相关论文: Movie Box Office Prediction With Self-Supervised a…

While self-supervised learning has made rapid advances in natural language processing, it remains unclear when researchers should engage in resource-intensive domain-specific pretraining (domain pretraining). The law, puzzlingly, has…

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…

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…

We apply deep belief networks of restricted Boltzmann machines to bags of words of sift features obtained from databases of 13 Scenes, 15 Scenes and Caltech 256 and study experimentally their behavior and performance. We find that the final…

In order to autonomously learn wide repertoires of complex skills, robots must be able to learn from their own autonomously collected data, without human supervision. One learning signal that is always available for autonomously collected…

Pre-training and self-training are two approaches to semi-supervised learning. The comparison between pre-training and self-training has been explored. However, the previous works led to confusing findings: self-training outperforms…

Phrase grounding, the problem of associating image regions to caption words, is a crucial component of vision-language tasks. We show that phrase grounding can be learned by optimizing word-region attention to maximize a lower bound on…

Self-supervised learning techniques have shown their abilities to learn meaningful feature representation. This is made possible by training a model on pretext tasks that only requires to find correlations between inputs or parts of inputs.…

We introduce a novel self-supervised pretext task for learning representations from audio-visual content. Prior work on audio-visual representation learning leverages correspondences at the video level. Approaches based on audio-visual…

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…

Weakly supervised phrase grounding aims at learning region-phrase correspondences using only image-sentence pairs. A major challenge thus lies in the missing links between image regions and sentence phrases during training. To address this…

Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint…

The immense success of deep learning based methods in computer vision heavily relies on large scale training datasets. These richly annotated datasets help the network learn discriminative visual features. Collecting and annotating such…

Weakly supervised video grounding aims to localize temporal boundaries relevant to a given query without explicit ground-truth temporal boundaries. While existing methods primarily use Gaussian-based proposals, they overlook the importance…

Data labeling in supervised learning is considered an expensive and infeasible tool in some conditions. The self-supervised learning method is proposed to tackle the learning effectiveness with fewer labeled data, however, there is a lack…

This paper addresses the challenging task of weakly-supervised video temporal grounding. Existing approaches are generally based on the moment proposal selection framework that utilizes contrastive learning and reconstruction paradigm for…

Recent work considered how images paired with speech can be used as supervision for building speech systems when transcriptions are not available. We ask whether visual grounding can be used for cross-lingual keyword spotting: given a text…

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…

Predictive models have been at the core of many robotic systems, from quadrotors to walking robots. However, it has been challenging to develop and apply such models to practical robotic manipulation due to high-dimensional sensory…

Large language models (LLMs) have demonstrated that large-scale pretraining enables systems to adapt rapidly to new problems with little supervision in the language domain. This success, however, has not translated as effectively to the…