Related papers: Discriminative Video Representation Learning Using…

Multi-label multi-view action recognition aims to recognize multiple concurrent or sequential actions from untrimmed videos captured by multiple cameras. Existing work has focused on multi-view action recognition in a narrow area with…

Discriminative linear models are a popular tool in machine learning. These can be generally divided into two types: The first is linear classifiers, such as support vector machines, which are well studied and provide state-of-the-art…

Learning feature representation from discriminative local regions plays a key role in fine-grained visual classification. Employing attention mechanisms to extract part features has become a trend. However, there are two major limitations…

Diverse input data modalities can provide complementary cues for several tasks, usually leading to more robust algorithms and better performance. However, while a (training) dataset could be accurately designed to include a variety of…

Deep neural networks, albeit their great success on feature learning in various computer vision tasks, are usually considered as impractical for online visual tracking because they require very long training time and a large number of…

Recent works find that AI algorithms learn biases from data. Therefore, it is urgent and vital to identify biases in AI algorithms. However, the previous bias identification pipeline overly relies on human experts to conjecture potential…

Video captioning is the task of automatically generating a textual description of the actions in a video. Although previous work (e.g. sequence-to-sequence model) has shown promising results in abstracting a coarse description of a short…

Motivated by the previous success of Two-Dimensional Convolutional Neural Network (2D CNN) on image recognition, researchers endeavor to leverage it to characterize videos. However, one limitation of applying 2D CNN to analyze videos is…

Brain-inspired deep predictive coding networks (DPCNs) effectively model and capture video features through a bi-directional information flow, even without labels. They are based on an overcomplete description of video scenes, and one of…

Human action recognition (HAR) in videos has garnered widespread attention due to the rich information in RGB videos. Nevertheless, existing methods for extracting deep features from RGB videos face challenges such as information…

Nowadays, Deep Neural Networks are among the main tools used in various sciences. Convolutional Neural Network is a special type of DNN consisting of several convolution layers, each followed by an activation function and a pooling layer.…

Few-shot learning often involves metric learning-based classifiers, which predict the image label by comparing the distance between the extracted feature vector and class representations. However, applying global pooling in the backend of…

Deep Learning has demonstrated a significant improvement against traditional machine learning approaches in different domains such as image and speech recognition. Their success on benchmark datasets is transferred to the real-world through…

Unsupervised video class incremental learning (uVCIL) represents an important learning paradigm for learning video information without forgetting, and without considering any data labels. Prior approaches have focused on supervised…

Data pooling offers various advantages, such as increasing the sample size, improving generalization, reducing sampling bias, and addressing data sparsity and quality, but it is not straightforward and may even be counterproductive.…

Traditional discriminative computer vision relies predominantly on static projections, mapping input features to outputs in a single computational step. Although efficient, this paradigm lacks the iterative refinement and robustness…

Self-attention mechanisms model long-range context by using pairwise attention between all input tokens. In doing so, they assume a fixed attention granularity defined by the individual tokens (e.g., text characters or image pixels), which…

Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition. However, global CNN activations lack geometric invariance, which limits their robustness for classification and matching of…

Recently, Deepfake has drawn considerable public attention due to security and privacy concerns in social media digital forensics. As the wildly spreading Deepfake videos on the Internet become more realistic, traditional detection…

This paper provides a review on representation learning for videos. We classify recent spatiotemporal feature learning methods for sequential visual data and compare their pros and cons for general video analysis. Building effective…