Using External Knowledge to Improve Zero-shot Action Recognition in Egocentric Videos

Zero-shot learning is a very promising research topic. For a vision-based action recognition system, for instance, zero-shot learning allows to recognise actions never seen during the training phase. Previous works in zero-shot action recognition have exploited in several ways the visual appearance of input videos to infer actions. Here, we propose to add external knowledge to improve the performance of purely vision-based systems. Specifically, we have explored three different sources of knowledge in the form of text corpora.

Teknologia, testuinguru digitala eta konpetentzia digitalak hezkuntzan

Teknologiaren garapenak ez du etenik. Badirudi hainbat motako datuen bilketa (eta hein batean jakintza) negozio bihurtu dela eta enpresa handien eta pribatuen esku nabarmen geratzen ari dela. Datuen bilketa eta garapen mota horrek gure identitate digitala (eta bestelakoa) arriskuan jar dezake eta oro har arrakala digitala areagotu egin du, eremu publikoaren edo jendartearen esku dauden aukerak eta baliabideak murrizten direlako.

A Methodology to Measure the Diachronic Language Distance between Three Languages Based on Perplexity

The aim of this paper is to apply a corpus-based methodology, based on the measure of perplexity, to automatically calculate the cross-lingual language distance between historical periods of three languages. The three historical corpora have been constructed and collected with the closest spelling to the original on a balanced basis of fiction and non-fiction.

Domain Adapted Distant Supervision for Pedagogically Motivated Relation Extraction

In this paper we present a relation extraction system that given a text extracts pedagogically motivated relation types, as a previousstep to obtaining a semantic representation of the text which will make possible to automatically generate questions for reading comprehension. The system maps pedagogically motivated relations with relations from ConceptNet and deploys Distant Supervisionfor relation extraction. We run a study on a subset of those relationships in order to analyse the viability of our approach.

Evaluating Multimodal Representations on Visual Semantic Textual Similarity

The combination of visual and textual representations has produced excellent results in tasks such as image captioning and visual question answering, but the inference capabilities of multimodal representations are largely untested.
In the case of textual representations, inference tasks such as Textual Entailment and Semantic Textual Similarity have been often used to benchmark the quality of textual representations.


Subscribe to RSS - Others