Related papers: Temporal and Object Quantification Networks

We propose Token Turing Machines (TTM), a sequential, autoregressive Transformer model with memory for real-world sequential visual understanding. Our model is inspired by the seminal Neural Turing Machine, and has an external memory…

Temporal sentence grounding (TSG) aims to localize the temporal segment which is semantically aligned with a natural language query in an untrimmed video.Most existing methods extract frame-grained features or object-grained features by 3D…

Modern object detectors can rarely achieve short training time, fast inference speed, and high accuracy at the same time. To strike a balance among them, we propose the Training-Time-Friendly Network (TTFNet). In this work, we start with…

Many real-world complex systems, such as epidemic spreading networks and ecosystems, can be modeled as networked dynamical systems that produce multivariate time series. Learning the intrinsic dynamics from observational data is pivotal for…

A temporal point process (TPP) is a stochastic process where its realization is a sequence of discrete events in time. Recent work in TPPs model the process using a neural network in a supervised learning framework, where a training set is…

In this paper, we propose a neuro-symbolic framework called weighted Signal Temporal Logic Neural Network (wSTL-NN) that combines the characteristics of neural networks and temporal logics. Weighted Signal Temporal Logic (wSTL) formulas are…

Video semantic segmentation requires to utilize the complex temporal relations between frames of the video sequence. Previous works usually exploit accurate optical flow to leverage the temporal relations, which suffer much from heavy…

We introduce a new neural architecture and an unsupervised algorithm for learning invariant representations from temporal sequence of images. The system uses two groups of complex cells whose outputs are combined multiplicatively: one that…

Molecular representation learning methods typically tokenize molecules as individual atoms or use rigid, rule-based fragment decompositions, limiting their ability to capture meaningful chemical substructure context. We introduce…

We propose a new deep convolutional neural network framework that uses object location knowledge implicit in network connection weights to guide selective attention in object detection tasks. Our approach is called What-Where Nets…

For a long time, the vision community tries to learn the spatio-temporal representation by combining convolutional neural network together with various temporal models, such as the families of Markov chain, optical flow, RNN and temporal…

Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise.…

Networks constitute efficient tools for assessing universal features of complex systems. In physical contexts, classical as well as quantum, networks are used to describe a wide range of phenomena, such as phase transitions, intricate…

Operating deep neural networks (DNNs) on devices with limited resources requires the reduction of their memory as well as computational footprint. Popular reduction methods are network quantization or pruning, which either reduce the word…

Time series are often complex and rich in information but sparsely labeled and therefore challenging to model. In this paper, we propose a self-supervised framework for learning generalizable representations for non-stationary time series.…

Time series models aim for accurate predictions of the future given the past, where the forecasts are used for important downstream tasks like business decision making. In practice, deep learning based time series models come in many forms,…

With the development of feed-forward models, the default model for sequence modeling has gradually evolved to replace recurrent networks. Many powerful feed-forward models based on convolutional networks and attention mechanism were…

Sequence modeling has demonstrated state-of-the-art performance on natural language and document understanding tasks. However, it is challenging to correctly serialize tokens in form-like documents in practice due to their variety of layout…

Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components,…

Recent research on temporal networks has highlighted the limitations of a static network perspective for our understanding of complex systems with dynamic topologies. In particular, recent works have shown that i) the specific order in…