相关论文: Semantics Meets Temporal Correspondence: Self-supe…

Current top-leading solutions for video object segmentation (VOS) typically follow a matching-based regime: for each query frame, the segmentation mask is inferred according to its correspondence to previously processed and the first…

Unsupervised representation learning methods like SwAV are proved to be effective in learning visual semantics of a target dataset. The main idea behind these methods is that different views of a same image represent the same semantics. In…

We propose a novel self-supervised approach for learning audio and visual representations from unlabeled videos, based on their correspondence. The approach uses an attention mechanism to learn the relative importance of convolutional…

We study the task of establishing object-level visual correspondence across different viewpoints in videos, focusing on the challenging egocentric-to-exocentric and exocentric-to-egocentric scenarios. We propose a simple yet effective…

Self-supervised tasks such as colorization, inpainting and zigsaw puzzle have been utilized for visual representation learning for still images, when the number of labeled images is limited or absent at all. Recently, this worthwhile stream…

Traditional video captioning requests a holistic description of the video, yet the detailed descriptions of the specific objects may not be available. Without associating the moving trajectories, these image-based data-driven methods cannot…

Video moment retrieval aims to search the moment most relevant to a given language query. However, most existing methods in this community often require temporal boundary annotations which are expensive and time-consuming to label. Hence…

Self-supervised learning holds the promise of learning good representations from real-world continuous uncurated data streams. However, most existing works in visual self-supervised learning focus on static images or artificial data…

We introduce a self-supervised method for learning visual correspondence from unlabeled video. The main idea is to use cycle-consistency in time as free supervisory signal for learning visual representations from scratch. At training time,…

Sentence-level classification and sequential labeling are two fundamental tasks in language understanding. While these two tasks are usually modeled separately, in reality, they are often correlated, for example in intent classification and…

Supervised learning for semantic segmentation requires a large number of labeled samples, which is difficult to obtain in the field of remote sensing. Self-supervised learning (SSL), can be used to solve such problems by pre-training a…

To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our key finding is to learn such representations by separating…

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.…

High resolution satellite image sequences are multidimensional signals composed of spatio-temporal patterns associated to numerous and various phenomena. Bayesian methods have been previously proposed in (Heas and Datcu, 2005) to code the…

Recent advances in language modeling have witnessed the rise of highly desirable emergent capabilities, such as reasoning and in-context learning. However, vision models have yet to exhibit comparable progress in these areas. In this paper,…

Pedestrian detection plays an important role in many applications such as autonomous driving. We propose a method that explores semantic segmentation results as self-attention cues to significantly improve the pedestrian detection…

Weakly supervised semantic segmentation (WSSS) based on image-level labels is challenging since it is hard to obtain complete semantic regions. To address this issue, we propose a self-training method that utilizes fused multi-scale…

In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…

Semi-Supervised Learning can be more beneficial for the video domain compared to images because of its higher annotation cost and dimensionality. Besides, any video understanding task requires reasoning over both spatial and temporal…

In many computer vision tasks, the relevant information to solve the problem at hand is mixed to irrelevant, distracting information. This has motivated researchers to design attentional models that can dynamically focus on parts of images…