WACV 2023 We propose Attentive Feature Aggregation (AFA) to exploit both spatial and channel information for semantic segmentation and boundary detection.
CoRL 2022 We propose a method for panoramic 3D object tracking, called CC-3DT, that associates and models object trajectories both temporally and across views.
RA-L 2022 This paper introduces a ray-based volumetric uncertainty estimator, which computes the entropy of the weight distribution of the color samples along each ray of the object’s implicit neural representation.
ECCV 2022 We introduce a new metric, Track Every Thing Accuracy (TETA), and a Track Every Thing tracker (TETer), which performs association using Class Exemplar Matching (CEM).
ECCV 2022 We propose Video Mask Transfiner (VMT) method, capable of leveraging fine-grained high-resolution features thanks to a highly efficient video transformer structure.
ECCV 2022 We propose SAGA (StochAstic whole-body Grasping with contAct).
ECCV 2022 Our method fuses multi-sensor depth streams regardless of time synchronization and calibration and generalizes well with little training data.
ECCV 2022 We introduce the more general taxonomy adaptive cross-domain semantic segmentation (TACS) problem, allowing for inconsistent taxonomies between the two domains.
CVPR 2022 we present Mask Transfiner for high-quality and efficient instance segmentation, which predicts highly accurate instance masks at a low computational cost using quadtree transformer.
CVPR 2022 We introduce the largest synthetic dataset for autonomous driving to study continuous domain adaptation and multi-task perception.
CVPR 2022 We propose Probabilistic Warp Consistency, a weakly-supervised learning objective for semantic matching.
CVPR 2022 We propose a tracker architecture employing a Transformer-based model prediction module.
CVPR 2022 Our method exploits the low frequency of anomalies towards building a cross-supervision between a generator and a discriminator.
CVPR 2022 We propose a Denoising Diffusion Probabilistic Model (DDPM) based inpainting approach that is applicable to even extreme masks.
CVPR 2022 Oral We propose a physically based method to simulate the effect of snowfall on real clear weather LiDAR point clouds.
ICML 2022 We provide a taxonomy of DUMs, evaluate their calibration under continuous distributional shifts, and extend them to semantic segmentation.
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.
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.
WACV 2022 We explore general flows as a fidelity-based alternative to the L1 objective.
NeurIPS 2021 Spotlight We propose Prototypical Cross-Attention Network (PCAN), capable of leveraging rich spatio-temporal information for online multiple object tracking and segmentation.
ICCV 2021 We study the effectiveness of auxiliary self-supervised tasks to improve the out-of-distribution generalization of object detectors.
ICCV 2021 Oral We propose Warp Consistency, an unsupervised learning objective for dense correspondence regression.
ICCV 2021 Oral We propose a pixel-wise contrastive algorithm for semantic segmentation in the fully supervised setting.
ICCV 2021 Oral We propose a deep reparametrization of the maximum a posteriori formulation commonly employed in multi-frame image restoration tasks.