Publications

Filter by type:

. Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs. CVPR, 2024.

. Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning. CVPR (Highlight), 2023.

PDF ArXiv

. Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles. ICML (Oral), 2023.

Code ArXiv

. A Unified Model for Tracking and Image-Video Object Detection. Under Review, 2023.

PDF ArXiv

. Universal Pyramid Adversarial Training for Improved ViT Performance. Under Review, 2023.

PDF

. Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding. ICCVW, 2023.

PDF ArXiv

. Robustness and Generalization via Generative Adversarial Training. ICCV, 2021.

PDF Slides Arxiv Supp

. Coupling Explicit and Implicit Surface Representations for Generative 3D Modeling. ECCV, 2020.

PDF Slides Video Arxiv Supp

. Interpolative AutoEncoders for Unsupervised Few-Shot Image Generation. ICLR, 2020.

PDF Supp arXiv

. Self-supervised Learning of Point Clouds via Orientation Estimation. 3DV, 2020.

PDF Code Slides Video Arxiv

. Neural Puppet: Generative Layered Cartoon Characters. WACV, 2019.

PDF Poster Slides ArXiv Supp

. Differential Privacy has Disparate Impact on Model Accuracy. NeurIPS, 2019.

PDF Code Poster

. Deep Fundamental Matrix Estimation without Correspondences. ECCV, 2018.

PDF Code Slides ArXiv Poster

. Generative Adversarial Perturbations. CVPR, 2018.

PDF Code Slides ArXiv Poster Supp

. Stacked Generative Adversarial Networks. CVPR, 2017.

PDF Code Poster Slides ArXiv

. Vision Based Real Estate Price Estimation. Machine Vision and Applications, 2017.

PDF Dataset ArXiv Supp