Related papers: DTG-Net: Differentiated Teachers Guided Self-Super…
Learning to recognize actions from only a handful of labeled videos is a challenging problem due to the scarcity of tediously collected activity labels. We approach this problem by learning a two-pathway temporal contrastive model using…
Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark…
Affective Behavior Analysis is an important part in human-computer interaction. Existing multi-task affective behavior recognition methods suffer from the problem of incomplete labeled datasets. To tackle this problem, this paper presents a…
Scribble-supervised methods have emerged to mitigate the prohibitive annotation burden in medical image segmentation. However, the inherent sparsity of these annotations introduces significant ambiguity, which results in noisy pseudo-label…
The exploration of video content via Self-Supervised Learning (SSL) models has unveiled a dynamic field of study, emphasizing both the complex challenges and unique opportunities inherent in this area. Despite the growing body of research,…
This study focuses on a novel task in text-to-image (T2I) generation, namely action customization. The objective of this task is to learn the co-existing action from limited data and generalize it to unseen humans or even animals.…
This paper addresses the problem of real-time action recognition in trimmed videos, for which deep neural networks have defined the state-of-the-art performance in the recent literature. For attaining higher recognition accuracies with…
Training a small student network with the guidance of a larger teacher network is an effective way to promote the performance of the student. Despite the different types, the guided knowledge used to distill is always kept unchanged for…
Video Temporal Grounding (VTG), which aims to ground target clips from videos (such as consecutive intervals or disjoint shots) according to custom language queries (e.g., sentences or words), is key for video browsing on social media. Most…
Human action recognition in dark videos is a challenging task for computer vision. Recent research focuses on applying dark enhancement methods to improve the visibility of the video. However, such video processing results in the loss of…
Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…
Current 3D semi-supervised segmentation methods face significant challenges such as limited consideration of contextual information and the inability to generate reliable pseudo-labels for effective unsupervised data use. To address these…
Recent advances in self-supervised learning (SSL) have largely closed the gap with supervised ImageNet pretraining. Despite their success these methods have been primarily applied to unlabeled ImageNet images, and show marginal gains when…
Action recognition, early prediction, and online action detection are complementary disciplines that are often studied independently. Most online action detection networks use a pre-trained feature extractor, which might not be optimal for…
Self-supervised learning (SSL) has revolutionized visual representation learning, but has not achieved the robustness of human vision. A reason for this could be that SSL does not leverage all the data available to humans during learning.…
Deep learning on graphs has attracted significant interests recently. However, most of the works have focused on (semi-) supervised learning, resulting in shortcomings including heavy label reliance, poor generalization, and weak…
Wildlife re-identification aims to match individuals of the same species across different observations. Current state-of-the-art (SOTA) models rely on class labels to train supervised models for individual classification. This dependence on…
Deep learning has achieved great success in recognizing video actions, but the collection and annotation of training data are still quite laborious, which mainly lies in two aspects: (1) the amount of required annotated data is large; (2)…
The remarkable performance gains realized by large pretrained models, e.g., GPT-3, hinge on the massive amounts of data they are exposed to during training. Analogously, distilling such large models to compact models for efficient…
Semi-supervised learning (SSL) has been proposed to leverage unlabeled data for training powerful models when only limited labeled data is available. While existing SSL methods assume that samples in the labeled and unlabeled data share the…