Related papers: Frame Shift Prediction
Pre-training of neural networks has recently revolutionized the field of Natural Language Processing (NLP) and has before demonstrated its effectiveness in computer vision. At the same time, advances around the detection of fake news were…
Cognitive processing signals can be used to improve natural language processing (NLP) tasks. However, it is not clear how these signals correlate with linguistic information. Bridging between human language processing and linguistic…
When captioning an image, people describe objects in diverse ways, such as by using different terms and/or including details that are perceptually noteworthy to them. Descriptions can be especially unique across languages and cultures.…
The task of video prediction is forecasting the next frames given some previous frames. Despite much recent progress, this task is still challenging mainly due to high nonlinearity in the spatial domain. To address this issue, we propose a…
Cross-lingual text classification aims at training a classifier on the source language and transferring the knowledge to target languages, which is very useful for low-resource languages. Recent multilingual pretrained language models…
The ability to predict and therefore to anticipate the future is an important attribute of intelligence. It is also of utmost importance in real-time systems, e.g. in robotics or autonomous driving, which depend on visual scene…
Many character-level tasks can be framed as sequence-to-sequence transduction, where the target is a word from a natural language. We show that leveraging target language models derived from unannotated target corpora, combined with a…
We propose SfM-Net, a geometry-aware neural network for motion estimation in videos that decomposes frame-to-frame pixel motion in terms of scene and object depth, camera motion and 3D object rotations and translations. Given a sequence of…
This paper argues in favor of the adoption of annotation practices for multimodal datasets that recognize and represent the inherently perspectivized nature of multimodal communication. To support our claim, we present a set of annotation…
Understanding and interacting with everyday physical scenes requires rich knowledge about the structure of the world, represented either implicitly in a value or policy function, or explicitly in a transition model. Here we introduce a new…
Media framing refers to the emphasis on specific aspects of perceived reality to shape how an issue is defined and understood. Its primary purpose is to shape public perceptions often in alignment with the authors' opinions and stances.…
The attention mechanisim is appealing for neural machine translation, since it is able to dynam- ically encode a source sentence by generating a alignment between a target word and source words. Unfortunately, it has been proved to be worse…
Visual-frame prediction is a pixel-dense prediction task that infers future frames from past frames. Lacking of appearance details, low prediction accuracy and high computational overhead are still major problems with current models or…
We propose a novel attention model that can accurately attends to target objects of various scales and shapes in images. The model is trained to gradually suppress irrelevant regions in an input image via a progressive attentive process…
We introduce a framework for designing multi-scale, adaptive, shift-invariant frames and bi-frames for representing signals. The new framework, called AdaFrame, improves over dictionary learning-based techniques in terms of computational…
The meanings and relationships of words shift over time. This phenomenon is referred to as semantic shift. Research focused on understanding how semantic shifts occur over multiple time periods is essential for gaining a detailed…
This paper introduces semantic frame forecast, a task that predicts the semantic frames that will occur in the next 10, 100, or even 1,000 sentences in a running story. Prior work focused on predicting the immediate future of a story, such…
Text detection in scenes based on deep neural networks have shown promising results. Instead of using word bounding box regression, recent state-of-the-art methods have started focusing on character bounding box and pixel-level prediction.…
Graph neural networks (GNNs) have achieved champion in wide applications. Neural message passing is a typical key module for feature propagation by aggregating neighboring features. In this work, we propose a new message passing based on…
This paper introduces a novel aligner for Abstract Meaning Representation (AMR) graphs that can scale cross-lingually, and is thus capable of aligning units and spans in sentences of different languages. Our approach leverages modern…