相关论文: Learnable Motion Coherence for Correspondence Prun…

The prediction of saliency areas in images has been traditionally addressed with hand crafted features based on neuroscience principles. This paper however addresses the problem with a completely data-driven approach by training a…

We propose an entirely new meta-learning framework for network pruning. It is a general framework that can be theoretically applied to almost all types of networks with all kinds of pruning and has great generality and transferability.…

We present a method for identifying the coherent structures associated with individual Lagrangian flow trajectories even where only sparse particle trajectory data is available. The method, based on techniques in spectral graph theory, uses…

Trajectory similarity computation is fundamental functionality that is used for, e.g., clustering, prediction, and anomaly detection. However, existing learning-based methods exhibit three key limitations: (1) insufficient modeling of…

Semantic understanding of 3D objects is crucial in many applications such as object manipulation. However, it is hard to give a universal definition of point-level semantics that everyone would agree on. We observe that people have a…

Existing pruning methods for large language models (LLMs) focus on achieving high compression rates while maintaining model performance. Although these methods have demonstrated satisfactory performance in handling a single user's…

This paper proposes a new end-to-end trainable matching network based on receptive field, RF-Net, to compute sparse correspondence between images. Building end-to-end trainable matching framework is desirable and challenging. The very…

Recovering 3D human pose from 2D joints is a highly unconstrained problem. We propose a novel neural network framework, PoseNet3D, that takes 2D joints as input and outputs 3D skeletons and SMPL body model parameters. By casting our…

The computation and memory needed for Convolutional Neural Network (CNN) inference can be reduced by pruning weights from the trained network. Pruning is guided by a pruning saliency, which heuristically approximates the change in the loss…

Let us rethink the real-world scenarios that require human motion prediction techniques, such as human-robot collaboration. Current works simplify the task of predicting human motions into a one-off process of forecasting a short future…

We introduce and study methods for inferring and learning from correspondences among neurons. The approach enables alignment of data from distinct multiunit studies of nervous systems. We show that the methods for inferring correspondences…

In recent years, neural networks have continued to flourish, achieving high efficiency in detecting relevant objects in photos or simply recognizing (classifying) these objects - mainly using CNN networks. Current solutions, however, are…

In this paper, we present a method to utilize 2D-2D point matches between images taken during different image conditions to train a convolutional neural network for semantic segmentation. Enforcing label consistency across the matches makes…

In this paper, we show that there is a close relation between consistency in a constraint network and set intersection. A proof schema is provided as a generic way to obtain consistency properties from properties on set intersection. This…

The message passing-based graph neural networks (GNNs) have achieved great success in many real-world applications. However, training GNNs on large-scale graphs suffers from the well-known neighbor explosion problem, i.e., the exponentially…

Computing the relative motion of objects is an important navigation task that we routinely perform by relying on inherently unreliable biological cells in the retina. The non-linear and adaptive response of memristive devices make them…

Some self-supervised cross-modal learning approaches have recently demonstrated the potential of image signals for enhancing point cloud representation. However, it remains a question on how to directly model cross-modal local and global…

Recent advances in geometric deep-learning introduce complex computational challenges for evaluating the distance between meshes. From a mesh model, point clouds are necessary along with a robust distance metric to assess surface quality or…

This paper tackles the problem of human motion prediction, consisting in forecasting future body poses from historically observed sequences. State-of-the-art approaches provide good results, however, they rely on deep learning architectures…

Advanced manipulation techniques have provided criminals with opportunities to make social panic or gain illicit profits through the generation of deceptive media, such as forged face images. In response, various deepfake detection methods…