Related papers: The ACTIONFINDER: An unsupervised deep learning al…

Summarizing video content is an important task in many applications. This task can be defined as the computation of the ordered list of actions present in a video. Such a list could be extracted using action detection algorithms. However,…

Human Activity Recognition (HAR) has recently witnessed advancements with Transformer-based models. Especially, ActionFormer shows us a new perspectives for HAR in the sense that this approach gives us additional outputs which detect the…

Deep learning models have achieved state-of-the- art performance in recognizing human activities, but often rely on utilizing background cues present in typical computer vision datasets that predominantly have a stationary camera. If these…

Accurate shape reconstruction of transparent objects is a challenging task due to their non-Lambertian surfaces and yet necessary for robots for accurate pose perception and safe manipulation. As vision-based sensing can produce erroneous…

Self-attention based Transformer models have demonstrated impressive results for image classification and object detection, and more recently for video understanding. Inspired by this success, we investigate the application of Transformer…

In this work, we propose an approach to the spatiotemporal localisation (detection) and classification of multiple concurrent actions within temporally untrimmed videos. Our framework is composed of three stages. In stage 1, appearance and…

We propose an automatic system for organizing the content of a collection of unstructured videos of an articulated object class (e.g. tiger, horse). By exploiting the recurring motion patterns of the class across videos, our system: 1)…

We have designed a powerful new algorithm to detect stellar streams in an automated and systematic way. The algorithm, which we call the STREAMFINDER, is well suited for finding dynamically cold and thin stream structures that may lie along…

Action-angle coordinates are an essential tool for understanding the properties of the six dimensional phase space involved in orbits of stars in galactic potentials. A new method, which does not require specific knowledge of a generating…

This paper proposes a novel multi-modal transformer network for detecting actions in untrimmed videos. To enrich the action features, our transformer network utilizes a new multi-modal attention mechanism that computes the correlations…

Current state-of-the-art approaches for spatio-temporal action localization rely on detections at the frame level that are then linked or tracked across time. In this paper, we leverage the temporal continuity of videos instead of operating…

Action recognition is an important yet challenging task in computer vision. In this paper, we propose a novel deep-based framework for action recognition, which improves the recognition accuracy by: 1) deriving more precise features for…

The existing action tubelet detectors often depend on heuristic anchor design and placement, which might be computationally expensive and sub-optimal for precise localization. In this paper, we present a conceptually simple, computationally…

Action recognition has long been a fundamental and intriguing problem in artificial intelligence. The task is challenging due to the high dimensionality nature of an action, as well as the subtle motion details to be considered. Current…

Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure.…

Action repetition counting is to estimate the occurrence times of the repetitive motion in one action, which is a relatively new, important but challenging measurement problem. To solve this problem, we propose a new method superior to the…

We propose DeepExplorer, a simple and lightweight metric-free exploration method for topological mapping of unknown environments. It performs task and motion planning (TAMP) entirely in image feature space. The task planner is a recurrent…

The goal of motion tomography is to recover a description of a vector flow field using information on the trajectory of a sensing unit. In this paper, we develop a predictor corrector algorithm designed to recover vector flow fields from…

Tactile exploration plays a crucial role in understanding object structures for fundamental robotics tasks such as grasping and manipulation. However, efficiently exploring such objects using tactile sensors is challenging, primarily due to…

A general relation is derived for the action difference between two fixed points and a phase space area bounded by the irreducible component of a heteroclinic tangle. The determination of this area can require accurate calculation of…