Related papers: A Renaissance of Explicit Motion Information Minin…
The high computational complexity and energy consumption of artificial intelligence (AI) algorithms hinder their application in augmented reality (AR) systems. However, mobile edge computing (MEC) makes it possible to solve this problem.…
Inspired by the masked language modeling (MLM) in natural language processing tasks, the masked image modeling (MIM) has been recognized as a strong self-supervised pre-training method in computer vision. However, the high random mask ratio…
Masked video modeling~(MVM) has emerged as a highly effective pre-training strategy for visual foundation models, whereby the model reconstructs masked spatiotemporal tokens using information from visible tokens. However, a key challenge in…
Counting repetitive actions in long untrimmed videos is a challenging task that has many applications such as rehabilitation. State-of-the-art methods predict action counts by first generating a temporal self-similarity matrix (TSM) from…
We introduce the first learning-based dense matching algorithm, termed Equirectangular Projection-Oriented Dense Kernelized Feature Matching (EDM), specifically designed for omnidirectional images. Equirectangular projection (ERP) images,…
Active recognition enables robots to intelligently explore novel observations, thereby acquiring more information while circumventing undesired viewing conditions. Recent approaches favor learning policies from simulated or collected data,…
User activity sequences have emerged as one of the most important signals in recommender systems. We present a foundational model, PinFM, for understanding user activity sequences across multiple applications at a billion-scale visual…
Educational data mining (EDM) is a new growing research area and the essence of data mining concepts are used in the educational field for the purpose of extracting useful information on the behaviors of students in the learning process. In…
Motion modeling is critical in flow-based Video Frame Interpolation (VFI). Existing paradigms either consider linear combinations of bidirectional flows or directly predict bilateral flows for given timestamps without exploring favorable…
Current state-of-the-art generative models map noise to data distributions by matching flows or scores. A key limitation of these models is their inability to readily integrate available partial observations and additional priors. In…
Self-attention mechanism has been widely used for various tasks. It is designed to compute the representation of each position by a weighted sum of the features at all positions. Thus, it can capture long-range relations for computer vision…
Energy-based models (EBMs) exhibit a variety of desirable properties in predictive tasks, such as generality, simplicity and compositionality. However, training EBMs on high-dimensional datasets remains unstable and expensive. In this…
Recognition and identification of unknown targets is a crucial task in surveillance and security systems. Electronic Support Measures (ESM) are one of the most effective sensors for identification, especially for maritime and…
Deep learning models, in particular \textit{image} models, have recently gained generalisability and robustness. %are becoming more general and robust by the day. In this work, we propose to exploit such advances in the realm of…
Learned world models hold significant potential for robotic manipulation, as they can serve as simulator for real-world interactions. While extensive progress has been made in 2D video-based world models, these approaches often lack…
Turbulence mitigation (TM) is highly ill-posed due to the stochastic nature of atmospheric turbulence. Most methods rely on multiple frames recorded by conventional cameras to capture stable patterns in natural scenarios. However, they…
In this work, we propose TextIM, a novel framework for synthesizing TEXT-driven human Interactive Motions, with a focus on the precise alignment of part-level semantics. Existing methods often overlook the critical roles of interactive body…
Extreme Learning Machines (ELM) provide a fast alternative to traditional gradient-based learning in neural networks, offering rapid training and robust generalization capabilities. Its theoretical basis shows its universal approximation…
This paper introduces a robust framework for motion segmentation and egomotion estimation using event-based normal flow, tailored specifically for neuromorphic vision sensors. In contrast to traditional methods that rely heavily on optical…
The ability to estimate epistemic uncertainty is often crucial when deploying machine learning in the real world, but modern methods often produce overconfident, uncalibrated uncertainty predictions. A common approach to quantify epistemic…