As an emerging and challenging problem in the computer vision community, weakly
supervised object localization and detection plays an important role for developing new …

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 …

Abstract Weakly Supervised Object Localization (WSOL) techniques learn the object
location only using image-level labels, without location annotations. A common limitation for …

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 …

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 …

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 …

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 …

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 …

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 …

Abstract The Convolutional Neural Network (CNN) based region proposal generation
method (ie region proposal network), trained using bounding box annotations, is an …