Related papers: Semi-Structured Object Sequence Encoders
Large-scale sound recognition data sets typically consist of acoustic recordings obtained from multimedia libraries. As a consequence, modalities other than audio can often be exploited to improve the outputs of models designed for…
Recently, Space-Time Memory Network (STM) based methods have achieved state-of-the-art performance in semi-supervised video object segmentation (VOS). A crucial problem in this task is how to model the dependency both among different frames…
Despite the wide variety of input types in machine learning, this diversity is often not fully reflected in their representations or model architectures, leading to inefficiencies throughout a model's lifecycle. This paper introduces an…
The task of learning to map an input set onto a permuted sequence of its elements is challenging for neural networks. Set-to-sequence problems occur in natural language processing, computer vision and structure prediction, where…
The ability to perceive and reason about individual objects and their interactions is a goal to be achieved for building intelligent artificial systems. State-of-the-art approaches use a feedforward encoder to extract object embeddings and…
We describe and analyze a simple and effective algorithm for sequence segmentation applied to speech processing tasks. We propose a neural architecture that is composed of two modules trained jointly: a recurrent neural network (RNN) module…
We propose a novel solution for semi-supervised video object segmentation. By the nature of the problem, available cues (e.g. video frame(s) with object masks) become richer with the intermediate predictions. However, the existing methods…
We present a novel approach to answering sequential questions based on structured objects such as knowledge bases or tables without using a logical form as an intermediate representation. We encode tables as graphs using a graph neural…
The neural architectures of language models are becoming increasingly complex, especially that of Transformers, based on the attention mechanism. Although their application to numerous natural language processing tasks has proven to be very…
This work presents an innovative method for point set self-embedding, that encodes the structural information of a dense point set into its sparser version in a visual but imperceptible form. The self-embedded point set can function as the…
Multiplex networks are complex graph structures in which a set of entities are connected to each other via multiple types of relations, each relation representing a distinct layer. Such graphs are used to investigate many complex…
For many structured learning tasks, the data annotation process is complex and costly. Existing annotation schemes usually aim at acquiring completely annotated structures, under the common perception that partial structures are of low…
We propose a new visual hierarchical representation paradigm for multi-object tracking. It is more effective to discriminate between objects by attending to objects' compositional visual regions and contrasting with the background…
This paper presents a new network architecture called multi-head decoder for end-to-end speech recognition as an extension of a multi-head attention model. In the multi-head attention model, multiple attentions are calculated, and then,…
For most of the attention-based sequence-to-sequence models, the decoder predicts the output sequence conditioned on the entire input sequence processed by the encoder. The asynchronous problem between the encoding and decoding makes these…
In contrast to regular (simple) networks, hyper networks possess the ability to depict more complex relationships among nodes and store extensive information. Such networks are commonly found in real-world applications, such as in social…
There is mounting evidence that existing neural network models, in particular the very popular sequence-to-sequence architecture, struggle to systematically generalize to unseen compositions of seen components. We demonstrate that one of…
Current approaches for predicting sets from feature vectors ignore the unordered nature of sets and suffer from discontinuity issues as a result. We propose a general model for predicting sets that properly respects the structure of sets…
Transcribing structured data into natural language descriptions has emerged as a challenging task, referred to as "data-to-text". These structures generally regroup multiple elements, as well as their attributes. Most attempts rely on…
Encoder-decoder models offer substantial inference-time savings over decoder-only models, but their pretraining objectives suffer from sparse supervision and dynamic sequence lengths, keeping them out of practice at scale. We propose…