Related papers: Self-supervised Extraction of Human Motion Structu…
Passive radio frequency (RF) sensing and monitoring of human daily activities in elderly care homes is an emerging topic. Micro-Doppler radars are an appealing solution considering their non-intrusiveness, deep penetration, and…
We propose a sparse-coding framework for activity recognition in ubiquitous and mobile computing that alleviates two fundamental problems of current supervised learning approaches. (i) It automatically derives a compact, sparse and…
Pedestrian detection methods have been significantly improved with the development of deep convolutional neural networks. Nevertheless, robustly detecting pedestrians with a large variant on sizes and with occlusions remains a challenging…
Generating long-range skeleton-based human actions has been a challenging problem since small deviations of one frame can cause a malformed action sequence. Most existing methods borrow ideas from video generation, which naively treat…
This paper proposes Attention-Seeker, an unsupervised keyphrase extraction method that leverages self-attention maps from a Large Language Model to estimate the importance of candidate phrases. Our approach identifies specific components -…
Self-supervised video correspondence learning depends on the ability to accurately associate pixels between video frames that correspond to the same visual object. However, achieving reliable pixel matching without supervision remains a…
Handwritten mathematical expression recognition is a challenging problem due to the complicated two-dimensional structures, ambiguous handwriting input and variant scales of handwritten math symbols. To settle this problem, we utilize the…
This paper introduces the use of single layer and deep convolutional networks for remote sensing data analysis. Direct application to multi- and hyper-spectral imagery of supervised (shallow or deep) convolutional networks is very…
We propose a new representation of human body motion which encodes a full motion in a sequence of latent motion primitives. Recently, task generic motion priors have been introduced and propose a coherent representation of human motion…
There have been a fairly of research interests in exploring the disentanglement of appearance and shape from human images. Most existing endeavours pursuit this goal by either using training images with annotations or regulating the…
Video Moment Retrieval (MR) and Highlight Detection (HD) aim to pinpoint specific moments and assess clip-wise relevance based on the text query. While DETR-based joint frameworks have made significant strides, there remains untapped…
Estimating geometric elements such as depth, camera motion, and optical flow from images is an important part of the robot's visual perception. We use a joint self-supervised method to estimate the three geometric elements. Depth network,…
Community detection refers to finding densely connected groups of nodes in graphs. In important applications, such as cluster analysis and network modelling, the graph is sparse but outliers and heavy-tailed noise may obscure its structure.…
Wearable sensor based human activity recognition is a challenging problem due to difficulty in modeling spatial and temporal dependencies of sensor signals. Recognition models in closed-set assumption are forced to yield members of known…
Deep neural network is an effective choice to automatically recognize human actions utilizing data from various wearable sensors. These networks automate the process of feature extraction relying completely on data. However, various noises…
We study the task of gesture recognition from electromyography (EMG), with the goal of enabling expressive human-computer interaction at high accuracy, while minimizing the time required for new subjects to provide calibration data. To…
This paper introduces an efficient and robust method for discovering interpretable circuits in large language models using discrete sparse autoencoders. Our approach addresses key limitations of existing techniques, namely computational…
Despite huge success in the image domain, modern detection models such as Faster R-CNN have not been used nearly as much for video analysis. This is arguably due to the fact that detection models are designed to operate on single frames and…
Analyzing human motion is a challenging task with a wide variety of applications in computer vision and in graphics. One such application, of particular importance in computer animation, is the retargeting of motion from one performer to…
Deep learning-based medical image segmentation technology aims at automatic recognizing and annotating objects on the medical image. Non-local attention and feature learning by multi-scale methods are widely used to model network, which…