IEEE transactions on pattern analysis and machine intelligence
Jun 5, 2023
Adversarial attacks can easily fool object recognition systems based on deep neural networks (DNNs). Although many defense methods have been proposed in recent years, most of them can still be adaptively evaded. One reason for the weak adversarial ro...
IEEE transactions on pattern analysis and machine intelligence
May 8, 2023
We present JRDB, a novel egocentric dataset collected from our social mobile manipulator JackRabbot. The dataset includes 64 minutes of annotated multimodal sensor data including stereo cylindrical 360 RGB video at 15 fps, 3D point clouds from two 1...
IEEE transactions on pattern analysis and machine intelligence
May 5, 2023
In real-world applications, we often encounter multi-view learning tasks where we need to learn from multiple sources of data or use multiple sources of data to make decisions. Multi-view representation learning, which can learn a unified representat...
IEEE transactions on pattern analysis and machine intelligence
May 5, 2023
Multi-modal datasets in artificial intelligence (AI) often capture a third-person perspective, but our embodied human intelligence evolved with sensory input from the egocentric, first-person perspective. Towards embodied AI, we introduce the Egocent...
IEEE transactions on pattern analysis and machine intelligence
Apr 3, 2023
Deep learning methods are achieving ever-increasing performance on many artificial intelligence tasks. A major limitation of deep models is that they are not amenable to interpretability. This limitation can be circumvented by developing post hoc tec...
IEEE transactions on pattern analysis and machine intelligence
Dec 5, 2022
Connecting Vision and Language plays an essential role in Generative Intelligence. For this reason, large research efforts have been devoted to image captioning, i.e. describing images with syntactically and semantically meaningful sentences. Startin...
IEEE transactions on pattern analysis and machine intelligence
Dec 5, 2022
The classification of deformable protein shapes, based solely on their macromolecular surfaces, is a challenging problem in protein-protein interaction prediction and protein design. Shape classification is made difficult by the fact that proteins ar...
IEEE transactions on pattern analysis and machine intelligence
Dec 5, 2022
Predicting human motion from historical pose sequence is crucial for a machine to succeed in intelligent interactions with humans. One aspect that has been obviated so far, is the fact that how we represent the skeletal pose has a critical impact on ...
IEEE transactions on pattern analysis and machine intelligence
Nov 7, 2022
The estimation of nested functions (i.e., functions of functions) is one of the central reasons for the success and popularity of machine learning. Today, artificial neural networks are the predominant class of algorithms in this area, known as repre...
IEEE transactions on pattern analysis and machine intelligence
Nov 7, 2022
Recently, hyperbolic deep neural networks (HDNNs) have been gaining momentum as the deep representations in the hyperbolic space provide high fidelity embeddings with few dimensions, especially for data possessing hierarchical structure. Such a hyper...