YouTube2Text: Recognizing and Describing Arbitrary Activities Using Semantic Hierarchies and Zero-Shot Recognition

Citations Over TimeTop 1% of 2013 papers

Abstract

Despite a recent push towards large-scale object recognition, activity recognition remains limited to narrow domains and small vocabularies of actions. In this paper, we tackle the challenge of recognizing and describing activities ``in-the-wild''. We present a solution that takes a short video clip and outputs a brief sentence that sums up the main activity in the video, such as the actor, the action and its object. Unlike previous work, our approach works on out-of-domain actions: it does not require training videos of the exact activity. If it cannot find an accurate prediction for a pre-trained model, it finds a less specific answer that is also plausible from a pragmatic standpoint. We use semantic hierarchies learned from the data to help to choose an appropriate level of generalization, and priors learned from Web-scale natural language corpora to penalize unlikely combinations of actors/actions/objects, we also use a Web-scale language model to ``fill in'' novel verbs, i.e. when the verb does not appear in the training set. We evaluate our method on a large YouTube corpus and demonstrate it is able to generate short sentence descriptions of video clips better than baseline approaches.

Related Papers

• → Accounting for baseline targets in NDCs(2018)3 cited
• Method for Improvement of Baseline Resolving Quality in GPS Measurement(2007)
• Analysis of the Baseline Decorrelation and Critical Baseline of Interferometric SAR(2003)
• Research of Baseline Implement(2010)
• Study and application of telecom operators system security state baseline(2012)