English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we study the problem of weakly-supervised temporal groundingof sentence in video. Specifically, given an untrimmed video and a querysentence, our goal is to localize a temporal segment in the video thatsemantically corresponds to the query sentence, with no reliance on anytemporal annotation during training. We propose a two-stage model to tacklethis problem in a coarse-to-fine manner. In the coarse stage, we first generatea set of fixed-length temporal proposals using multi-scale sliding windows, andmatch their visual features against the sentence features to identify thebest-matched proposal as a coarse grounding result. In the fine stage, weperform a fine-grained matching between the visual features of the frames inthe best-matched proposal and the sentence features to locate the precise frameboundary of the fine grounding result. Comprehensive experiments on theActivityNet Captions dataset and the Charades-STA dataset demonstrate that ourtwo-stage model achieves compelling performance.

Look Closer to Ground Better: Weakly-Supervised Temporal Grounding of Sentence in Video