相关论文: LORTSAR: Low-Rank Transformer for Skeleton-based A…

A critical object detection task is finetuning an existing model to detect novel objects, but the standard workflow requires bounding box annotations which are time-consuming and expensive to collect. Weakly supervised object detection…

Recognizing actions from a limited set of labeled videos remains a challenge as annotating visual data is not only tedious but also can be expensive due to classified nature. Moreover, handling spatio-temporal data using deep $3$D…

Recent technological advancements have significantly expanded the potential of human action recognition through harnessing the power of 3D data. This data provides a richer understanding of actions, including depth information that enables…

Recognizing an activity with a single reference sample using metric learning approaches is a promising research field. The majority of few-shot methods focus on object recognition or face-identification. We propose a metric learning…

Skeleton-based action recognition is vital for comprehending human-centric videos and has applications in diverse domains. One of the challenges of skeleton-based action recognition is dealing with low-quality data, such as skeletons that…

Skeleton-based human action recognition has been drawing more interest recently due to its low sensitivity to appearance changes and the accessibility of more skeleton data. However, even the 3D skeletons captured in practice are still…

In this paper we propose novel methods for completion (from limited samples) and de-noising of multilinear (tensor) data and as an application consider 3-D and 4- D (color) video data completion and de-noising. We exploit the recently…

LoFTR arXiv:2104.00680 is an efficient deep learning method for finding appropriate local feature matches on image pairs. This paper reports on the optimization of this method to work on devices with low computational performance and…

Human skeleton information is important in skeleton-based action recognition, which provides a simple and efficient way to describe human pose. However, existing skeleton-based methods focus more on the skeleton, ignoring the objects…

The target of space-time video super-resolution (STVSR) is to increase the spatial-temporal resolution of low-resolution (LR) and low frame rate (LFR) videos. Recent approaches based on deep learning have made significant improvements, but…

Recent improvements in the performance of state-of-the-art (SOTA) methods for Graph Representational Learning (GRL) have come at the cost of significant computational resource requirements for training, e.g., for calculating gradients via…

Deep learning methods, in particular, trained Convolutional Neural Networks (CNN) have recently been shown to produce compelling results for single image Super-Resolution (SR). Invariably, a CNN is learned to map the Low Resolution (LR)…

In analyzing and assessing the condition of dynamical systems, it is necessary to account for nonlinearity. Recent advances in computation have rendered previously computationally infeasible analyses readily executable on common computer…

In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Overlooking this difference, many 3D detectors directly follow the common…

Distributions measured in high energy physics experiments are usually distorted and/or transformed by various detector effects. A regularization method for unfolding these distributions is re-formulated in terms of the Singular Value…

Patient-specific bone models are essential for designing surgical guides and preoperative planning, as they enable the visualization of intricate anatomical structures. However, traditional CT-based approaches for creating bone models are…

A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix. This matrix is decomposed into a product of…

Face recognition and identification is a very important application in machine learning. Due to the increasing amount of available data, traditional approaches based on matricization and matrix PCA methods can be difficult to implement.…

By representing documents as mixtures of topics, topic modeling has allowed the successful analysis of datasets across a wide spectrum of applications ranging from ecology to genetics. An important body of recent work has demonstrated the…

Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments. Low-rank Adaptation…