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

Single object tracking aims to locate one specific target in video sequences,given its initial state. Classical trackers rely solely on visual cues,restricting their ability to handle challenges such as appearance variations,ambiguity, and distractions. Hence, Vision-Language (VL) tracking has emergedas a promising approach, incorporating language descriptions to directlyprovide high-level semantics and enhance tracking performance. However, currentVL trackers have not fully exploited the power of VL learning, as they sufferfrom limitations such as heavily relying on off-the-shelf backbones for featureextraction, ineffective VL fusion designs, and the absence of VL-related lossfunctions. Consequently, we present a novel tracker that progressively explorestarget-centric semantics for VL tracking. Specifically, we propose the firstSynchronous Learning Backbone (SLB) for VL tracking, which consists of twonovel modules: the Target Enhance Module (TEM) and the Semantic Aware Module(SAM). These modules enable the tracker to perceive target-related semanticsand comprehend the context of both visual and textual modalities at the samepace, facilitating VL feature extraction and fusion at different semanticlevels. Moreover, we devise the dense matching loss to further strengthenmulti-modal representation learning. Extensive experiments on VL trackingdatasets demonstrate the superiority and effectiveness of our methods.

Beyond Visual Cues: Synchronously Exploring Target-Centric Semantics for Vision-Language Tracking