Publications

Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences

Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences

CVPR 2022 We propose Probabilistic Warp Consistency, a weakly-supervised learning objective for semantic matching.

Transforming Model Prediction for Tracking

Transforming Model Prediction for Tracking

CVPR 2022 We propose a tracker architecture employing a Transformer-based model prediction module.

Generative Cooperative Learning for Unsupervised Video Anomaly Detection

Generative Cooperative Learning for Unsupervised Video Anomaly Detection

CVPR 2022 Our method exploits the low frequency of anomalies towards building a cross-supervision between a generator and a discriminator.

RePaint: Inpainting using Denoising Diffusion Probabilistic Models

RePaint: Inpainting using Denoising Diffusion Probabilistic Models

CVPR 2022 We propose a Denoising Diffusion Probabilistic Model (DDPM) based inpainting approach that is applicable to even extreme masks.

LiDAR Snowfall Simulation for Robust 3D Object Detection

LiDAR Snowfall Simulation for Robust 3D Object Detection

CVPR 2022 Oral We propose a physically based method to simulate the effect of snowfall on real clear weather LiDAR point clouds.

On the Practicality of Deterministic Epistemic Uncertainty

On the Practicality of Deterministic Epistemic Uncertainty

ICML 2022 We provide a taxonomy of DUMs, evaluate their calibration under continuous distributional shifts, and extend them to semantic segmentation.

Fast Hierarchical Learning for Few-Shot Object Detection

Fast Hierarchical Learning for Few-Shot Object Detection

IROS 2022 We pose few-shot detection as a hierarchical learning problem, where the novel classes are treated as the child classes of existing base classes and the background class.

Monocular Quasi-Dense 3D Object Tracking

Monocular Quasi-Dense 3D Object Tracking

TPAMI 2022 We combine quasi-dense tracking on 2D images and motion prediction in 3D space to achieve significant advance in 3D object tracking from monocular videos.

Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic Super-resolution

Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic Super-resolution

WACV 2022 We explore general flows as a fidelity-based alternative to the L1 objective.

Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation

Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation

NeurIPS 2021 Spotlight We propose Prototypical Cross-Attention Network (PCAN), capable of leveraging rich spatio-temporal information for online multiple object tracking and segmentation.

Robust Object Detection via Instance-Level Temporal Cycle Confusion

Robust Object Detection via Instance-Level Temporal Cycle Confusion

ICCV 2021 We study the effectiveness of auxiliary self-supervised tasks to improve the out-of-distribution generalization of object detectors.

Warp Consistency for Unsupervised Learning of Dense Correspondences

Warp Consistency for Unsupervised Learning of Dense Correspondences

ICCV 2021 Oral We propose Warp Consistency, an unsupervised learning objective for dense correspondence regression.

Exploring Cross-Image Pixel Contrast for Semantic Segmentation

Exploring Cross-Image Pixel Contrast for Semantic Segmentation

ICCV 2021 Oral We propose a pixel-wise contrastive algorithm for semantic segmentation in the fully supervised setting.

Deep Reparametrization of Multi-Frame Super-Resolution and Denoising

Deep Reparametrization of Multi-Frame Super-Resolution and Denoising

ICCV 2021 Oral We propose a deep reparametrization of the maximum a posteriori formulation commonly employed in multi-frame image restoration tasks.

End-to-End Urban Driving by Imitating a Reinforcement Learning Coach

End-to-End Urban Driving by Imitating a Reinforcement Learning Coach

ICCV 2021 We demonstrated that an RL coach (Roach) would be a better choice to supervise imitation learning agents.

Quasi-Dense Similarity Learning for Multiple Object Tracking

Quasi-Dense Similarity Learning for Multiple Object Tracking

CVPR 2021 Oral We propose a simple yet effective multi-object tracking method in this paper.

Instance-Aware Predictive Navigation in Multi-Agent Environments

Instance-Aware Predictive Navigation in Multi-Agent Environments

ICRA 2021 A new visual model-based RL method with consideration of multiple hypotheses for future object movement.

BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning

BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning

CVPR 2020 Oral The largest driving video dataset for heterogeneous multitask learning.

Frustratingly Simple Few-Shot Object Detection

Frustratingly Simple Few-Shot Object Detection

ICML 2020 State-of-the-art few-shot detection method with backpropagation learning.

Learning Saliency Propagation for Semi-Supervised Instance Segmentation

Learning Saliency Propagation for Semi-Supervised Instance Segmentation

CVPR 2020 We propose a ShapeProp module to propagate information between object detection and segmentation supervisions for Semi-Supervised Instance Segmentation.

Joint Monocular 3D Vehicle Detection and Tracking

Joint Monocular 3D Vehicle Detection and Tracking

ICCV 2019 We propose a novel online framework for 3D vehicle detection and tracking from monocular videos.

Disentangling Propagation and Generation for Video Prediction

Disentangling Propagation and Generation for Video Prediction

ICCV 2019 We describe a computational model for high-fidelity video prediction which disentangles motion-specific propagation from motion-agnostic generation.

Few Shot Object Detection via Feature Reweighting

Few Shot Object Detection via Feature Reweighting

ICCV 2019 We develop a few-shot object detector that can learn to detect novel objects from only a few annotated examples.

Deep Mixture of Experts via Shallow Embedding

Deep Mixture of Experts via Shallow Embedding

UAI 2019 We explore a mixture of experts (MoE) approach to deep dynamic routing, which activates certain experts in the network on a per-example basis.