VLMs and CNNs complement each other on spectrum tasks, with CNNs strong on spatial localization and VLMs on semantic reasoning; a router combining them improves composite performance by 39% over CNN alone.
Deep residual learning for image recognition
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
method 1polarities
use method 1representative citing papers
SO-TA replaces standard attention with optimal-transport alignment across vision, force/torque, and proprioception to improve diffusion-policy performance on real-robot insertion and wiping tasks.
LPLCv2 is a larger, more annotated dataset for fine-grained license plate legibility classification with a baseline model reaching 89.5% F1-score via a new training method and camera-contamination protocol.
citing papers explorer
-
When Does Multimodal AI Help? Diagnostic Complementarity of Vision-Language Models and CNNs for Spectrum Management in Satellite-Terrestrial Networks
VLMs and CNNs complement each other on spectrum tasks, with CNNs strong on spatial localization and VLMs on semantic reasoning; a router combining them improves composite performance by 39% over CNN alone.
-
Spacetime Optimal-Transport Attention for Visuo-Haptic Imitation Learning of Contact-Rich Manipulation
SO-TA replaces standard attention with optimal-transport alignment across vision, force/torque, and proprioception to improve diffusion-policy performance on real-robot insertion and wiping tasks.
-
LPLCv2: An Expanded Dataset for Fine-Grained License Plate Legibility Classification
LPLCv2 is a larger, more annotated dataset for fine-grained license plate legibility classification with a baseline model reaching 89.5% F1-score via a new training method and camera-contamination protocol.