Prototypical Contrastive Learning (PCL) combines clustering with contrastive loss, improving low-resource transfer by encoding semantic structures.

Junnan Li, Pan Zhou, Caiming Xiong et al.

CoReNet achieves multi-object 3D scene reconstruction from a single RGB image, improving accuracy.

Stefan Popov, Pablo Bauszat, Vittorio Ferrari

RTCnet fuses target features with local 3D radar-cube data, achieving 0.70 target-level and 0.56 object-level F1.

Andras Palffy, Jiaao Dong, Julian F. P. Kooij et al.

Proposes a CNN-GRU based deepfake detection method achieving top 6% on DFDC with 0.321 log-likelihood error.

Daniel Mas Montserrat, Hanxiang Hao, S. K. Yarlagadda et al.

Proposes a single-view MPI prediction framework with scale-invariant view synthesis, achieving high-quality novel view rendering and depth estimation.

Richard Tucker, Noah Snavely

Shortcut learning in deep learning affects model generalization in complex scenarios.

Robert Geirhos, Jörn-Henrik Jacobsen, Claudio Michaelis et al.

DISTS combines structure and texture similarity, improving robustness to texture resampling and geometric transformations in image quality assessment.

Keyan Ding, Kede Ma, Shiqi Wang et al.

TVOS propagates labels through long-range spatiotemporal embeddings, reaching 72.3 J&F on DAVIS 2017 validation at 37 FPS.

Yizhuo Zhang, Zhirong Wu, Houwen Peng et al.

Proposes a PointNet+GCN-based method for regressing 3D semantic scene graphs, introducing the large-scale 3DSSG dataset with rich relations.

Johanna Wald, Helisa Dhamo, Nassir Navab et al.

Introduced VLN-CE in continuous 3D environments, using low-level actions and attention models, achieving 33% success rate over 55 steps, highlighting real-world challenges.

Jacob Krantz, Erik Wijmans, Arjun Majumdar et al.

Guiding monocular depth estimation using Depth-Attention Volume, achieving state-of-the-art on NYU-Depth-v2.

Lam Huynh, Phong Nguyen-Ha, Jiri Matas et al.

Introduces affine skip connections in GNNs, inspired by RBF interpolation, improving shape reconstruction and classification with 8% error reduction.

Shunwang Gong, Mehdi Bahri, Michael M. Bronstein et al.

Proposed Anisotropic Convolutional Network (AIC-Net) improves 3D semantic scene completion accuracy on NYU-Depth-v2.

Jie Li, Kai Han, Peng Wang et al.

PointGroup achieves 63.6% mAP50 on ScanNet v2 using dual-set clustering for 3D instance segmentation.

Li Jiang, Hengshuang Zhao, Shaoshuai Shi et al.

Physics-based NLOS 3D human pose estimation from transient photon histograms, leveraging deep reinforcement learning and learnable PSF for robust performance.

Mariko Isogawa, Ye Yuan, Matthew O'Toole et al.

Proposed 3D Sketch-aware Semantic Scene Completion method improves SSC task performance by 7.8% on NYU dataset.

Xiaokang Chen, Kwan-Yee Lin, Chen Qian et al.

Open-source TensorFlow tool supports hyperspectral image augmentation with 13 channels, boosting remote sensing model accuracy.

Mohamed Abdelhack

Introduced TextCaps dataset with 145k captions for 28k images, integrating OCR and visual reasoning for advanced image captioning.

Oleksii Sidorov, Ronghang Hu, Marcus Rohrbach et al.

SAPIEN environment integrates PhysX and PartNet-Mobility, enabling detailed part-level interaction and perception tasks for household robots, advancing realism and diversity.

Fanbo Xiang, Yuzhe Qin, Kaichun Mo et al.

Axial-DeepLab uses axial-attention to outperform existing models on ImageNet, improving COCO test set by 2.8% PQ.

Huiyu Wang, Yukun Zhu, Bradley Green et al.