OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer
arXiv:2604.24762
[PDF] [Project Website] [Source code] [Demo]
Keywords: shot boundary detection, video understanding
Publications
Preprints
Empowering Dynamic Urban Navigation with Stereo and Mid-Level Vision
arXiv:2512.10956
[PDF] [Project Website] [Source code]
Keywords: mid-level vision, robot navigation
2026
WildRayZer: Self-supervised Large View Synthesis in Dynamic Environments
Computer Vision and Pattern Recognition (CVPR), 2026. (highlight)
[PDF] [Project Website] [Dataset] [Source code] [Demo]
Keywords: self-supervised learning, 3D understanding
Point-MoE: Towards Cross-Domain Generalization in 3D Semantic Segmentation via Mixture-of-Experts
The International Conference on Learning Representations (ICLR) 2026
[PDF] [Project Website] [Source code]
Keywords: 3D understanding
Semantic-Free Procedural 3D Shapes Are Surprisingly Good Teachers
International Conference on 3D Vision (3DV) 2026
[PDF] [Project Website] [Dataset] [Source code]
Keywords: Self-supervised learning, 3D representation learning
Open Vocabulary Monocular 3D Object Detection
International Conference on 3D Vision (3DV) 2026
[PDF] [Project Website] [Source code]
Keywords: 3D recognition
2025
Frame In-N-Out: Unbounded Controllable Image-to-Video Generation
Conference on Neural Information Processing Systems (NeurIPS) 2025
[PDF] [Project Website] [Source code] [Demo]
Keywords: Controllable video generation
LabelAny3D: Label Any Object 3D in the Wild
Conference on Neural Information Processing Systems (NeurIPS) 2025
[PDF] [Project Website] [Source code] [3D Annotation Tool]
Keywords: 3D understanding
Probing the Mid-level Vision Capabilities of Self-Supervised Learning
Computer Vision and Pattern Recognition (CVPR), 2025
[PDF] [Project Website] [Source code]
Keywords: Self-supervised learning, 3D representation learning
SAB3R: Semantic-Augmented Backbone in 3D Reconstruction
3D-LLM/VLA Workshop @ CVPR 2025
[PDF] [Project Website] [Source code]
Keywords: 3D understanding
E-BARF: Bundle Adjusting Neural Radiance Fields from a Moving Event Camera
Event-based Vision @ CVPR 2025
[PDF]
Keywords: 3D understanding
2024
Using spatio-temporal information in weather radar data to detect and track communal bird roosts
Remote Sensing in Ecology and Conservation, 2024
[PDF] [Source code]
Keywords: radar ecology, spatio-temporal tracking
2023
LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs
IEEE International Conference on Computer Vision (ICCV), 2023
[PDF] [Project Website]
Keywords: NeRF, 3D reconstruction, camera pose
Accidental Turntables: Learning 3D Pose by Watching Objects Turn
ICCV Workshop on Recovering 6D Object Pose, 2023
[PDF] [Project Website] [Poster]
Keywords: 3D pose, video understanding
ZeoNet: 3D convolutional neural networks for predicting adsorption in nanoporous zeolites
Journal of Materials Chemistry A, 2023
[PDF] [Project Website]
Keywords: 3D convolution, materials science
A Semi-Automated System to Annotate Communal Roosts in Large-Scale Weather Radar Data
NeurIPS 2023 Computational Sustainability: Pitfalls and Promises from Theory to Deployment
[PDF] [Project Website]
Keywords: radar ecology, annotation systems
2022
Cross-Modal 3D Shape Generation and Manipulation
European Conference on Computer Vision (ECCV), 2022
[PDF] [Source code] [Project Website] [Poster] [Video]
Keywords: 3D generation, cross-modal learning
Long-term analysis of persistence and size of swallow and martin roosts in the US Great Lakes
Remote Sensing in Ecology and Conservation, 2022
[PDF]
Keywords: radar ecology, long-term monitoring
Quantifying Long-term Phenological Patterns of Aerial Insectivores Roosting in the Great Lakes Region using Weather Surveillance Radar
Global Change Biology, 2022
[PDF]
Keywords: radar ecology, phenology
Improving Few-Shot Part Segmentation using Coarse Supervision
European Conference on Computer Vision (ECCV), 2022
[PDF] [Source code] [Project Website]
Keywords: few-shot learning, part segmentation
GANORCON: Are Generative Models Useful for Few-shot Segmentation?
Computer Vision and Pattern Recognition (CVPR), 2022
[PDF] [Source code] [Project Website]
Keywords: few-shot segmentation, generative models
2021
On Equivariant and Invariant Learning of Object Landmark Representations
IEEE International Conference on Computer Vision (ICCV), 2021
[PDF] [Source code] [Project Website] [Poster] [arXiv]
Keywords: landmark learning, equivariance, invariance
AI for conservation: learning to track birds with radar
ACM XRDS, 2021
[PDF]
Keywords: computer vision for conservation, radar ecology
A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification
Computer Vision and Pattern Recognition (CVPR), 2021. (Oral)
[PDF] [Source code] [Poster] [Slides]
Keywords: semi-supervised learning, fine-grained classification
2020 and Earlier
Detecting and Tracking Communal Bird Roosts in Weather Radar Data
Association for the Advancement of Artificial Intelligence (AAAI), 2020. (Oral)
[PDF] [Source code] [Project Website] [arXiv] [Supplementary]
Keywords: radar ecology, object detection, tracking
A Bayesian Perspective on the Deep Image Prior
Computer Vision and Pattern Recognition (CVPR), 2019
[PDF] [Source code] [Project Website] [Poster] [Supplementary]
Keywords: deep image prior, Bayesian modeling
Colorization Using Neural Network Ensemble
IEEE Transactions on Image Processing (TIP), 2017
[PDF] [Source code] [Project Website]
Keywords: image colorization, neural networks
Deep Colorization
IEEE International Conference on Computer Vision (ICCV), 2015
[PDF] [Source code] [Project Website]
Keywords: image colorization, deep learning