V-Nutri fuses final-dish features with cooking-process keyframes from egocentric videos to improve dish-level calorie and macronutrient estimation over single-image baselines.
Deep residual learning for image recognition
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
AnchorSplat uses anchor-aligned 3D Gaussians guided by geometric priors for feed-forward scene reconstruction, achieving SOTA novel view synthesis on ScanNet++ with fewer primitives and better view consistency.
Cine-DL uses targeted k-space preprocessing and an unrolled ResNet-based network to reconstruct motion-robust free-breathing radial cardiac cine MRI, outperforming k-t SENSE and iGRASP in volunteer and patient data.
ST-GD adapts Grounding DINO with about 10 million trainable parameters via adapters and a temporal decoder to achieve competitive performance on limited-data spatio-temporal video grounding benchmarks.
citing papers explorer
-
V-Nutri: Dish-Level Nutrition Estimation from Egocentric Cooking Videos
V-Nutri fuses final-dish features with cooking-process keyframes from egocentric videos to improve dish-level calorie and macronutrient estimation over single-image baselines.
-
AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors
AnchorSplat uses anchor-aligned 3D Gaussians guided by geometric priors for feed-forward scene reconstruction, achieving SOTA novel view synthesis on ScanNet++ with fewer primitives and better view consistency.
-
Motion-Robust Deep Reconstruction for Free-Breathing Cardiac Cine MRI
Cine-DL uses targeted k-space preprocessing and an unrolled ResNet-based network to reconstruct motion-robust free-breathing radial cardiac cine MRI, outperforming k-t SENSE and iGRASP in volunteer and patient data.
-
Unlocking the Potential of Grounding DINO in Videos: Parameter-Efficient Adaptation for Limited-Data Spatial-Temporal Localization
ST-GD adapts Grounding DINO with about 10 million trainable parameters via adapters and a temporal decoder to achieve competitive performance on limited-data spatio-temporal video grounding benchmarks.