Related papers: Learning Unsupervised Visual Grounding Through Sem…
Visual localization is one of the most important components for robotics and autonomous driving. Recently, inspiring results have been shown with CNN-based methods which provide a direct formulation to end-to-end regress 6-DoF absolute…
This paper demonstrates a self-supervised approach for learning semantic video representations. Recent vision studies show that a masking strategy for vision and natural language supervision has contributed to developing transferable visual…
Textual grounding is an important but challenging task for human-computer interaction, robotics and knowledge mining. Existing algorithms generally formulate the task as selection from a set of bounding box proposals obtained from deep net…
This paper presents an approach for grounding phrases in images which jointly learns multiple text-conditioned embeddings in a single end-to-end model. In order to differentiate text phrases into semantically distinct subspaces, we propose…
Grounding free-form textual queries necessitates an understanding of these textual phrases and its relation to the visual cues to reliably reason about the described locations. Spatial attention networks are known to learn this relationship…
Supervised or weakly supervised methods for phrase localization (textual grounding) either rely on human annotations or some other supervised models, e.g., object detectors. Obtaining these annotations is labor-intensive and may be…
Self-supervised learning aims to learn representations from the data itself without explicit manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning - the ability to scale to large amount of data because…
Visual grounding localizes regions (boxes or segments) in the image corresponding to given referring expressions. In this work we address image segmentation from referring expressions, a problem that has so far only been addressed in a…
Robots have the capability to collect large amounts of data autonomously by interacting with objects in the world. However, it is often not obvious \emph{how} to learning from autonomously collected data without human-labeled supervision.…
State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any…
Unsupervised learning of keypoints and landmarks has seen significant progress with the help of modern neural network architectures, but performance is yet to match the supervised counterpart, making their practicability questionable. We…
Pretrained language models are long known to be subpar in capturing sentence and document-level semantics. Though heavily investigated, transferring perturbation-based methods from unsupervised visual representation learning to NLP remains…
Today's most accurate language models are trained on orders of magnitude more language data than human language learners receive - but with no supervision from other sensory modalities that play a crucial role in human learning. Can we make…
Any city-scale visual localization system has to overcome long-term appearance changes, such as varying illumination conditions or seasonal changes between query and database images. Since semantic content is more robust to such changes, we…
Concept learning constructs visual representations that are connected to linguistic semantics, which is fundamental to vision-language tasks. Although promising progress has been made, existing concept learners are still vulnerable to…
We explore the power of spatial context as a self-supervisory signal for learning visual representations. In particular, we propose spatial context networks that learn to predict a representation of one image patch from another image patch,…
Self-supervised learning is showing great promise for monocular depth estimation, using geometry as the only source of supervision. Depth networks are indeed capable of learning representations that relate visual appearance to 3D properties…
Sentence representation models trained only on language could potentially suffer from the grounding problem. Recent work has shown promising results in improving the qualities of sentence representations by jointly training them with…
We introduce a new dataset for training and evaluating grounded language models. Our data is collected within a virtual reality environment and is designed to emulate the quality of language data to which a pre-verbal child is likely to…
Current unsupervised image-to-image translation techniques struggle to focus their attention on individual objects without altering the background or the way multiple objects interact within a scene. Motivated by the important role of…