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

Early weakly supervised video grounding (WSVG) methods often struggle withincomplete boundary detection due to the absence of temporal boundaryannotations. To bridge the gap between video-level and boundary-levelannotation, explicit-supervision methods, i.e., generating pseudo-temporalboundaries for training, have achieved great success. However, dataaugmentations in these methods might disrupt critical temporal information,yielding poor pseudo boundaries. In this paper, we propose a new perspectivethat maintains the integrity of the original temporal content while introducingmore valuable information for expanding the incomplete boundaries. To this end,we propose EtC (Expand then Clarify), first use the additional information toexpand the initial incomplete pseudo boundaries, and subsequently refine theseexpanded ones to achieve precise boundaries. Motivated by video continuity,i.e., visual similarity across adjacent frames, we use powerful multimodallarge language models (MLLMs) to annotate each frame within initial pseudoboundaries, yielding more comprehensive descriptions for expanded boundaries.To further clarify the noise of expanded boundaries, we combine mutual learningwith a tailored proposal-level contrastive objective to use a learnableapproach to harmonize a balance between incomplete yet clean (initial) andcomprehensive yet noisy (expanded) boundaries for more precise ones.Experiments demonstrate the superiority of our method on two challenging WSVGdatasets.

EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model