DualGaze-VLM uses text guidance and a new object-level dataset G-W3DA to predict driver attention, beating prior models by up to 17.8% in similarity metrics and passing human visual Turing tests at 88%.
Squeeze-and-excitation networks,
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
GDNet introduces global dynamic convolution and two-stage Mixup to outperform prior methods on SAR image change detection across three datasets.
LITE combines a 1D conv autoencoder for 50% CSI compression with an asymmetric SE-BiLSTM predictor to cut model complexity 83% and X-haul load while losing only 6% accuracy versus a full BiLSTM baseline.
HELENA delivers a smaller dual-attention neural estimator that cuts inference time by 45% and parameters by 8x versus CEViT while keeping comparable NMSE accuracy.
citing papers explorer
-
From Scene to Object: Text-Guided Dual-Gaze Prediction
DualGaze-VLM uses text guidance and a new object-level dataset G-W3DA to predict driver attention, beating prior models by up to 17.8% in similarity metrics and passing human visual Turing tests at 88%.
-
Synthetic Aperture Radar Image Change Detection Based on Global Dynamic Context-Aware Network
GDNet introduces global dynamic convolution and two-stage Mixup to outperform prior methods on SAR image change detection across three datasets.
-
LITE: Lightweight Channel Gain Estimation with Reduced X-Haul CSI Signaling in O-RAN
LITE combines a 1D conv autoencoder for 50% CSI compression with an asymmetric SE-BiLSTM predictor to cut model complexity 83% and X-haul load while losing only 6% accuracy versus a full BiLSTM baseline.
-
HELENA: High-Efficiency Learning-based channel Estimation using dual Neural Attention
HELENA delivers a smaller dual-attention neural estimator that cuts inference time by 45% and parameters by 8x versus CEViT while keeping comparable NMSE accuracy.