相关论文: SemiMultiPose: A Semi-supervised Multi-animal Pose…

Human pose estimation is a fundamental and challenging task in computer vision. Larger-scale and more accurate keypoint annotations, while helpful for improving the accuracy of supervised pose estimation, are often expensive and difficult…

Automatic emotion recognition is an active research topic with wide range of applications. Due to the high manual annotation cost and inevitable label ambiguity, the development of emotion recognition dataset is limited in both scale and…

Learning algorithms normally assume that there is at most one annotation or label per data point. However, in some scenarios, such as medical diagnosis and on-line collaboration,multiple annotations may be available. In either case,…

Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant. However, as the acquisition of ground-truth 3D labels is labor intensive and time consuming, recent attention has shifted…

For human pose estimation in still images, this paper proposes three semi- and weakly-supervised learning schemes. While recent advances of convolutional neural networks improve human pose estimation using supervised training data, our…

Semi-supervised pose estimation is a practically challenging task for computer vision. Although numerous excellent semi-supervised classification methods have emerged, these methods typically use confidence to evaluate the quality of…

Animal pose estimation (APE) aims to locate the animal body parts using a diverse array of sensor and modality inputs (e.g. RGB cameras, LiDAR, infrared, IMU, acoustic and language cues), which is crucial for research across neuroscience,…

Wildlife camera trap images are being used extensively to investigate animal abundance, habitat associations, and behavior, which is complicated by the fact that experts must first classify the images manually. Artificial intelligence…

This paper presents a semi-supervised learning framework to train a keypoint detector using multiview image streams given the limited labeled data (typically $<$4\%). We leverage the complementary relationship between multiview geometry and…

Supervised learning in large discriminative models is a mainstay for modern computer vision. Such an approach necessitates investing in large-scale human-annotated datasets for achieving state-of-the-art results. In turn, the efficacy of…

In semantic segmentation, the creation of pixel-level labels for training data incurs significant costs. To address this problem, semi-supervised learning, which utilizes a small number of labeled images alongside unlabeled images to…

Due to abundance of data from multiple modalities, cross-modal retrieval tasks with image-text, audio-image, etc. are gaining increasing importance. Of the different approaches proposed, supervised methods usually give significant…

RGB-based 3D pose estimation methods have been successful with the development of deep learning and the emergence of high-quality 3D pose datasets. However, most existing methods do not operate well for testing images whose distribution is…

In this paper, we study the task of 3D human pose estimation in the wild. This task is challenging due to lack of training data, as existing datasets are either in the wild images with 2D pose or in the lab images with 3D pose. We propose a…

Physiological and behavioral data collected from wearable or mobile sensors have been used to estimate self-reported stress levels. Since the stress annotation usually relies on self-reports during the study, a limited amount of labeled…

Identifying individual animals in long-duration videos is essential for behavioral ecology, wildlife monitoring, and livestock management. Traditional methods require extensive manual annotation, while existing self-supervised approaches…

Deep learning demands a huge amount of well-labeled data to train the network parameters. How to use the least amount of labeled data to obtain the desired classification accuracy is of great practical significance, because for many…

To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like…

We present two techniques to improve landmark localization in images from partially annotated datasets. Our primary goal is to leverage the common situation where precise landmark locations are only provided for a small data subset, but…

Recent advancements in semi-supervised deep learning have introduced effective strategies for leveraging both labeled and unlabeled data to improve classification performance. This work proposes a semi-supervised framework that utilizes a…