Related papers: FinePseudo: Improving Pseudo-Labelling through Tem…

Visual place recognition (VPR) using deep networks has achieved state-of-the-art performance. However, most of them require a training set with ground truth sensor poses to obtain positive and negative samples of each observation's spatial…

We introduce Action Discovery, a novel setup within Temporal Action Segmentation that addresses the challenge of defining and annotating ambiguous actions and incomplete annotations in partially labeled datasets. In this setup, only a…

Semi-supervised learning has attracted much attention in medical image segmentation due to challenges in acquiring pixel-wise image annotations, which is a crucial step for building high-performance deep learning methods. Most existing…

Real-world videos contain many complex actions with inherent relationships between action classes. In this work, we propose an attention-based architecture that models these action relationships for the task of temporal action localization…

The growing popularity of online sports and exercise necessitates effective methods for evaluating the quality of online exercise executions. Previous action quality assessment methods, which relied on labeled scores from motion videos,…

In this paper, we propose a novel graph-based approach for semi-supervised learning problems, which considers an adaptive adjacency of the examples throughout the unsupervised portion of the training. Adjacency of the examples is inferred…

Joint segmentation and classification of fine-grained actions is important for applications of human-robot interaction, video surveillance, and human skill evaluation. However, despite substantial recent progress in large-scale action…

In this work, we propose an approach to the spatiotemporal localisation (detection) and classification of multiple concurrent actions within temporally untrimmed videos. Our framework is composed of three stages. In stage 1, appearance and…

We tackle the problem of localizing temporal intervals of actions with only a single frame label for each action instance for training. Owing to label sparsity, existing work fails to learn action completeness, resulting in fragmentary…

Automated Human Activity Recognition has long been a problem of great interest in human-centered and ubiquitous computing. In the last years, a plethora of supervised learning algorithms based on deep neural networks has been suggested to…

In this paper we present a three-stream algorithm for real-time action recognition and a new dataset of handwash videos, with the intent of aligning action recognition with real-world constraints to yield effective conclusions. A…

Semantic segmentation is an important technique for environment perception in intelligent transportation systems. With the rapid development of convolutional neural networks (CNNs), road scene analysis can usually achieve satisfactory…

Learning generalized representations from limited training samples is crucial for applying deep neural networks in low-resource scenarios. Recently, methods based on Contrastive Language-Image Pre-training (CLIP) have exhibited promising…

Contrastive Language-Image Pre-training (CLIP) excels in multimodal tasks such as image-text retrieval and zero-shot classification but struggles with fine-grained understanding due to its focus on coarse-grained short captions. To address…

Skeleton-based action recognition has attracted much attention, benefiting from its succinctness and robustness. However, the minimal inter-class variation in similar action sequences often leads to confusion. The inherent spatiotemporal…

Detection of anomalous events in videos is an important problem in applications such as surveillance. Video anomaly detection (VAD) is well-studied in the one-class classification (OCC) and weakly supervised (WS) settings. However, fully…

Current approaches for fine-grained recognition do the following: First, recruit experts to annotate a dataset of images, optionally also collecting more structured data in the form of part annotations and bounding boxes. Second, train a…

Unsupervised visible-infrared person re-identification (USL-VI-ReID) seeks to match pedestrian images of the same individual across different modalities without human annotations for model learning. Previous methods unify pseudo-labels of…

Fine-grained image recognition is a longstanding computer vision challenge that focuses on differentiating objects belonging to multiple subordinate categories within the same meta-category. Since images belonging to the same meta-category…

Fine-grained image recognition (FGIR) aims to distinguish visually similar sub-categories within a broader class, such as identifying bird species. While most existing FGIR methods rely on backbones pretrained on large-scale datasets like…