Related papers: NeuralAnnot: Neural Annotator for 3D Human Mesh Tr…

While the use of artificial intelligence (AI) for medical image analysis is gaining wide acceptance, the expertise, time and cost required to generate annotated data in the medical field are significantly high, due to limited availability…

This work studies semantic segmentation using 3D LiDAR data. Popular deep learning methods applied for this task require a large number of manual annotations to train the parameters. We propose a new method that makes full use of the…

Deep residual networks (ResNets) and their variants are widely used in many computer vision applications and natural language processing tasks. However, the theoretical principles for designing and training ResNets are still not fully…

The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and…

Detecting 3D objects from point clouds is a practical yet challenging task that has attracted increasing attention recently. In this paper, we propose a Label-Guided auxiliary training method for 3D object detection (LG3D), which serves as…

Adversarial training is a method for enhancing neural networks to improve the robustness against adversarial examples. Besides the security concerns of potential adversarial examples, adversarial training can also improve the generalization…

3D instance segmentation is crucial for understanding complex 3D environments, yet fully supervised methods require dense point-level annotations, resulting in substantial annotation costs and labor overhead. To mitigate this, box-level…

Recent deep networks have achieved good performance on a variety of 3d points classification tasks. However, these models often face challenges in "wild tasks".There are considerable differences between the labeled training/source data…

Session-based recommendation systems suggest relevant items to users by modeling user behavior and preferences using short-term anonymous sessions. Existing methods leverage Graph Neural Networks (GNNs) that propagate and aggregate…

Graph neural networks (GNNs) have shown promising performance in solving both Boolean satisfiability (SAT) and Maximum Satisfiability (MaxSAT) problems due to their ability to efficiently model and capture the structural dependencies…

Active vision is inherently attention-driven: The agent actively selects views to attend in order to fast achieve the vision task while improving its internal representation of the scene being observed. Inspired by the recent success of…

3D object detectors are fundamental components of perception systems in autonomous vehicles. While these detectors achieve remarkable performance on standard autonomous driving benchmarks, they often struggle to generalize across different…

Online 3D multi-object tracking (MOT) has witnessed significant research interest in recent years, largely driven by demand from the autonomous systems community. However, 3D offline MOT is relatively less explored. Labeling 3D trajectory…

As the emerging trend of graph-based deep learning, Graph Neural Networks (GNNs) excel for their capability to generate high-quality node feature vectors (embeddings). However, the existing one-size-fits-all GNN implementations are…

In this paper, we investigate a novel problem of using generative adversarial networks in the task of 3D shape generation according to semantic attributes. Recent works map 3D shapes into 2D parameter domain, which enables training…

Graph neural networks (GNNs) have brought revolutionary advancements to the field of link prediction (LP), providing powerful tools for mining potential relationships in graphs. However, existing methods face challenges when dealing with…

Neural machine translation (NMT) heavily relies on an attention network to produce a context vector for each target word prediction. In practice, we find that context vectors for different target words are quite similar to one another and…

Traditional algorithms to optimize artificial neural networks when confronted with a supervised learning task are usually exploitation-type relaxational dynamics such as gradient descent (GD). Here, we explore the dynamics of the neural…

We propose a new representation for encoding 3D shapes as neural fields. The representation is designed to be compatible with the transformer architecture and to benefit both shape reconstruction and shape generation. Existing works on…

Our ability to train end-to-end systems for 3D human pose estimation from single images is currently constrained by the limited availability of 3D annotations for natural images. Most datasets are captured using Motion Capture (MoCap)…