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

We propose an effective two-stage approach to tackle the problem oflanguage-based Human-centric Spatio-Temporal Video Grounding (HC-STVG) task. Inthe first stage, we propose an Augmented 2D Temporal Adjacent Network(Augmented 2D-TAN) to temporally ground the target moment corresponding to thegiven description. Primarily, we improve the original 2D-TAN from two aspects:First, a temporal context-aware Bi-LSTM Aggregation Module is developed toaggregate clip-level representations, replacing the original max-pooling.Second, we propose to employ Random Concatenation Augmentation (RCA) mechanismduring the training phase. In the second stage, we use pretrained MDETR modelto generate per-frame bounding boxes via language query, and design a set ofhand-crafted rules to select the best matching bounding box outputted by MDETRfor each frame within the grounded moment.

Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding