Related papers: Scaling 4D Representations
Neural fields excel in computer vision and robotics due to their ability to understand the 3D visual world such as inferring semantics, geometry, and dynamics. Given the capabilities of neural fields in densely representing a 3D scene from…
Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about determining the right inductive bias in diverse scenarios.…
Modern video summarization methods are based on deep neural networks that require a large amount of annotated data for training. However, existing datasets for video summarization are small-scale, easily leading to over-fitting of the deep…
Unsupervised learning has always been appealing to machine learning researchers and practitioners, allowing them to avoid an expensive and complicated process of labeling the data. However, unsupervised learning of complex data is…
Video representation learning has seen tremendous progress in recent years. This has been driven by many factors, including the scale of training and the success of visual models trained contrastively with language. While these factors have…
In the context of mobile sensing environments, various sensors on mobile devices continually generate a vast amount of data. Analyzing this ever-increasing data presents several challenges, including limited access to annotated data and a…
Self-supervised approaches for video have shown impressive results in video understanding tasks. However, unlike early works that leverage temporal self-supervision, current state-of-the-art methods primarily rely on tasks from the image…
We witnessed a massive growth in the supervised learning paradigm in the past decade. Supervised learning requires a large amount of labeled data to reach state-of-the-art performance. However, labeling the samples requires a lot of human…
The objective of this paper is self-supervised learning from video, in particular for representations for action recognition. We make the following contributions: (i) We propose a new architecture and learning framework Memory-augmented…
In the fast-evolving field of artificial intelligence, where models are increasingly growing in complexity and size, the availability of labeled data for training deep learning models has become a significant challenge. Addressing complex…
Self-supervised learning has emerged as a powerful paradigm for label-free model pretraining, particularly in the video domain, where manual annotation is costly and time-intensive. However, existing self-supervised approaches employ…
Videos captured from multiple viewpoints can help in perceiving the 3D structure of the world and benefit computer vision tasks such as action recognition, tracking, etc. In this paper, we present a method for self-supervised learning from…
A key challenge of learning a visual representation for the 3D high fidelity geometry of dressed humans lies in the limited availability of the ground truth data (e.g., 3D scanned models), which results in the performance degradation of 3D…
The objective of this paper is self-supervised learning of spatio-temporal embeddings from video, suitable for human action recognition. We make three contributions: First, we introduce the Dense Predictive Coding (DPC) framework for…
This paper presents TCE: Temporally Coherent Embeddings for self-supervised video representation learning. The proposed method exploits inherent structure of unlabeled video data to explicitly enforce temporal coherency in the embedding…
Unsupervised representation learning aims at finding methods that learn representations from data without annotation-based signals. Abstaining from annotations not only leads to economic benefits but may - and to some extent already does -…
Remote sensing images present unique challenges to image analysis due to the extensive geographic coverage, hardware limitations, and misaligned multi-scale images. This paper revisits the classical multi-scale representation learning…
Visual data such as images and videos are typically modeled as discretizations of inherently continuous, multidimensional signals. Existing continuous-signal models attempt to exploit this fact by modeling the underlying signals of visual…
The purpose of the research is to determine if currently available self-supervised learning techniques can accomplish human level comprehension of visual images using the same degree and amount of sensory input that people acquire from.…
It is known that representations from self-supervised pre-training can perform on par, and often better, on various downstream tasks than representations from fully-supervised pre-training. This has been shown in a host of settings such as…