Related papers: DoGCLR: Dominance-Game Contrastive Learning Networ…
Heterogeneous graph neural network (HGNN) is a very popular technique for the modeling and analysis of heterogeneous graphs. Most existing HGNN-based approaches are supervised or semi-supervised learning methods requiring graphs to be…
Reinforcement learning (RL) has made significant progress in various domains, but scaling it to long-horizon tasks with complex decision-making remains challenging. Skill learning attempts to address this by abstracting actions into…
Human action understanding serves as a foundational pillar in the field of intelligent motion perception. Skeletons serve as a modality- and device-agnostic representation for human modeling, and skeleton-based action understanding has…
Self-supervised visual representation learning aims to learn useful representations without relying on human annotations. Joint embedding approach bases on maximizing the agreement between embedding vectors from different views of the same…
Existing deep learning-based cross-view geo-localization methods primarily focus on improving the accuracy of cross-domain image matching, rather than enabling models to comprehensively capture contextual information around the target and…
Recently, there has been a remarkable increase in the interest towards skeleton-based action recognition within the research community, owing to its various advantageous features, including computational efficiency, representative features,…
Amari's Dynamic Neural Field (DNF) framework provides a brain-inspired approach to modeling the average activation of neuronal groups. Leveraging a single field, DNF has become a promising foundation for low-energy looming perception module…
The computer vision community is currently focusing on solving action recognition problems in real videos, which contain thousands of samples with many challenges. In this process, Deep Convolutional Neural Networks (D-CNNs) have played a…
Deep clustering has shown its promising capability in joint representation learning and clustering via deep neural networks. Despite the significant progress, the existing deep clustering works mostly utilize some distribution-based…
Contrastive learning (CL) is one of the most successful paradigms for self-supervised learning (SSL). In a principled way, it considers two augmented "views" of the same image as positive to be pulled closer, and all other images as…
Previous multimodal sentence representation learning methods have achieved impressive performance. However, most approaches focus on aligning images and text at a coarse level, facing two critical challenges:cross-modal misalignment bias…
Action recognition has been heavily employed in many applications such as autonomous vehicles, surveillance, etc, where its robustness is a primary concern. In this paper, we examine the robustness of state-of-the-art action recognizers…
We propose ADCLR: A ccurate and D ense Contrastive Representation Learning, a novel self-supervised learning framework for learning accurate and dense vision representation. To extract spatial-sensitive information, ADCLR introduces query…
Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this…
Neural networks have revolutionized various domains, exhibiting remarkable accuracy in tasks like natural language processing and computer vision. However, their vulnerability to slight alterations in input samples poses challenges,…
Skeleton-based action recognition is an important task that requires the adequate understanding of movement characteristics of a human action from the given skeleton sequence. Recent studies have shown that exploring spatial and temporal…
Self-supervised methods have shown tremendous success in the field of computer vision, including applications in remote sensing and medical imaging. Most popular contrastive-loss based methods like SimCLR, MoCo, MoCo-v2 use multiple views…
For years, adversarial training has been extensively studied in natural language processing (NLP) settings. The main goal is to make models robust so that similar inputs derive in semantically similar outcomes, which is not a trivial…
Many real-world decisions are made under uncertainty by solving optimization problems using predicted quantities. This predict-then-optimize paradigm has motivated decision-focused learning, which trains models with awareness of how the…
Graph Convolutional Networks (GCNs) have been widely used in skeleton-based human action recognition. In GCN-based methods, the spatio-temporal graph is fundamental for capturing motion patterns. However, existing approaches ignore the…