Recently, CLIP has been applied to pixel-level zero-shot learning tasks via a wo-stage
scheme. The general idea is to first generate class-agnostic region proposals and then feed …

Abstract Large-scale Vision-Language Models, such as CLIP, learn powerful image-text
representations that have found numerous applications, from zero-shot classification to text …

We present Neural Feature Fusion Fields (N3F),\a method that improves dense 2D image
feature extractors when the latter are applied to the analysis of multiple images …

Humans naturally decompose their environment into entities at the appropriate level of
abstraction to act in the world. Allowing machine learning algorithms to derive this …

Abstract We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility
function for CLIP's contrastive loss, intending to train an alignment between the patch tokens …

We present a new method for open-vocabulary universal image segmentation, which is
capable of performing instance, semantic, and panoptic segmentation under a unified …

Recent advances in large-scale pretraining have yielded visual foundation models with
strong capabilities. Not only can recent models generalize to arbitrary images for their …

Representing robotic manipulation tasks as constraints that associate the robot and the
environment is a promising way to encode desired robot behaviors. However, it remains …

Current referring video object segmentation (R-VOS) techniques extract conditional kernels
from encoded (low-resolution) vision-language features to segment the decoded high …

We present DINO-Tracker–a new framework for long-term dense tracking in video. The pillar
of our approach is combining test-time training on a single video, with the powerful localized …