Temporal Sentence Grounding in Streaming Videos
This addresses the problem of real-time video analysis for applications like surveillance and live-stream analysis, though it is incremental as it builds on existing temporal grounding tasks by adapting to streaming contexts.
The paper tackles the novel task of Temporal Sentence Grounding in Streaming Videos (TSGSV), which involves evaluating the relevance between a video stream and a sentence query without access to future frames, and proposes methods like TwinNet and a language-guided feature compressor to address challenges such as processing long historical frames effectively, achieving superior results on datasets like ActivityNet Captions, TACoS, and MAD.
This paper aims to tackle a novel task - Temporal Sentence Grounding in Streaming Videos (TSGSV). The goal of TSGSV is to evaluate the relevance between a video stream and a given sentence query. Unlike regular videos, streaming videos are acquired continuously from a particular source, and are always desired to be processed on-the-fly in many applications such as surveillance and live-stream analysis. Thus, TSGSV is challenging since it requires the model to infer without future frames and process long historical frames effectively, which is untouched in the early methods. To specifically address the above challenges, we propose two novel methods: (1) a TwinNet structure that enables the model to learn about upcoming events; and (2) a language-guided feature compressor that eliminates redundant visual frames and reinforces the frames that are relevant to the query. We conduct extensive experiments using ActivityNet Captions, TACoS, and MAD datasets. The results demonstrate the superiority of our proposed methods. A systematic ablation study also confirms their effectiveness.