A Prior-Guided Part Aggregator (PGA) is designed, which leverages the foreground prior provided by foundation models to guide discriminative part discovery, enhancing target region responses while suppressing background interference, and a Topology-Informed Semantic Graph Convolutional Network (TIS-GCN) is designed to...
This work proposes a novel Multimodal-Guided Self-Distillation (MGSD) method for Unified Person Search that leverages multimodal textual descriptions and self-distillation to enhance pedestrian representation learning, and introduces three key innovations.
This work proposes CLIP-SGI, a semantic-guided and instance-consistent framework for generalizable person ReID that combines semantic guidance, domain-aware representation learning, and instance consistency to improve robustness under domain shifts.
Passage-based top-view person re-identification aims to match individuals across short overhead walking videos. This privacy-preserving setting is challenging because overhead cameras suppress facial and body-part cues, compress pedestrian appearance, and make models vulnerable to scene shortcuts from floors, ramps, an...
This work proposes FineHOI, a zero-shot HOI framework that explicitly models interactions from dense patch-level features, and introduces an Adaptive Part-Level Attention module that decomposes humans and objects into semantically coherent parts via unsupervised clustering, and re-weights them based on their interactio...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
