7 papers
SciFig: Towards Automating Editable Figure Generation for Scientific Papers
Siyuan Huang, Yifan Zhou, Yutong Gao +8
High-quality methodology figures are central to scientific communication, yet they remain difficult and time-consuming to create. Such figures must distill a method's components an…
AttriBE: Quantifying Attribute Expressivity in Body Embeddings for Recognition and Identification
Basudha Pal, Siyuan Huang, Anirudh Nanduri +2
Person re-identification (ReID) systems that match individuals across images or video frames are essential in many real-world applications. However, existing methods are often infl…
Cross-Spectral Body Recognition with Side Information Embedding: Benchmarks on LLCM and Analyzing Range-Induced Occlusions on IJB-MDF
Anirudh Nanduri, Siyuan Huang, Rama Chellappa
Vision Transformers (ViTs) have demonstrated impressive performance across a wide range of biometric tasks, including face and body recognition. In this work, we adapt a ViT model…
A Quantitative Evaluation of the Expressivity of BMI, Pose and Gender in Body Embeddings for Recognition and Identification
Basudha Pal, Siyuan Huang, Rama Chellappa
Person Re-identification (ReID) systems that match individuals across images or video frames are essential in many real-world applications. However, existing methods are often infl…
Multi-Domain Biometric Recognition using Body Embeddings
Anirudh Nanduri, Siyuan Huang, Rama Chellappa
Biometric recognition becomes increasingly challenging as we move away from the visible spectrum to infrared imagery, where domain discrepancies significantly impact identification…
VILLS -- Video-Image Learning to Learn Semantics for Person Re-Identification
Siyuan Huang, Ram Prabhakar, Yuxiang Guo +2
Person Re-identification is a research area with significant real world applications. Despite recent progress, existing methods face challenges in robust re-identification in the w…