Showing 2025Show all
2 papers · 1 filter
cs.CV2025
StegaVAR: Privacy-Preserving Video Action Recognition via Steganographic Domain Analysis
Lixin Chen, Chaomeng Chen, Jiale Zhou +2
Despite the rapid progress of deep learning in video action recognition (VAR) in recent years, privacy leakage in videos remains a critical concern. Current state-of-the-art privac…
cs.CL2025
SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression
Biao Zhang, Lixin Chen, Tong Liu +1
Large language models (LLMs) generate high-dimensional embeddings that capture rich semantic and syntactic information. However, high-dimensional embeddings exacerbate computationa…