Abstract: Zero-shot skeleton-based action recognition aims to classify unseen skeleton-based human actions without prior exposure to such categories during training. This task is extremely challenging ...
Semantic Entity Alignment and Non-Corresponding Reasoning for Text-to-Image Person Re-identification
Abstract: With the rapid development of intelligent surveillance technology, the massive amount of multimodal data (e.g., videos, images, and text) has imposed higher demands on efficient information ...
A powerful, production-ready Streamlit web application for comprehensive LLM response evaluation and benchmarking. Features multi-dimensional scoring across 7 key criteria, interactive analytics ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results