporal Action Localization (TAL) in untrimmed video is important for many
applications. But it is very expensive to annotate the segment-level ground truth (action class …
applications. But it is very expensive to annotate the segment-level ground truth (action class …
Ha-ccn: Hierarchical attention-based crowd counting network
VA Sindagi, VM Patel - IEEE Transactions on Image Processing, 2019 - ieeexplore.ieee.org
Single image-based crowd counting has recently witnessed increased focus, but many
leading methods are far from optimal, especially in highly congested scenes. In this paper …
leading methods are far from optimal, especially in highly congested scenes. In this paper …
Min-entropy latent model for weakly supervised object detection
Weakly supervised object detection is a challenging task when provided with image
category supervision but required to learn, at the same time, object locations and object …
category supervision but required to learn, at the same time, object locations and object …
Weakly supervised region proposal network and object detection
Abstract The Convolutional Neural Network (CNN) based region proposal generation
method (ie region proposal network), trained using bounding box annotations, is an …
method (ie region proposal network), trained using bounding box annotations, is an …