IEEE transactions on pattern analysis and machine intelligence
May 5, 2022
Human motion prediction aims to generate future motions based on the observed human motions. Witnessing the success of Recurrent Neural Networks (RNN) in modeling sequential data, recent works utilize RNNs to model human-skeleton motions on the obser...
IEEE transactions on pattern analysis and machine intelligence
May 5, 2022
Modern CNN-based object detectors assign anchors for ground-truth objects under the restriction of object-anchor Intersection-over-Union (IoU). In this study, we propose a learning-to-match (LTM) method to break IoU restriction, allowing objects to m...
IEEE transactions on pattern analysis and machine intelligence
May 5, 2022
Over the last decade, deep neural networks (DNNs) are regarded as black-box methods, and their decisions are criticized for the lack of explainability. Existing attempts based on local explanations offer each input a visual saliency map, where the su...
IEEE transactions on pattern analysis and machine intelligence
May 5, 2022
This paper addresses the task of detecting and recognizing human-object interactions (HOI) in images. Considering the intrinsic complexity and structural nature of the task, we introduce a cascaded parsing network (CP-HOI) for a multi-stage, structur...
IEEE transactions on pattern analysis and machine intelligence
May 5, 2022
We present the lifted proximal operator machine (LPOM) to train fully-connected feed-forward neural networks. LPOM represents the activation function as an equivalent proximal operator and adds the proximal operators to the objective function of a ne...
IEEE transactions on pattern analysis and machine intelligence
May 5, 2022
Understanding human language is one of the key themes of artificial intelligence. For language representation, the capacity of effectively modeling the linguistic knowledge from the detail-riddled and lengthy texts and getting ride of the noises is e...
IEEE transactions on pattern analysis and machine intelligence
May 5, 2022
Recently, generative adversarial network (GAN) has shown its strong ability on modeling data distribution via adversarial learning. Cross-modal GAN, which attempts to utilize the power of GAN to model the cross-modal joint distribution and to learn c...
IEEE transactions on pattern analysis and machine intelligence
May 5, 2022
The ability to predict, anticipate and reason about future outcomes is a key component of intelligent decision-making systems. In light of the success of deep learning in computer vision, deep-learning-based video prediction emerged as a promising re...
IEEE transactions on pattern analysis and machine intelligence
May 5, 2022
In this paper, we propose a general framework termed centroid estimation with guaranteed efficiency (CEGE) for weakly supervised learning (WSL) with incomplete, inexact, and inaccurate supervision. The core of our framework is to devise an unbiased a...
IEEE transactions on pattern analysis and machine intelligence
May 5, 2022
Machine learning models have been shown to be vulnerable to adversarial examples. While most of the existing methods for adversarial attack and defense work on the 2D image domain, a few recent attempts have been made to extend them to 3D point cloud...