Related papers: Unsupervised Visual Representation Learning by Tra…

We study self-supervised video representation learning, which is a challenging task due to 1) lack of labels for explicit supervision; 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video…

This paper describes recent developments in object specific pose and shape prediction from single images. The main contribution is a new approach to camera pose prediction by self-supervised learning of keypoints corresponding to locations…

Unsupervised visual representation learning offers the opportunity to leverage large corpora of unlabeled trajectories to form useful visual representations, which can benefit the training of reinforcement learning (RL) algorithms. However,…

Instance-level contrastive learning techniques, which rely on data augmentation and a contrastive loss function, have found great success in the domain of visual representation learning. They are not suitable for exploiting the rich…

We introduce DIP, a novel unsupervised post-training method designed to enhance dense image representations in large-scale pretrained vision encoders for in-context scene understanding. Unlike prior approaches that rely on complex…

Self-supervised visual representation learning traditionally focuses on image-level instance discrimination. Our study introduces an innovative, fine-grained dimension by integrating patch-level discrimination into these methodologies. This…

Though a large body of computer vision research has investigated developing generic semantic representations, efforts towards developing a similar representation for 3D has been limited. In this paper, we learn a generic 3D representation…

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,…

Many state-of-the-art trackers usually resort to the pretrained convolutional neural network (CNN) model for correlation filtering, in which deep features could usually be redundant, noisy and less discriminative for some certain instances,…

Videos are a rich source for self-supervised learning (SSL) of visual representations due to the presence of natural temporal transformations of objects. However, current methods typically randomly sample video clips for learning, which…

Video understanding relies on perceiving the global content and modeling its internal connections (e.g., causality, movement, and spatio-temporal correspondence). To learn these interactions, we apply a mask-then-predict pre-training task…

The use of self-supervised pre-training has emerged as a promising approach to enhance the performance of many different visual tasks. In this context, recent approaches have employed the Masked Image Modeling paradigm, which pre-trains a…

Research in child development has shown that embodied experience handling physical objects contributes to many cognitive abilities, including visual learning. One characteristic of such experience is that the learner sees the same object…

We present a large-scale study on unsupervised spatiotemporal representation learning from videos. With a unified perspective on four recent image-based frameworks, we study a simple objective that can easily generalize all these methods to…

Unlike quasi-static robotic manipulation tasks like pick-and-place, dynamic tasks such as non-prehensile manipulation pose greater challenges, especially for vision-based control. Successful control requires the extraction of features…

A growing body of research suggests that embodied gameplay, prevalent not just in human cultures but across a variety of animal species including turtles and ravens, is critical in developing the neural flexibility for creative problem…

We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA.…

Coordinate-based Multilayer Perceptron (MLP) networks, despite being capable of learning neural implicit representations, are not performant for internal image synthesis applications. Convolutional Neural Networks (CNNs) are typically used…

Deep networks have been successfully applied to visual tracking by learning a generic representation offline from numerous training images. However the offline training is time-consuming and the learned generic representation may be less…

This paper presents a novel approach for video-based person re-identification using multiple Convolutional Neural Networks (CNNs). Unlike previous work, we intend to extract a compact yet discriminative appearance representation from…