相关论文: PredNet and Predictive Coding: A Critical Review

Inspired by "predictive coding" - a theory in neuroscience, we develop a bi-directional and dynamic neural network with local recurrent processing, namely predictive coding network (PCN). Unlike feedforward-only convolutional neural…

Most prior motion prediction endeavors in autonomous driving have inadequately encoded future scenarios, leading to predictions that may fail to accurately capture the diverse movements of agents (e.g., vehicles or pedestrians). To address…

Close human-robot cooperation is a key enabler for new developments in advanced manufacturing and assistive applications. Close cooperation require robots that can predict human actions and intent, and understand human non-verbal cues.…

Predictive coding (PC) is an influential theory in computational neuroscience, which argues that the cortex forms unsupervised world models by implementing a hierarchical process of prediction error minimization. PC networks (PCNs) are…

The computer vision world has been re-gaining enthusiasm in various pre-trained models, including both classical ImageNet supervised pre-training and recently emerged self-supervised pre-training such as simCLR and MoCo. Pre-trained weights…

The existing internet-scale image and video datasets cover a wide range of everyday objects and tasks, bringing the potential of learning policies that generalize in diverse scenarios. Prior works have explored visual pre-training with…

Current machine learning models have shown high efficiency in solving a wide variety of real-world problems. However, their black box character poses a major challenge for the understanding and traceability of the underlying decision-making…

Dominant approaches to action detection can only provide sub-optimal solutions to the problem, as they rely on seeking frame-level detections, to later compose them into "action tubes" in a post-processing step. With this paper we radically…

Engagement estimation from face video remains challenging because facial evidence is often incomplete, labeled data are limited, and engagement annotations are subjective. We present PriorNet, a prior-guided framework that injects…

Humans learn complex latent structures from their environments (e.g., natural language, mathematics, music, social hierarchies). In cognitive science and cognitive neuroscience, models that infer higher-order structures from sensory or…

Neural networks reach state-of-the-art performance in a variety of learning tasks. However, a lack of understanding the decision making process yields to an appearance as black box. We address this and propose ConstraintNet, a neural…

Parameter fine tuning is a transfer learning approach whereby learned parameters from pre-trained source network are transferred to the target network followed by fine-tuning. Prior research has shown that this approach is capable of…

This paper proposes a novel deep reinforcement learning architecture that was inspired by previous tree structured architectures which were only useable in discrete action spaces. Policy Prediction Network offers a way to improve sample…

The objective of this work is human pose estimation in videos, where multiple frames are available. We investigate a ConvNet architecture that is able to benefit from temporal context by combining information across the multiple frames…

Action recognition is a fundamental problem in computer vision with a lot of potential applications such as video surveillance, human computer interaction, and robot learning. Given pre-segmented videos, the task is to recognize actions…

One key challenge to learning-based video compression is that motion predictive coding, a very effective tool for video compression, can hardly be trained into a neural network. In this paper we propose the concept of PixelMotionCNN (PMCNN)…

Due to the unprecedented success of deep learning, it has become an integral component in several multimedia computing applications in todays world. Unfortunately, deep learning systems are not perfect and can fail, sometimes abruptly,…

Probing classifiers have emerged as one of the prominent methodologies for interpreting and analyzing deep neural network models of natural language processing. The basic idea is simple -- a classifier is trained to predict some linguistic…

The explosive increase of multimodal data makes a great demand in many cross-modal applications that follow the strict prior related assumption. Thus researchers study the definition of cross-modal correlation category and construct various…

Continual learning requires a model to adapt to ongoing changes in the data distribution, and often to the set of tasks to be performed. It is rare, however, that the data and task changes are completely unpredictable. Given a description…