Related papers: Combined CNN Transformer Encoder for Enhanced Fine…

The Transformer architecture has gained significant popularity in computer vision tasks due to its capacity to generalize and capture long-range dependencies. This characteristic makes it well-suited for generating spatiotemporal tokens…

Latent fingerprint identification remains a challenging task due to low image quality, background noise, and partial impressions. In this work, we propose a novel identification approach called LatentPrintFormer. The proposed model…

Our objective in this work is fine-grained classification of actions in untrimmed videos, where the actions may be temporally extended or may span only a few frames of the video. We cast this into a query-response mechanism, where each…

Multi-modal approaches employ data from multiple input streams such as textual and visual domains. Deep neural networks have been successfully employed for these approaches. In this paper, we present a novel multi-modal approach that fuses…

Despite the fact that notable improvements have been made recently in the field of feature extraction and classification, human action recognition is still challenging, especially in images, in which, unlike videos, there is no motion.…

Recently, deep learning methods have achieved state-of-the-art performance in many medical image segmentation tasks. Many of these are based on convolutional neural networks (CNNs). For such methods, the encoder is the key part for global…

Deep learning techniques are being used in skeleton based action recognition tasks and outstanding performance has been reported. Compared with RNN based methods which tend to overemphasize temporal information, CNN-based approaches can…

It remains a challenge to efficiently extract spatialtemporal information from skeleton sequences for 3D human action recognition. Although most recent action recognition methods are based on Recurrent Neural Networks which present…

The discriminative power of modern deep learning models for 3D human action recognition is growing ever so potent. In conjunction with the recent resurgence of 3D human action representation with 3D skeletons, the quality and the pace of…

Despite the evolution of deep-learning-based visual-textual processing systems, precise multi-modal matching remains a challenging task. In this work, we tackle the task of cross-modal retrieval through image-sentence matching based on…

Image captioning by the encoder-decoder framework has shown tremendous advancement in the last decade where CNN is mainly used as encoder and LSTM is used as a decoder. Despite such an impressive achievement in terms of accuracy in simple…

Recognizing fine-grained actions from temporally corrupted skeleton sequences remains a significant challenge, particularly in real-world scenarios where online pose estimation often yields substantial missing data. Existing methods often…

Many previous methods have demonstrated the importance of considering semantically relevant objects for carrying out video-based human activity recognition, yet none of the methods have harvested the power of large text corpora to relate…

Fingerspelling in sign language has been the means of communicating technical terms and proper nouns when they do not have dedicated sign language gestures. Automatic recognition of fingerspelling can help resolve communication barriers…

Robots operating in human-centered environments, such as retail stores, restaurants, and households, are often required to distinguish between similar objects in different contexts with a high degree of accuracy. However, fine-grained…

With the advancement of remote-sensed imaging large volumes of very high resolution land cover images can now be obtained. Automation of object recognition in these 2D images, however, is still a key issue. High intra-class variance and low…

In recent years, representation learning approaches have disrupted many multimedia computing tasks. Among those approaches, deep convolutional neural networks (CNNs) have notably reached human level expertise on some constrained image…

Semantic segmentation assigns labels to pixels in images, a critical yet challenging task in computer vision. Convolutional methods, although capturing local dependencies well, struggle with long-range relationships. Vision Transformers…

Accurate classification of fine-grained images remains a challenge in backbones based on convolutional operations or self-attention mechanisms. This study proposes novel dual-current neural networks (DCNN), which combine the advantages of…

Due to its widespread applications, human action recognition is one of the most widely studied research problems in Computer Vision. Recent studies have shown that addressing it using multimodal data leads to superior performance as…