Related papers: FinePseudo: Improving Pseudo-Labelling through Tem…
Recent advances in semi-supervised learning (SSL) demonstrate that a combination of consistency regularization and pseudo-labeling can effectively improve image classification accuracy in the low-data regime. Compared to classification,…
We evaluate the effectiveness of semi-supervised learning (SSL) on a realistic benchmark where data exhibits considerable class imbalance and contains images from novel classes. Our benchmark consists of two fine-grained classification…
Unsupervised semantic segmentation aims to obtain high-level semantic representation on low-level visual features without manual annotations. Most existing methods are bottom-up approaches that try to group pixels into regions based on…
Understanding Activities of Daily Living (ADLs) is a crucial step for different applications including assistive robots, smart homes, and healthcare. However, to date, few benchmarks and methods have focused on complex ADLs, especially…
Given the difficulty of manually annotating motion in video, the current best motion estimation methods are trained with synthetic data, and therefore struggle somewhat due to a train/test gap. Self-supervised methods hold the promise of…
Objective: Extracting PICO elements -- Participants, Intervention, Comparison, and Outcomes -- from clinical trial literature is essential for clinical evidence retrieval, appraisal, and synthesis. Existing approaches do not distinguish the…
Semantic segmentation requires pixel-level annotation, which is time-consuming. Active Learning (AL) is a promising method for reducing data annotation costs. Due to the gap between aerial and natural images, the previous AL methods are not…
This work addresses the problem of Social Activity Recognition (SAR), a critical component in real-world tasks like surveillance and assistive robotics. Unlike traditional event understanding approaches, SAR necessitates modeling individual…
Weakly-supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos using only video-level supervision. Latest WSTAL methods introduce pseudo label learning framework to bridge the gap between…
Recent progress in Temporal Action Segmentation (TAS) has increasingly relied on complex architectures, which can hinder practical deployment. We present a lightweight dual-loss training framework that improves fine-grained segmentation…
Semantic segmentation has been continuously investigated in the last ten years, and majority of the established technologies are based on supervised models. In recent years, image-level weakly supervised semantic segmentation (WSSS),…
Fine-grained action segmentation during renorrhaphy in robot-assisted partial nephrectomy requires frame-level recognition of visually similar suturing gestures with variable duration and substantial class imbalance. The SIA-RAPN benchmark…
The emergence of self-supervised learning in the field of wearables-based human activity recognition (HAR) has opened up opportunities to tackle the most pressing challenges in the field, namely to exploit unlabeled data to derive reliable…
Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A…
Human activity recognition (HAR) with wearables is one of the serviceable technologies in ubiquitous and mobile computing applications. The sliding-window scheme is widely adopted while suffering from the multi-class windows problem. As a…
Supervised learning algorithms based on Convolutional Neural Networks have become the benchmark for medical image segmentation tasks, but their effectiveness heavily relies on a large amount of labeled data. However, annotating medical…
Gait recognition is an emerging identification technology that distinguishes individuals at long distances by analyzing individual walking patterns. Traditional techniques rely heavily on large-scale labeled datasets, which incurs high…
Fine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-language navigation. Unlike global alignment, fine-grained…
Temporal sentence grounding aims to detect event timestamps described by the natural language query from given untrimmed videos. The existing fully-supervised setting achieves great results but requires expensive annotation costs; while the…
Deep learning-based fine-grained network intrusion detection systems (NIDS) enable different attacks to be responded to in a fast and targeted manner with the help of large-scale labels. However, the cost of labeling causes insufficient…