conftrace_

text-guided compression

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

image-text attention (1) video token (1) cross-modal query (1) dinov2 features (1) inter-frame dependencies (1) spatiotemporal adaptive compression (1) learned image compression (1) semantic guidance (1) image-text fusion (1) semantic consistency (1)

Papers

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding ICML 2025 Multi-Modality Deep Network for Extreme Learned Image Compression AAAI 2023