相关论文: Spot What Matters: Learning Context Using Graph Co…

Context, as referred to situational factors related to the object of interest, can help infer the object's states or properties in visual recognition. As such contextual features are too diverse (across instances) to be annotated, existing…

Video salient object detection aims to find the most visually distinctive objects in a video. To explore the temporal dependencies, existing methods usually resort to recurrent neural networks or optical flow. However, these approaches…

Most of computer vision focuses on what is in an image. We propose to train a standalone object-centric context representation to perform the opposite task: seeing what is not there. Given an image, our context model can predict where…

Motivated by the success of data-driven convolutional neural networks (CNNs) in object recognition on static images, researchers are working hard towards developing CNN equivalents for learning video features. However, learning video…

Temporal Action Detection (TAD), the task of localizing and classifying actions in untrimmed video, remains challenging due to action overlaps and variable action durations. Recent findings suggest that TAD performance is dependent on the…

The understanding of where humans look in a scene is a problem of great interest in visual perception and computer vision. When eye-tracking devices are not a viable option, models of human attention can be used to predict fixations. In…

Performing data augmentation for learning deep neural networks is known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves…

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…

Graph few-shot learning, which aims to classify nodes from novel classes with only a few labeled examples, is a widely studied problem in graph learning. However, existing methods often face two key limitations. First, the predominant graph…

In this paper, we present a framework that jointly retrieves and spatiotemporally highlights actions in videos by enhancing current deep cross-modal retrieval methods. Our work takes on the novel task of action highlighting, which…

In-context learning based on attention models is examined for data with categorical outcomes, with inference in such models viewed from the perspective of functional gradient descent (GD). We develop a network composed of attention blocks,…

In skeleton-based action recognition, Graph Convolutional Networks model human skeletal joints as vertices and connect them through an adjacency matrix, which can be seen as a local attention mask. However, in most existing Graph…

This research mainly emphasizes on traffic detection thus essentially involving object detection and classification. The particular work discussed here is motivated from unsatisfactory attempts of re-using well known pre-trained object…

We explore the power of spatial context as a self-supervisory signal for learning visual representations. In particular, we propose spatial context networks that learn to predict a representation of one image patch from another image patch,…

Video action recognition, a critical problem in video understanding, has been gaining increasing attention. To identify actions induced by complex object-object interactions, we need to consider not only spatial relations among objects in a…

The paper addresses the problem of recognition of actions in video with low inter-class variability such as Table Tennis strokes. Two stream, "twin" convolutional neural networks are used with 3D convolutions both on RGB data and optical…

The problem of determining whether an object is in motion, irrespective of camera motion, is far from being solved. We address this challenging task by learning motion patterns in videos. The core of our approach is a fully convolutional…

Context matters! Nevertheless, there has not been much research in exploiting contextual information in deep neural networks. For most part, the entire usage of contextual information has been limited to recurrent neural networks. Attention…

Videos are more well-organized curated data sources for visual concept learning than images. Unlike the 2-dimensional images which only involve the spatial information, the additional temporal dimension bridges and synchronizes multiple…

Weakly-supervised temporal action localization is a problem of learning an action localization model with only video-level action labeling available. The general framework largely relies on the classification activation, which employs an…